Search

Estimating full-body motion using the tracking signals of head and hands from VR devices holds great potential for various applications. However, the sparsity and unique distribution of observations present a significant challenge, resulting in an ill-posed problem with multiple feasible solutions (i.e., hypotheses). This amplifies uncertainty and ambiguity in full-body motion estimation, especially for the lower-body joints. Therefore, we propose a new method, EnvPoser, that employs a two-stage framework to perform full-body motion estimation using sparse tracking signals and pre-scanned environment from VR devices. EnvPoser models the multi-hypothesis nature of human motion through an uncertainty-aware estimation module in the first stage. In the second stage, we refine these multi-hypothesis estimates by integrating semantic and geometric environmental constraints, ensuring that the final motion estimation aligns realistically with both the environmental context and physical interactions. Qualitative and quantitative experiments on two public datasets demonstrate that our method achieves state-of-the-art performance, highlighting significant improvements in human motion estimation within motion-environment interaction scenarios.

The number of categories of instances in the real world is normally huge, and each instance may contain multiple labels. To distinguish these massive labels utilizing machine learning, eXtreme Label Classification (XLC) has been established. However, as the number of categories increases, the number of parameters and nonlinear operations in the classifier also rises. This results in a Classifier Computational Overload Problem (CCOP). To address this, we propose a Multi-Head Encoding (MHE) mechanism, which replaces the vanilla classifier with a multi-head classifier. During the training process, MHE decomposes extreme labels into the product of multiple short local labels, with each head trained on these local labels. During testing, the predicted labels can be directly calculated from the local predictions of each head. This reduces the computational load geometrically. Then, according to the characteristics of different XLC tasks, e.g., single-label, multi-label, and model pretraining tasks, three MHE-based implementations, i.e., Multi-Head Product, Multi-Head Cascade, and Multi-Head Sampling, are proposed to more effectively cope with CCOP. Moreover, we theoretically demonstrate that MHE can achieve performance approximately equivalent to that of the vanilla classifier by generalizing the low-rank approximation problem from Frobenius-norm to Cross-Entropy. Experimental results show that the proposed methods achieve state-of-the-art performance while significantly streamlining the training and inference processes of XLC tasks. The source code has been made public at https://github.com/Anoise/MHE., Comment: 20 pages, 12 figs, Published in TPAMI

Graphs are ubiquitous data structures found in numerous real-world applications, such as drug discovery, recommender systems, and social network analysis. Graph neural networks (GNNs) have become a popular tool to learn node embeddings through message passing on these structures. However, a significant challenge arises when applying GNNs to multiple graphs with different feature spaces, as existing GNN architectures are not designed for cross-graph feature alignment. To address this, recent approaches introduce text-attributed graphs, where each node is associated with a textual description, enabling the use of a shared textual encoder to project nodes from different graphs into a unified feature space. While promising, this method relies heavily on the availability of text-attributed data, which can be difficult to obtain in practice. To bridge this gap, we propose a novel method named Topology-Aware Node description Synthesis (TANS), which leverages large language models (LLMs) to automatically convert existing graphs into text-attributed graphs. The key idea is to integrate topological information with each node's properties, enhancing the LLMs' ability to explain how graph topology influences node semantics. We evaluate our TANS on text-rich, text-limited, and text-free graphs, demonstrating that it enables a single GNN to operate across diverse graphs. Notably, on text-free graphs, our method significantly outperforms existing approaches that manually design node features, showcasing the potential of LLMs for preprocessing graph-structured data, even in the absence of textual information. The code and data are available at https://github.com/Zehong-Wang/TANS.

As AI continues to advance, there is a growing demand for systems that go beyond language-based assistance and move toward intelligent agents capable of performing real-world actions. This evolution requires the transition from traditional Large Language Models (LLMs), which excel at generating textual responses, to Large Action Models (LAMs), designed for action generation and execution within dynamic environments. Enabled by agent systems, LAMs hold the potential to transform AI from passive language understanding to active task completion, marking a significant milestone in the progression toward artificial general intelligence. In this paper, we present a comprehensive framework for developing LAMs, offering a systematic approach to their creation, from inception to deployment. We begin with an overview of LAMs, highlighting their unique characteristics and delineating their differences from LLMs. Using a Windows OS-based agent as a case study, we provide a detailed, step-by-step guide on the key stages of LAM development, including data collection, model training, environment integration, grounding, and evaluation. This generalizable workflow can serve as a blueprint for creating functional LAMs in various application domains. We conclude by identifying the current limitations of LAMs and discussing directions for future research and industrial deployment, emphasizing the challenges and opportunities that lie ahead in realizing the full potential of LAMs in real-world applications. The code for the data collection process utilized in this paper is publicly available at: https://github.com/microsoft/UFO/tree/main/dataflow, and comprehensive documentation can be found at https://microsoft.github.io/UFO/dataflow/overview/., Comment: 25pages,12 figures

In today's digital landscape, the blending of AI-generated and authentic content has underscored the need for copyright protection and content authentication. Watermarking has become a vital tool to address these challenges, safeguarding both generated and real content. Effective watermarking methods must withstand various distortions and attacks. Current deep watermarking techniques often use an encoder-noise layer-decoder architecture and include distortions to enhance robustness. However, they struggle to balance robustness and fidelity and remain vulnerable to adaptive attacks, despite extensive training. To overcome these limitations, we propose SuperMark, a robust, training-free watermarking framework. Inspired by the parallels between watermark embedding/extraction in watermarking and the denoising/noising processes in diffusion models, SuperMark embeds the watermark into initial Gaussian noise using existing techniques. It then applies pre-trained Super-Resolution (SR) models to denoise the watermarked noise, producing the final watermarked image. For extraction, the process is reversed: the watermarked image is inverted back to the initial watermarked noise via DDIM Inversion, from which the embedded watermark is extracted. This flexible framework supports various noise injection methods and diffusion-based SR models, enabling enhanced customization. The robustness of the DDIM Inversion process against perturbations allows SuperMark to achieve strong resilience to distortions while maintaining high fidelity. Experiments demonstrate that SuperMark achieves fidelity comparable to existing methods while significantly improving robustness. Under standard distortions, it achieves an average watermark extraction accuracy of 99.46%, and 89.29% under adaptive attacks. Moreover, SuperMark shows strong transferability across datasets, SR models, embedding methods, and resolutions., Comment: robust image watermarking

Classifier-free guidance (CFG) is widely used in diffusion models but often introduces over-contrast and over-saturation artifacts at higher guidance strengths. We present EP-CFG (Energy-Preserving Classifier-Free Guidance), which addresses these issues by preserving the energy distribution of the conditional prediction during the guidance process. Our method simply rescales the energy of the guided output to match that of the conditional prediction at each denoising step, with an optional robust variant for improved artifact suppression. Through experiments, we show that EP-CFG maintains natural image quality and preserves details across guidance strengths while retaining CFG's semantic alignment benefits, all with minimal computational overhead.

This study employs a novel approach for reconstructing the thermal Sunyaev-Zeldovich (tSZ) effect power spectrum from Planck data using the Analytical Blind Separation (ABS) method. The ABS method improves the recovery of weak signals, by applying eigenmode exclusion for low signal-to-noise ratio regimes and introducing a shift parameter to stabilize calculations. Validation through simulated Planck data demonstrates the robustness of ABS in reconstructing the tSZ power spectrum, even under challenging conditions. In the analysis of the Planck PR3 full-mission data, ABS shows lower amplitudes at $\ell \gtrsim 300$ compared to the Planck 2015 band powers using the MILCA and NILC foreground cleaning methods. After marginalizing over residual foreground components, the ABS analysis finds the overall tSZ power spectrum amplitude to be 20\% lower than the Planck best-fit one, suggesting a smaller $S_8$. At $\ell \simeq 200$, the tSZ band power is $10^{12} \ell(\ell+1)C^{yy}_\ell/(2\pi) = 0.126\pm 0.018$, largely independent of the tSZ model choice. These findings highlight the potential of the ABS method as a promising alternative for tSZ power spectrum analysis, offering a robust and independent means of extracting cosmological parameters.

As a fundamental vision task, stereo matching has made remarkable progress. While recent iterative optimization-based methods have achieved promising performance, their feature extraction capabilities still have room for improvement. Inspired by the ability of vision foundation models (VFMs) to extract general representations, in this work, we propose AIO-Stereo which can flexibly select and transfer knowledge from multiple heterogeneous VFMs to a single stereo matching model. To better reconcile features between heterogeneous VFMs and the stereo matching model and fully exploit prior knowledge from VFMs, we proposed a dual-level feature utilization mechanism that aligns heterogeneous features and transfers multi-level knowledge. Based on the mechanism, a dual-level selective knowledge transfer module is designed to selectively transfer knowledge and integrate the advantages of multiple VFMs. Experimental results show that AIO-Stereo achieves start-of-the-art performance on multiple datasets and ranks $1^{st}$ on the Middlebury dataset and outperforms all the published work on the ETH3D benchmark., Comment: Accepted by AAAI 2025

Zero-shot action recognition (ZSAR) requires collaborative multi-modal spatiotemporal understanding. However, finetuning CLIP directly for ZSAR yields suboptimal performance, given its inherent constraints in capturing essential temporal dynamics from both vision and text perspectives, especially when encountering novel actions with fine-grained spatiotemporal discrepancies. In this work, we propose Spatiotemporal Dynamic Duo (STDD), a novel CLIP-based framework to comprehend multi-modal spatiotemporal dynamics synergistically. For the vision side, we propose an efficient Space-time Cross Attention, which captures spatiotemporal dynamics flexibly with simple yet effective operations applied before and after spatial attention, without adding additional parameters or increasing computational complexity. For the semantic side, we conduct spatiotemporal text augmentation by comprehensively constructing an Action Semantic Knowledge Graph (ASKG) to derive nuanced text prompts. The ASKG elaborates on static and dynamic concepts and their interrelations, based on the idea of decomposing actions into spatial appearances and temporal motions. During the training phase, the frame-level video representations are meticulously aligned with prompt-level nuanced text representations, which are concurrently regulated by the video representations from the frozen CLIP to enhance generalizability. Extensive experiments validate the effectiveness of our approach, which consistently surpasses state-of-the-art approaches on popular video benchmarks (i.e., Kinetics-600, UCF101, and HMDB51) under challenging ZSAR settings. Code is available at https://github.com/Mia-YatingYu/STDD., Comment: Accepted by AAAI 2025

In this paper, we present an advanced strategy for the coordinated control of a multi-agent aerospace system, utilizing Deep Neural Networks (DNNs) within a reinforcement learning framework. Our approach centers on optimizing autonomous task assignment to enhance the system's operational efficiency in object relocation tasks, framed as an aerospace-oriented pick-and-place scenario. By modeling this coordination challenge within a MuJoCo environment, we employ a deep reinforcement learning algorithm to train a DNN-based policy to maximize task completion rates across the multi-agent system. The objective function is explicitly designed to maximize effective object transfer rates, leveraging neural network capabilities to handle complex state and action spaces in high-dimensional aerospace environments. Through extensive simulation, we benchmark the proposed method against a heuristic combinatorial approach rooted in game-theoretic principles, demonstrating a marked performance improvement, with the trained policy achieving up to 16\% higher task efficiency. Experimental validation is conducted on a multi-agent hardware setup to substantiate the efficacy of our approach in a real-world aerospace scenario.

Knowledge distillation (KD) is a model compression technique that transfers knowledge from a large teacher model to a smaller student model to enhance its performance. Existing methods often assume that the student model is inherently inferior to the teacher model. However, we identify that the fundamental issue affecting student performance is the bias transferred by the teacher. Current KD frameworks transmit both right and wrong knowledge, introducing bias that misleads the student model. To address this issue, we propose a novel strategy to rectify bias and greatly improve the student model's performance. Our strategy involves three steps: First, we differentiate knowledge and design a bias elimination method to filter out biases, retaining only the right knowledge for the student model to learn. Next, we propose a bias rectification method to rectify the teacher model's wrong predictions, fundamentally addressing bias interference. The student model learns from both the right knowledge and the rectified biases, greatly improving its prediction accuracy. Additionally, we introduce a dynamic learning approach with a loss function that updates weights dynamically, allowing the student model to quickly learn right knowledge-based easy tasks initially and tackle hard tasks corresponding to biases later, greatly enhancing the student model's learning efficiency. To the best of our knowledge, this is the first strategy enabling the student model to surpass the teacher model. Experiments demonstrate that our strategy, as a plug-and-play module, is versatile across various mainstream KD frameworks. We will release our code after the paper is accepted.

Observations of the intracluster medium (ICM) in the outskirts of galaxy clusters reveal shocks associated with gas accretion from the cosmic web. Previous work based on non-radiative cosmological hydrodynamical simulations have defined the shock radius, $r_\text{shock}$, using the ICM entropy, $K \propto T/{n_\mathrm{e}}^{2/3}$, where $T$ and $n_\text{e}$ are the ICM temperature and electron density respectively; the $r_\text{shock}$ is identified with either the radius at which $K$ is a maximum or at which its logarithmic slope is a minimum. We investigate the relationship between $r_\text{shock}$, which is driven by gravitational hydrodynamics and shocks, and the splashback radius, $r_\text{splash}$, which is driven by the gravitational dynamics of cluster stars and dark matter and is measured from their mass profile. Using 324 clusters from {\small The Three Hundred} project of cosmological galaxy formation simulations, we quantify statistically how $r_\text{shock}$ relates to $r_\text{splash}$. Depending on our definition, we find that the median $r_\text{shock} \simeq 1.38 r_\text{splash} (2.58 R_{200})$ when $K$ reaches its maximum and $r_\text{shock} \simeq 1.91 r_\text{splash} (3.54 R_{200})$ when its logarithmic slope is a minimum; the best-fit linear relation increases as $r_\text{shock} \propto 0.65 r_\text{splash}$. We find that $r_\text{shock}/R_{200}$ and $r_\text{splash}/R_{200}$ anti-correlate with virial mass, $M_{200}$, and recent mass accretion history, and $r_\text{shock}/r_\text{splash}$ tends to be larger for clusters with higher recent accretion rates. We discuss prospects for measuring $r_\text{shock}$ observationally and how the relationship between $r_\text{shock}$ and $r_\text{splash}$ can be used to improve constraints from radio, X-ray, and thermal Sunyaev-Zeldovich surveys that target the interface between the cosmic web and clusters., Comment: 11 pages, 6 figures; accepted for publication in the Publications of the Astronomical Society of Australia (PASA)

Fock-state lattices (FSLs), composed of photon number states with infinite Hilbert space, have emerged as a promising platform for simulating high-dimensional physics due to their potential to extend into arbitrarily high dimensions. Here, we demonstrate the construction of multi-dimensional FSLs using superconducting quantum circuits. By controlling artificial gauge fields within their internal structures, we investigate flux-induced extreme localization dynamics, such as Aharonov-Bohm caging, extending from 2D to 3D. We also explore the coherent interference of quantum superposition states, achieving extreme localization within specific subspaces assisted by quantum entanglement. Our findings pave the way for manipulating the behavior of a broad class of quantum states in higher-dimensional systems., Comment: 6+23 pages; 4+18 figures

The effectiveness of large language models (LLMs) is closely tied to the design of prompts, making prompt optimization essential for enhancing their performance across a wide range of tasks. Many existing approaches to automating prompt engineering rely exclusively on textual feedback, refining prompts based solely on inference errors identified by large, computationally expensive LLMs. Unfortunately, smaller models struggle to generate high-quality feedback, resulting in complete dependence on large LLM judgment. Moreover, these methods fail to leverage more direct and finer-grained information, such as gradients, due to operating purely in text space. To this end, we introduce GReaTer, a novel prompt optimization technique that directly incorporates gradient information over task-specific reasoning. By utilizing task loss gradients, GReaTer enables self-optimization of prompts for open-source, lightweight language models without the need for costly closed-source LLMs. This allows high-performance prompt optimization without dependence on massive LLMs, closing the gap between smaller models and the sophisticated reasoning often needed for prompt refinement. Extensive evaluations across diverse reasoning tasks including BBH, GSM8k, and FOLIO demonstrate that GReaTer consistently outperforms previous state-of-the-art prompt optimization methods, even those reliant on powerful LLMs. Additionally, GReaTer-optimized prompts frequently exhibit better transferability and, in some cases, boost task performance to levels comparable to or surpassing those achieved by larger language models, highlighting the effectiveness of prompt optimization guided by gradients over reasoning. Code of GReaTer is available at https://github.com/psunlpgroup/GreaTer., Comment: 32 pages, 8 figures

Visual diffusion models achieve remarkable progress, yet they are typically trained at limited resolutions due to the lack of high-resolution data and constrained computation resources, hampering their ability to generate high-fidelity images or videos at higher resolutions. Recent efforts have explored tuning-free strategies to exhibit the untapped potential higher-resolution visual generation of pre-trained models. However, these methods are still prone to producing low-quality visual content with repetitive patterns. The key obstacle lies in the inevitable increase in high-frequency information when the model generates visual content exceeding its training resolution, leading to undesirable repetitive patterns deriving from the accumulated errors. To tackle this challenge, we propose FreeScale, a tuning-free inference paradigm to enable higher-resolution visual generation via scale fusion. Specifically, FreeScale processes information from different receptive scales and then fuses it by extracting desired frequency components. Extensive experiments validate the superiority of our paradigm in extending the capabilities of higher-resolution visual generation for both image and video models. Notably, compared with the previous best-performing method, FreeScale unlocks the generation of 8k-resolution images for the first time., Comment: Project Page: http://haonanqiu.com/projects/FreeScale.html

As virtual reality gains popularity, the demand for controllable creation of immersive and dynamic omnidirectional videos (ODVs) is increasing. While previous text-to-ODV generation methods achieve impressive results, they struggle with content inaccuracies and inconsistencies due to reliance solely on textual inputs. Although recent motion control techniques provide fine-grained control for video generation, directly applying these methods to ODVs often results in spatial distortion and unsatisfactory performance, especially with complex spherical motions. To tackle these challenges, we propose OmniDrag, the first approach enabling both scene- and object-level motion control for accurate, high-quality omnidirectional image-to-video generation. Building on pretrained video diffusion models, we introduce an omnidirectional control module, which is jointly fine-tuned with temporal attention layers to effectively handle complex spherical motion. In addition, we develop a novel spherical motion estimator that accurately extracts motion-control signals and allows users to perform drag-style ODV generation by simply drawing handle and target points. We also present a new dataset, named Move360, addressing the scarcity of ODV data with large scene and object motions. Experiments demonstrate the significant superiority of OmniDrag in achieving holistic scene-level and fine-grained object-level control for ODV generation. The project page is available at https://lwq20020127.github.io/OmniDrag.

Creating AI systems that can interact with environments over long periods, similar to human cognition, has been a longstanding research goal. Recent advancements in multimodal large language models (MLLMs) have made significant strides in open-world understanding. However, the challenge of continuous and simultaneous streaming perception, memory, and reasoning remains largely unexplored. Current MLLMs are constrained by their sequence-to-sequence architecture, which limits their ability to process inputs and generate responses simultaneously, akin to being unable to think while perceiving. Furthermore, relying on long contexts to store historical data is impractical for long-term interactions, as retaining all information becomes costly and inefficient. Therefore, rather than relying on a single foundation model to perform all functions, this project draws inspiration from the concept of the Specialized Generalist AI and introduces disentangled streaming perception, reasoning, and memory mechanisms, enabling real-time interaction with streaming video and audio input. The proposed framework InternLM-XComposer2.5-OmniLive (IXC2.5-OL) consists of three key modules: (1) Streaming Perception Module: Processes multimodal information in real-time, storing key details in memory and triggering reasoning in response to user queries. (2) Multi-modal Long Memory Module: Integrates short-term and long-term memory, compressing short-term memories into long-term ones for efficient retrieval and improved accuracy. (3) Reasoning Module: Responds to queries and executes reasoning tasks, coordinating with the perception and memory modules. This project simulates human-like cognition, enabling multimodal large language models to provide continuous and adaptive service over time., Comment: Github Repo: https://github.com/InternLM/InternLM-XComposer/tree/main/InternLM-XComposer-2.5-OmniLive

Pathological diagnosis is vital for determining disease characteristics, guiding treatment, and assessing prognosis, relying heavily on detailed, multi-scale analysis of high-resolution whole slide images (WSI). However, traditional pure vision models face challenges of redundant feature extraction, whereas existing large vision-language models (LVLMs) are limited by input resolution constraints, hindering their efficiency and accuracy. To overcome these issues, we propose two innovative strategies: the mixed task-guided feature enhancement, which directs feature extraction toward lesion-related details across scales, and the prompt-guided detail feature completion, which integrates coarse- and fine-grained features from WSI based on specific prompts without compromising inference speed. Leveraging a comprehensive dataset of 490,000 samples from diverse pathology tasks-including cancer detection, grading, vascular and neural invasion identification, and so on-we trained the pathology-specialized LVLM, OmniPath. Extensive experiments demonstrate that this model significantly outperforms existing methods in diagnostic accuracy and efficiency, offering an interactive, clinically aligned approach for auxiliary diagnosis in a wide range of pathology applications.

A search for $D^0$ meson decays to the $\pi^+\pi^-e^+e^-$ and $K^+K^-e^+e^-$ final states is reported using a sample of proton-proton collisions collected by the LHCb experiment at a center-of-mass energy of 13 TeV, corresponding to an integrated luminosity of 6 fb$^{-1}$. The decay $D^0 \rightarrow \pi^+\pi^-e^+e^-$ is observed for the first time when requiring that the two electrons are consistent with coming from the decay of a $\phi$ or $\rho^0/\omega$ meson. The corresponding branching fractions are measured relative to the $D^0 \rightarrow K^-\pi^-[e^+e^-]_{\rho^0/\omega}$ decay, where the two electrons are consistent with coming from the decay of a $\rho^0$ or $\omega$ meson. No evidence is found for the $D^0 \rightarrow K^+K^-e^+e^-$ decay and world-best limits are set on its branching fraction. The results are compared to, and found to be consistent with, the branching fractions of the $D^0 \rightarrow \pi^+\pi^-\mu^+\mu^-$ and $D^0 \rightarrow K^+K^-\mu^+\mu^-$ decays recently measured by LHCb and confirm lepton universality at the current precision., Comment: All figures and tables, along with machine-readable versions and any supplementary material and additional information, are available at https://lbfence.cern.ch/alcm/public/analysis/full-details/1611/ (LHCb public pages)

Clinical trials are an indispensable part of the drug development process, bridging the gap between basic research and clinical application. During the development of new drugs, clinical trials are used not only to evaluate the safety and efficacy of the drug but also to explore its dosage, treatment regimens, and potential side effects. This review discusses the various stages of clinical trials, including Phase I (safety assessment), Phase II (preliminary efficacy evaluation), Phase III (large-scale validation), and Phase IV (post-marketing surveillance), highlighting the characteristics of each phase and their interrelationships. Additionally, the paper addresses the major challenges encountered in clinical trials, such as ethical issues, subject recruitment difficulties, diversity and representativeness concerns, and proposes strategies for overcoming these challenges. With the advancement of technology, innovative technologies such as artificial intelligence, big data, and digitalization are gradually transforming clinical trial design and implementation, improving trial efficiency and data quality. The article also looks forward to the future of clinical trials, particularly the impact of emerging therapies such as gene therapy and immunotherapy on trial design, as well as the importance of regulatory reforms and global collaboration. In conclusion, the core role of clinical trials in drug development will continue to drive the progress of innovative drug development and clinical treatment., Comment: 11 pages

A spectrum of new hardware has been studied to accelerate database systems in the past decade. Specifically, CUDA cores are known to benefit from the fast development of GPUs and make notable performance improvements. The state-of-the-art GPU-based implementation, i.e., Crystal, can achieve up to 61 times higher performance than CPU-based implementations. However, experiments show that the approach has already saturated almost all GPU memory bandwidth, which means there is little room left for further performance improvements. We introduce RTCUDB, the first query engine that leverages ray tracing (RT) cores in GPUs to accelerate database query processing. RTCUDB efficiently transforms the evaluation of a query into a ray-tracing job in a three-dimensional space. By dramatically reducing the amount of accessed data and optimizing the data access pattern with the ray tracing mechanism, the performance of RTCUDB is no longer limited by the memory bandwidth as in CUDA-based implementations. Experimental results show that RTCUDB outperforms the state-of-the-art GPU-based query engine by up to 18.3 times while the memory bandwidth usage drops to only 36.7% on average.

With the increasing development of intelligent transportation systems and advancements in aviation technology, the concept of Advanced Air Mobility (AAM) is gaining attention. This study aims to improve operational safety and service quality within Urban Air Mobility (UAM) through a trajectory-based operation (TBO). A multi-layer operational risk assessment model is introduced to capture the effects of aircraft failure scenarios on critical urban entities, including ground personnel, vehicles, and in-flight UAVs (unmanned aerial vehicles). Based on this, a single-aircraft track planning model is designed to balance operational risk and transportation cost under the performance constraints of eVTOL (electric Vertical Take-off and Landing) aircraft. A customized track planning algorithm with safety buffer zones is used to identify the most efficient flight paths. Additionally, a multi-aircraft scheduling optimization model is proposed to minimize delays and reduce mid-air collision risks. Experimental results show that the presented approach improves both efficiency and safety, providing practical solutions for UAM operations., Comment: 35 pages, 24 figures,7 tables

Topological metals possess various types of symmetry-protected degenerate band crossings. When a topological metal becomes superconducting, the low-energy electronic excitations stemming from the band crossings located close to the Fermi level may contribute to highly unusual pairing symmetry and superconducting states. In this work, we study the electronic band structure of the time-reversal symmetry breaking superconductor LaNiGa$_2$ by means of quantum oscillation measurements. A comprehensive investigation combining angle-resolved high-field de Haas-van Alphen (dHvA) spectroscopy and first-principles calculations reveals the fermiology of LaNiGa$_2$ and verifies its nonsymmorphic $Cmcm$ lattice symmetry, which promises nodal band crossings pinned at the Fermi level with fourfold degeneracies. Moreover, such nodal structures, proposed to play a crucial role giving rise to the interorbital triplet pairing, are indeed captured by our dHvA analysis. Our results identify LaNiGa$_2$ as a prototypical topological crystalline superconductor and highlight the putative contribution of low-energy nodal quasiparticles to unconventional superconducting pairing., Comment: 9 pages, 5 figures, accepted by SCIENCE CHINA Physics, Mechanics & Astronomy

Text embedding has become a foundational technology in natural language processing (NLP) during the deep learning era, driving advancements across a wide array of downstream tasks. While many natural language understanding challenges can now be modeled using generative paradigms and leverage the robust generative and comprehension capabilities of large language models (LLMs), numerous practical applications, such as semantic matching, clustering, and information retrieval, continue to rely on text embeddings for their efficiency and effectiveness. In this survey, we categorize the interplay between LLMs and text embeddings into three overarching themes: (1) LLM-augmented text embedding, enhancing traditional embedding methods with LLMs; (2) LLMs as text embedders, utilizing their innate capabilities for embedding generation; and (3) Text embedding understanding with LLMs, leveraging LLMs to analyze and interpret embeddings. By organizing these efforts based on interaction patterns rather than specific downstream applications, we offer a novel and systematic overview of contributions from various research and application domains in the era of LLMs. Furthermore, we highlight the unresolved challenges that persisted in the pre-LLM era with pre-trained language models (PLMs) and explore the emerging obstacles brought forth by LLMs. Building on this analysis, we outline prospective directions for the evolution of text embedding, addressing both theoretical and practical opportunities in the rapidly advancing landscape of NLP., Comment: Work in progress

Offline preference-based reinforcement learning (PbRL) typically operates in two phases: first, use human preferences to learn a reward model and annotate rewards for a reward-free offline dataset; second, learn a policy by optimizing the learned reward via offline RL. However, accurately modeling step-wise rewards from trajectory-level preference feedback presents inherent challenges. The reward bias introduced, particularly the overestimation of predicted rewards, leads to optimistic trajectory stitching, which undermines the pessimism mechanism critical to the offline RL phase. To address this challenge, we propose In-Dataset Trajectory Return Regularization (DTR) for offline PbRL, which leverages conditional sequence modeling to mitigate the risk of learning inaccurate trajectory stitching under reward bias. Specifically, DTR employs Decision Transformer and TD-Learning to strike a balance between maintaining fidelity to the behavior policy with high in-dataset trajectory returns and selecting optimal actions based on high reward labels. Additionally, we introduce an ensemble normalization technique that effectively integrates multiple reward models, balancing the tradeoff between reward differentiation and accuracy. Empirical evaluations on various benchmarks demonstrate the superiority of DTR over other state-of-the-art baselines, Comment: 7 pages, Proceedings of the 39th AAAI Conference on Artificial Intelligence (AAAI-25)

Large Language models (LLMs) have become a research hotspot. To accelerate the inference of LLMs, storing computed caches in memory has become the standard technique. However, as the inference length increases, growing KV caches might lead to out-of-memory issues. Many existing methods address this issue through KV cache compression, primarily by preserving key tokens throughout all layers to reduce information loss. Most of them allocate a uniform budget size for each layer to retain. However, we observe that the minimum budget sizes needed to retain essential information vary across layers and models based on the perspectives of attention and hidden state output. Building on this observation, this paper proposes a simple yet effective KV cache compression method that leverages layer uncertainty to allocate budget size for each layer. Experimental results show that the proposed method can reduce memory usage of the KV caches to only $\sim$20\% when compared to Full KV inference while achieving nearly lossless performance.

Organic Solar Cells (OSCs) are a promising technology for sustainable energy production. However, the identification of molecules with desired OSC properties typically involves laborious experimental research. To accelerate progress in the field, it is crucial to develop machine learning models capable of accurately predicting the properties of OSC molecules. While graph representation learning has demonstrated success in molecular property prediction, it remains underexplored for OSC-specific tasks. Existing methods fail to capture the unique structural features of OSC molecules, particularly the intricate ring systems that critically influence OSC properties, leading to suboptimal performance. To fill the gap, we present RingFormer, a novel graph transformer framework specially designed to capture both atom and ring level structural patterns in OSC molecules. RingFormer constructs a hierarchical graph that integrates atomic and ring structures and employs a combination of local message passing and global attention mechanisms to generate expressive graph representations for accurate OSC property prediction. We evaluate RingFormer's effectiveness on five curated OSC molecule datasets through extensive experiments. The results demonstrate that RingFormer consistently outperforms existing methods, achieving a 22.77% relative improvement over the nearest competitor on the CEPDB dataset., Comment: 12 pages, 4 figures. This is the extended version of the paper accepted at AAAI 2025, which includes all technical appendices and additional experimental details

Deep learning has transformed AI applications but faces critical security challenges, including adversarial attacks, data poisoning, model theft, and privacy leakage. This survey examines these vulnerabilities, detailing their mechanisms and impact on model integrity and confidentiality. Practical implementations, including adversarial examples, label flipping, and backdoor attacks, are explored alongside defenses such as adversarial training, differential privacy, and federated learning, highlighting their strengths and limitations. Advanced methods like contrastive and self-supervised learning are presented for enhancing robustness. The survey concludes with future directions, emphasizing automated defenses, zero-trust architectures, and the security challenges of large AI models. A balanced approach to performance and security is essential for developing reliable deep learning systems.

The prevalence of unhealthy eating habits has become an increasingly concerning issue in the United States. However, major food recommendation platforms (e.g., Yelp) continue to prioritize users' dietary preferences over the healthiness of their choices. Although efforts have been made to develop health-aware food recommendation systems, the personalization of such systems based on users' specific health conditions remains under-explored. In addition, few research focus on the interpretability of these systems, which hinders users from assessing the reliability of recommendations and impedes the practical deployment of these systems. In response to this gap, we first establish two large-scale personalized health-aware food recommendation benchmarks at the first attempt. We then develop a novel framework, Multi-Objective Personalized Interpretable Health-aware Food Recommendation System (MOPI-HFRS), which provides food recommendations by jointly optimizing the three objectives: user preference, personalized healthiness and nutritional diversity, along with an large language model (LLM)-enhanced reasoning module to promote healthy dietary knowledge through the interpretation of recommended results. Specifically, this holistic graph learning framework first utilizes two structure learning and a structure pooling modules to leverage both descriptive features and health data. Then it employs Pareto optimization to achieve designed multi-facet objectives. Finally, to further promote the healthy dietary knowledge and awareness, we exploit an LLM by utilizing knowledge-infusion, prompting the LLMs with knowledge obtained from the recommendation model for interpretation.

Fairness in multi-document summarization (MDS) measures whether a system can generate a summary fairly representing information from documents with different social attribute values. Fairness in MDS is crucial since a fair summary can offer readers a comprehensive view. Previous works focus on quantifying summary-level fairness using Proportional Representation, a fairness measure based on Statistical Parity. However, Proportional Representation does not consider redundancy in input documents and overlooks corpus-level unfairness. In this work, we propose a new summary-level fairness measure, Equal Coverage, which is based on coverage of documents with different social attribute values and considers the redundancy within documents. To detect the corpus-level unfairness, we propose a new corpus-level measure, Coverage Parity. Our human evaluations show that our measures align more with our definition of fairness. Using our measures, we evaluate the fairness of thirteen different LLMs. We find that Claude3-sonnet is the fairest among all evaluated LLMs. We also find that almost all LLMs overrepresent different social attribute values.

A complete understanding of the initial conditions of high-mass star formation and what processes determine multiplicity require the study of the magnetic field (B-field) in young, massive cores. Using ALMA 250 GHz polarization (0.3" = 1000 au) and ALMA 220 GHz high-angular resolution observations (0.05" = 160 au), we have performed a full energy analysis including the B-field at core scales and have assessed what influences the multiplicity inside a massive core previously believed to be in the prestellar phase. With 31 Msun, the G11.92 MM2 core has a young CS outflow with a dynamical time scale of a few thousand years. At high-resolution, the MM2 core fragments into a binary system with a projected separation of 505 au and a binary mass ratio of 1.14. Using the DCF method with an ADF analysis, we estimate in this core a B-field strength of 6.2 mG and a mass-to-flux ratio of 18. The MM2 core is strongly subvirialized with a virial parameter of 0.064, including the B-field. The high mass-to-flux ratio and low virial parameter indicate that this massive core is very likely undergoing runaway collapse, which is in direct contradiction with the core-accretion model. The MM2 core is embedded in a filament that has a velocity gradient consistent with infall. In line with clump-fed scenarios, the core can grow in mass at a rate of 1.9--5.6 x 10^-4 Msun/yr. In spite of the B-field having only a minor contribution to the total energy budget at core scales, it likely plays a more important role at smaller scales by setting the binary properties. Considering energy ratios and a fragmentation criterion at the core scale, the binary could have been formed by core fragmentation. The binary properties (separation and mass ratio), however, are also consistent with radiation-magnetohydrodynamic simulations with super-Alfvenic, supersonic (or sonic) turbulence that form binaries by disk fragmentation., Comment: Accepted for publications in ApJ (9 pages, 3 figures, Appendix)

Modeling the evolutions of driving scenarios is important for the evaluation and decision-making of autonomous driving systems. Most existing methods focus on one aspect of scene evolution such as map generation, motion prediction, and trajectory planning. In this paper, we propose a unified Generative Pre-training for Driving (GPD-1) model to accomplish all these tasks altogether without additional fine-tuning. We represent each scene with ego, agent, and map tokens and formulate autonomous driving as a unified token generation problem. We adopt the autoregressive transformer architecture and use a scene-level attention mask to enable intra-scene bi-directional interactions. For the ego and agent tokens, we propose a hierarchical positional tokenizer to effectively encode both 2D positions and headings. For the map tokens, we train a map vector-quantized autoencoder to efficiently compress ego-centric semantic maps into discrete tokens. We pre-train our GPD-1 on the large-scale nuPlan dataset and conduct extensive experiments to evaluate its effectiveness. With different prompts, our GPD-1 successfully generalizes to various tasks without finetuning, including scene generation, traffic simulation, closed-loop simulation, map prediction, and motion planning. Code: https://github.com/wzzheng/GPD., Comment: Code is available at: https://github.com/wzzheng/GPD

Current collaborative perception methods often rely on fully annotated datasets, which can be expensive to obtain in practical situations. To reduce annotation costs, some works adopt sparsely supervised learning techniques and generate pseudo labels for the missing instances. However, these methods fail to achieve an optimal confidence threshold that harmonizes the quality and quantity of pseudo labels. To address this issue, we propose an end-to-end Collaborative perception Dual Teacher-Student framework (CoDTS), which employs adaptive complementary learning to produce both high-quality and high-quantity pseudo labels. Specifically, the Main Foreground Mining (MFM) module generates high-quality pseudo labels based on the prediction of the static teacher. Subsequently, the Supplement Foreground Mining (SFM) module ensures a balance between the quality and quantity of pseudo labels by adaptively identifying missing instances based on the prediction of the dynamic teacher. Additionally, the Neighbor Anchor Sampling (NAS) module is incorporated to enhance the representation of pseudo labels. To promote the adaptive complementary learning, we implement a staged training strategy that trains the student and dynamic teacher in a mutually beneficial manner. Extensive experiments demonstrate that the CoDTS effectively ensures an optimal balance of pseudo labels in both quality and quantity, establishing a new state-of-the-art in sparsely supervised collaborative perception., Comment: AAAI 2025

Parameter-efficient transfer learning (PETL) has become a promising paradigm for adapting large-scale vision foundation models to downstream tasks. Typical methods primarily leverage the intrinsic low rank property to make decomposition, learning task-specific weights while compressing parameter size. However, such approaches predominantly manipulate within the original feature space utilizing a single-branch structure, which might be suboptimal for decoupling the learned representations and patterns. In this paper, we propose ALoRE, a novel PETL method that reuses the hypercomplex parameterized space constructed by Kronecker product to Aggregate Low Rank Experts using a multi-branch paradigm, disentangling the learned cognitive patterns during training. Thanks to the artful design, ALoRE maintains negligible extra parameters and can be effortlessly merged into the frozen backbone via re-parameterization in a sequential manner, avoiding additional inference latency. We conduct extensive experiments on 24 image classification tasks using various backbone variants. Experimental results demonstrate that ALoRE outperforms the full fine-tuning strategy and other state-of-the-art PETL methods in terms of performance and parameter efficiency. For instance, ALoRE obtains 3.06% and 9.97% Top-1 accuracy improvement on average compared to full fine-tuning on the FGVC datasets and VTAB-1k benchmark by only updating 0.15M parameters., Comment: 23 pages, 7 figures

As a common form of communication in social media,stickers win users' love in the internet scenarios, for their ability to convey emotions in a vivid, cute, and interesting way. People prefer to get an appropriate sticker through retrieval rather than creation for the reason that creating a sticker is time-consuming and relies on rule-based creative tools with limited capabilities. Nowadays, advanced text-to-video algorithms have spawned numerous general video generation systems that allow users to customize high-quality, photo-realistic videos by only providing simple text prompts. However, creating customized animated stickers, which have lower frame rates and more abstract semantics than videos, is greatly hindered by difficulties in data acquisition and incomplete benchmarks. To facilitate the exploration of researchers in animated sticker generation (ASG) field, we firstly construct the currently largest vision-language sticker dataset named VSD2M at a two-million scale that contains static and animated stickers. Secondly, to improve the performance of traditional video generation methods on ASG tasks with discrete characteristics, we propose a Spatial Temporal Interaction (STI) layer that utilizes semantic interaction and detail preservation to address the issue of insufficient information utilization. Moreover, we train baselines with several video generation methods (e.g., transformer-based, diffusion-based methods) on VSD2M and conduct a detailed analysis to establish systemic supervision on ASG task. To the best of our knowledge, this is the most comprehensive large-scale benchmark for multi-frame animated sticker generation, and we hope this work can provide valuable inspiration for other scholars in intelligent creation., Comment: 11 pages, 9 figures

Proline (Pro) is one kind of proteinogenic amino acid and an important signaling molecule in the process of metabolism. Hydroxyproline (Hyp) is a product on Pro oxygen sensing post-translational modification (PTM), which is efficiently modulated tumor cells for angiogenesis. Distinguishing between Pro and Hyp is crucial for diagnosing connective tissue disorders, as elevated levels of Hyp can indicate abnormal collagen metabolism, often associated with diseases like osteogenesis imperfecta or fibrosis. However, there is a very small difference between molecular structures of Pro and Hyp, which is a big challenge for current detection technologies to distinguish them. For surface-enhanced Raman scattering (SERS) sensors, the similar molecule structure leads to similar Raman spectra that are difficult to distinguish. Furthermore, another problem is the weak affinity between amino acids sample and SERS-active substrates by physical adsorption. The selecting capturing of Pro and Hyp in the mixture of amino acids is not easy to achieve. In this work, we designed a new method for Pro and Hyp specifical detection and recognition by using gold nanopillars as the SERS substrate and combing nitrilotriacetic acid (NTA) with nickel (Ni) to form NTA-Ni structure as a specifical affinity agent. One side of NTA-Ni was attached to gold nanopillars through thiol binding. Another side captured the amino acids using reversible binding by receptor-ligand interaction between Ni and amino acids. Because of the different binding time with NTA-Ni and amino acids, the sensor can recognize Pro and Hyp from amino acids mixture. Then we used automatic peak assignment program for data analysis and machine learning model to distinguish between Pro and Hyp. The label-free SERS detection of amino acids PTM using gold nanopillars provides a potential method to further biomolecule detection and specifical capture.

It is well known that LLM-based systems are data-hungry. Recent LLM-based TTS works typically employ complex data processing pipelines to obtain high-quality training data. These sophisticated pipelines require excellent models at each stage (e.g., speech denoising, speech enhancement, speaker diarization, and punctuation models), which themselves demand high-quality training data and are rarely open-sourced. Even with state-of-the-art models, issues persist, such as incomplete background noise removal and misalignment between punctuation and actual speech pauses. Moreover, the stringent filtering strategies often retain only 10-30\% of the original data, significantly impeding data scaling efforts. In this work, we leverage a noise-robust audio tokenizer (S3Tokenizer) to design a simplified yet effective TTS data processing pipeline that maintains data quality while substantially reducing data acquisition costs, achieving a data retention rate of over 50\%. Beyond data scaling challenges, LLM-based TTS systems also incur higher deployment costs compared to conventional approaches. Current systems typically use LLMs solely for text-to-token generation, while requiring separate models (e.g., flow matching models) for token-to-waveform generation, which cannot be directly executed by LLM inference engines, further complicating deployment. To address these challenges, we eliminate redundant modules in both LLM and flow components, replacing the flow model backbone with an LLM architecture. Building upon this simplified flow backbone, we propose a unified architecture for both streaming and non-streaming inference, significantly reducing deployment costs. Finally, we explore the feasibility of unifying TTS and ASR tasks using the same data for training, thanks to the simplified pipeline and the S3Tokenizer that reduces the quality requirements for TTS training data., Comment: Technical Report

Due to the scarcity and unpredictable nature of defect samples, industrial anomaly detection (IAD) predominantly employs unsupervised learning. However, all unsupervised IAD methods face a common challenge: the inherent bias in normal samples, which causes models to focus on variable regions while overlooking potential defects in invariant areas. To effectively overcome this, it is essential to decompose and recalibrate attention, guiding the model to suppress irrelevant variations and concentrate on subtle, defect-susceptible areas. In this paper, we propose Recalibrating Attention of Industrial Anomaly Detection (RAAD), a framework that systematically decomposes and recalibrates attention maps. RAAD employs a two-stage process: first, it reduces attention bias through quantization, and second, it fine-tunes defect-prone regions for improved sensitivity. Central to this framework is Hierarchical Quantization Scoring (HQS), which dynamically allocates bit-widths across layers based on their anomaly detection contributions. HQS dynamically adjusts bit-widths based on the hierarchical nature of attention maps, compressing lower layers that produce coarse and noisy attention while preserving deeper layers with sharper, defect-focused attention. This approach optimizes both computational efficiency and the model' s sensitivity to anomalies. We validate the effectiveness of RAAD on 32 datasets using a single 3090ti. Experiments demonstrate that RAAD, balances the complexity and expressive power of the model, enhancing its anomaly detection capability.

Photonic neural networks (PNNs) have garnered significant interest due to their potential to offer low latency, high bandwidth, and energy efficiency in neuromorphic computing and machine learning. In PNNs, weights are photonic devices that make them susceptible to environmental factors and fabrication variations. These vulnerabilities can result in inaccurate parameter mapping, increased tuning power consumption, and reduced network performance when conventional offline training methods are used. Here, we experimentally demonstrate an online training and pruning method to address these challenges. By incorporating a power-related term into the conventional loss function, our approach minimizes the inference power budget. With this method, PNNs achieve 96% accuracy while reducing the power consumption by almost 45% on the Iris dataset, despite fabrication and thermal variations. Furthermore, our method is validated with a two-layer convolutional neural network (CNN) experiment for radio-frequency (RF) fingerprinting applications and simulations across larger CNNs on image classification datasets, including MNIST, CIFAR-10, and CIFAR-100. This work represents a significant milestone in enabling adaptive online training of PNNs and showcases their potential for real-world applications., Comment: 16 pages, 6 figures

Image inpainting is an important image generation task, which aims to restore corrupted image from partial visible area. Recently, diffusion Schr\"odinger bridge methods effectively tackle this task by modeling the translation between corrupted and target images as a diffusion Schr\"odinger bridge process along a noising schedule path. Although these methods have shown superior performance, in this paper, we find that 1) existing methods suffer from a schedule-restoration mismatching issue, i.e., the theoretical schedule and practical restoration processes usually exist a large discrepancy, which theoretically results in the schedule not fully leveraged for restoring images; and 2) the key reason causing such issue is that the restoration process of all pixels are actually asynchronous but existing methods set a synchronous noise schedule to them, i.e., all pixels shares the same noise schedule. To this end, we propose a schedule-Asynchronous Diffusion Schr\"odinger Bridge (AsyncDSB) for image inpainting. Our insight is preferentially scheduling pixels with high frequency (i.e., large gradients) and then low frequency (i.e., small gradients). Based on this insight, given a corrupted image, we first train a network to predict its gradient map in corrupted area. Then, we regard the predicted image gradient as prior and design a simple yet effective pixel-asynchronous noise schedule strategy to enhance the diffusion Schr\"odinger bridge. Thanks to the asynchronous schedule at pixels, the temporal interdependence of restoration process between pixels can be fully characterized for high-quality image inpainting. Experiments on real-world datasets show that our AsyncDSB achieves superior performance, especially on FID with around 3% - 14% improvement over state-of-the-art baseline methods., Comment: Accepted by AAAI 2025

Event cameras, as bio-inspired sensors, are asynchronously triggered with high-temporal resolution compared to intensity cameras. Recent work has focused on fusing the event measurements with inertial measurements to enable ego-motion estimation in high-speed and HDR environments. However, existing methods predominantly rely on IMU preintegration designed mainly for synchronous sensors and discrete-time frameworks. In this paper, we propose a continuous-time preintegration method based on the Temporal Gaussian Process (TGP) called GPO. Concretely, we model the preintegration as a time-indexed motion trajectory and leverage an efficient two-step optimization to initialize the precision preintegration pseudo-measurements. Our method realizes a linear and constant time cost for initialization and query, respectively. To further validate the proposal, we leverage the GPO to design an asynchronous event-inertial odometry and compare with other asynchronous fusion schemes within the same odometry system. Experiments conducted on both public and own-collected datasets demonstrate that the proposed GPO offers significant advantages in terms of precision and efficiency, outperforming existing approaches in handling asynchronous sensor fusion., Comment: 8pages

We present phi-4, a 14-billion parameter language model developed with a training recipe that is centrally focused on data quality. Unlike most language models, where pre-training is based primarily on organic data sources such as web content or code, phi-4 strategically incorporates synthetic data throughout the training process. While previous models in the Phi family largely distill the capabilities of a teacher model (specifically GPT-4), phi-4 substantially surpasses its teacher model on STEM-focused QA capabilities, giving evidence that our data-generation and post-training techniques go beyond distillation. Despite minimal changes to the phi-3 architecture, phi-4 achieves strong performance relative to its size -- especially on reasoning-focused benchmarks -- due to improved data, training curriculum, and innovations in the post-training scheme.

Blue Large-Amplitude Pulsators (BLAPs) represent a recently identified class of pulsating stars distinguished by their short pulsation periods (22-40 minutes) and asymmetric light curves. This study investigates the evolutionary channel of HD 133729, the first confirmed BLAP in a binary system. Through binary evolution simulations with MESA, we explored various mass ratios and initial orbital periods, finding that a mass ratio of q = 0.30 coupled with non-conservative mass transfer ($\rm \beta$ = 0.15) successfully reproduces the observational characteristics (including luminosity, surface gravity, and effective temperature) of the binary system. Our models not only match the observed pulsational properties but also predict significant helium and nitrogen enhancements on the surface of the main-sequence companion. The system is expected to eventually undergo a common envelope phase leading to a stellar merger. Our findings provide crucial insights into the formation mechanism and evolutionary fate of BLAPs with main-sequence companions, while also placing constraints on the elemental abundances of their binary companions., Comment: Comments are welcome

Automated drug discovery offers significant potential for accelerating the development of novel therapeutics by substituting labor-intensive human workflows with machine-driven processes. However, a critical bottleneck persists in the inability of current automated frameworks to assess whether newly designed molecules infringe upon existing patents, posing significant legal and financial risks. We introduce PatentFinder, a novel tool-enhanced and multi-agent framework that accurately and comprehensively evaluates small molecules for patent infringement. It incorporates both heuristic and model-based tools tailored for decomposed subtasks, featuring: MarkushParser, which is capable of optical chemical structure recognition of molecular and Markush structures, and MarkushMatcher, which enhances large language models' ability to extract substituent groups from molecules accurately. On our benchmark dataset MolPatent-240, PatentFinder outperforms baseline approaches that rely solely on large language models, demonstrating a 13.8\% increase in F1-score and a 12\% rise in accuracy. Experimental results demonstrate that PatentFinder mitigates label bias to produce balanced predictions and autonomously generates detailed, interpretable patent infringement reports. This work not only addresses a pivotal challenge in automated drug discovery but also demonstrates the potential of decomposing complex scientific tasks into manageable subtasks for specialized, tool-augmented agents.

Current video diffusion models achieve impressive generation quality but struggle in interactive applications due to bidirectional attention dependencies. The generation of a single frame requires the model to process the entire sequence, including the future. We address this limitation by adapting a pretrained bidirectional diffusion transformer to a causal transformer that generates frames on-the-fly. To further reduce latency, we extend distribution matching distillation (DMD) to videos, distilling 50-step diffusion model into a 4-step generator. To enable stable and high-quality distillation, we introduce a student initialization scheme based on teacher's ODE trajectories, as well as an asymmetric distillation strategy that supervises a causal student model with a bidirectional teacher. This approach effectively mitigates error accumulation in autoregressive generation, allowing long-duration video synthesis despite training on short clips. Our model supports fast streaming generation of high quality videos at 9.4 FPS on a single GPU thanks to KV caching. Our approach also enables streaming video-to-video translation, image-to-video, and dynamic prompting in a zero-shot manner. We will release the code based on an open-source model in the future., Comment: Project Page: https://causvid.github.io/

We introduce UniReal, a unified framework designed to address various image generation and editing tasks. Existing solutions often vary by tasks, yet share fundamental principles: preserving consistency between inputs and outputs while capturing visual variations. Inspired by recent video generation models that effectively balance consistency and variation across frames, we propose a unifying approach that treats image-level tasks as discontinuous video generation. Specifically, we treat varying numbers of input and output images as frames, enabling seamless support for tasks such as image generation, editing, customization, composition, etc. Although designed for image-level tasks, we leverage videos as a scalable source for universal supervision. UniReal learns world dynamics from large-scale videos, demonstrating advanced capability in handling shadows, reflections, pose variation, and object interaction, while also exhibiting emergent capability for novel applications., Comment: webpage: https://xavierchen34.github.io/UniReal-Page/

Document content extraction is crucial in computer vision, especially for meeting the high-quality data needs of large language models (LLMs) and retrieval-augmented generation (RAG) technologies. However, current document parsing methods suffer from significant limitations in terms of diversity and comprehensive evaluation. To address these challenges, we introduce OmniDocBench, a novel multi-source benchmark designed to advance automated document content extraction. OmniDocBench includes a meticulously curated and annotated high-quality evaluation dataset comprising nine diverse document types, such as academic papers, textbooks, slides, among others. Our benchmark provides a flexible and comprehensive evaluation framework with 19 layout category labels and 14 attribute labels, enabling multi-level assessments across entire datasets, individual modules, or specific data types. Using OmniDocBench, we perform an exhaustive comparative analysis of existing modular pipelines and multimodal end-to-end methods, highlighting their limitations in handling document diversity and ensuring fair evaluation. OmniDocBench establishes a robust, diverse, and fair evaluation standard for the document content extraction field, offering crucial insights for future advancements and fostering the development of document parsing technologies. The codes and dataset is available in https://github.com/opendatalab/OmniDocBench.

LiDAR is widely used in Simultaneous Localization and Mapping (SLAM) and autonomous driving. The LiDAR odometry is of great importance in multi-sensor fusion. However, in some unstructured environments, the point cloud registration cannot constrain the poses of the LiDAR due to its sparse geometric features, which leads to the degeneracy of multi-sensor fusion accuracy. To address this problem, we propose a novel real-time approach to sense and compensate for the degeneracy of LiDAR. Firstly, this paper introduces the degeneracy factor with clear meaning, which can measure the degeneracy of LiDAR. Then, the Density-Based Spatial Clustering of Applications with Noise (DBSCAN) clustering method adaptively perceives the degeneracy with better environmental generalization. Finally, the degeneracy perception results are utilized to fuse LiDAR and IMU, thus effectively resisting degeneracy effects. Experiments on our dataset show the method's high accuracy and robustness and validate our algorithm's adaptability to different environments and LiDAR scanning modalities., Comment: 13 pages