Search

Utilizing a data set of $6.7$ fb$^{-1}$ from electron-positron collisions recorded by the BESIII detector at the BEPCII storage ring, a search is conducted for the processes $e^{+}e^{-} \to \phi \chi_{c0}$ and $\phi\eta_{c2}(1D)$ across center-of-mass energies from 4.47 to 4.95 GeV. In the absence of any significant signals, upper limits are set. These include limits on the Born cross sections for $e^{+}e^{-} \to \phi \chi_{c0}$, as well as the product of the Born cross section for $e^{+}e^{-} \to \phi\eta_{c2}(1D)$ and a sum of five branching fractions. Furthermore, the product of the electronic width of $Y(4660)$ and the branching fraction of the $Y(4660) \to \phi\chi_{c0}$, denoted as $\Gamma^{Y(4660)}_{e^{+}e^{-}} \mathcal{B}_{Y(4660) \to \phi\chi_{c0}}$, is determined to be $< 0.40$ eV at the 90\% confidence level., Comment: 14 pages, 6 figures

The integration of Large Language Models (LLMs) into autonomous driving systems demonstrates strong common sense and reasoning abilities, effectively addressing the pitfalls of purely data-driven methods. Current LLM-based agents require lengthy inference times and face challenges in interacting with real-time autonomous driving environments. A key open question is whether we can effectively leverage the knowledge from LLMs to train an efficient and robust Reinforcement Learning (RL) agent. This paper introduces RAPID, a novel \underline{\textbf{R}}obust \underline{\textbf{A}}daptive \underline{\textbf{P}}olicy \underline{\textbf{I}}nfusion and \underline{\textbf{D}}istillation framework, which trains specialized mix-of-policy RL agents using data synthesized by an LLM-based driving agent and online adaptation. RAPID features three key designs: 1) utilization of offline data collected from an LLM agent to distil expert knowledge into RL policies for faster real-time inference; 2) introduction of robust distillation in RL to inherit both performance and robustness from LLM-based teacher; and 3) employment of a mix-of-policy approach for joint decision decoding with a policy adapter. Through fine-tuning via online environment interaction, RAPID reduces the forgetting of LLM knowledge while maintaining adaptability to different tasks. Extensive experiments demonstrate RAPID's capability to effectively integrate LLM knowledge into scaled-down RL policies in an efficient, adaptable, and robust way. Code and checkpoints will be made publicly available upon acceptance.

In this paper, we revisit the f\'eeton (gauge boson of $U(1)_{B-L}$ symmetry) dark matter scenario, and first point out the $U(1)$ gauge symmetry can be a linear combination of the $B-L$ and the SM hypercharge gauge symmetries. With the redefinition of $B-L$ charge of fermions, the coupling between electron and f\'eeton can be enhanced. After showing the parameter space required from the DM stability and cosmic production, we discuss the potential for verifying them in dark matter direct detection experiments. The results show that future experiments, such as SuperCDMS, have a sensitivity to reach the f\'eeton DM region consistent with its cosmic production., Comment: 13 pages, 2 figures

Text-driven video editing utilizing generative diffusion models has garnered significant attention due to their potential applications. However, existing approaches are constrained by the limited word embeddings provided in pre-training, which hinders nuanced editing targeting open concepts with specific attributes. Directly altering the keywords in target prompts often results in unintended disruptions to the attention mechanisms. To achieve more flexible editing easily, this work proposes an improved concept-augmented video editing approach that generates diverse and stable target videos flexibly by devising abstract conceptual pairs. Specifically, the framework involves concept-augmented textual inversion and a dual prior supervision mechanism. The former enables plug-and-play guidance of stable diffusion for video editing, effectively capturing target attributes for more stylized results. The dual prior supervision mechanism significantly enhances video stability and fidelity. Comprehensive evaluations demonstrate that our approach generates more stable and lifelike videos, outperforming state-of-the-art methods.

Short-term traffic volume prediction is crucial for intelligent transportation system and there are many researches focusing on this field. However, most of these existing researches concentrated on refining model architecture and ignored amount of training data. Therefore, there remains a noticeable gap in thoroughly exploring the effect of augmented dataset, especially extensive historical data in training. In this research, two datasets containing taxi and bike usage spanning over eight years in New York were used to test such effects. Experiments were conducted to assess the precision of models trained with data in the most recent 12, 24, 48, and 96 months. It was found that the training set encompassing 96 months, at times, resulted in diminished accuracy, which might be owing to disparities between historical traffic patterns and present ones. An analysis was subsequently undertaken to discern potential sources of inconsistent patterns, which may include both covariate shift and concept shift. To address these shifts, we proposed an innovative approach that aligns covariate distributions using a weighting scheme to manage covariate shift, coupled with an environment aware learning method to tackle the concept shift. Experiments based on real word datasets demonstrate the effectiveness of our method which can significantly decrease testing errors and ensure an improvement in accuracy when training with large-scale historical data. As far as we know, this work is the first attempt to assess the impact of contiguously expanding training dataset on the accuracy of traffic prediction models. Besides, our training method is able to be incorporated into most existing short-term traffic prediction models and make them more suitable for long term historical training dataset., Comment: submitted to IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS

Large language models revolutionize Text2SQL through supervised fine-tuning, yet a crucial limitation is overlooked: the complexity of databases leads to an increased context length, consequently resulting in higher GPU memory demands for model fine-tuning. To address this issue, we propose LR-SQL. LR-SQL comprises two supervised fine-tuning models: the schema\_link model and the SQL\_generation model, with the schema\_link model serving as the focal point for streamlining the overall process. During the fine-tuning of the schema\_link model, LR-SQL breaks down the complete database into flexible combinations of tables with adjustable quantities, enabling the model to learn the relationships within the entire database from these dispersed slices. Furthermore, to enhance the model's ability to perceive the relationships among various discrete slices during inference, LR-SQL trains the model's Chain-of-Thought capability for this task. Experimental results demonstrate that LR-SQL can reduce the total GPU memory usage by 40\% compared to existing fine-tuning methods, while only losing 2\% of table prediction accuracy in schema\_link task. For the overall Text2SQL task, the Execution Accuracy decrease by 0.6\%.Our project is now available on https://github.com/hongWin/LR-SQL, Comment: 12pages, 4 figures,submitting to a journal

This study explores a Gaussian quasi-likelihood approach for estimating parameters of diffusion processes with Markovian regime switching. Assuming the ergodicity under high-frequency sampling, we will show the asymptotic normality of the unknown parameters contained in the drift and diffusion coefficients and present a consistent explicit estimator for the generator of the Markov chain. Simulation experiments are conducted to illustrate the theoretical results obtained., Comment: 25 pages

The advent of massive ultra-reliable and low-latency communications (mURLLC) has introduced a critical class of time- and reliability-sensitive services within next-generation wireless networks. This shift has attracted significant research attention, driven by the need to meet stringent quality-of-service (QoS) requirements. In this context, non-orthogonal multiple access (NOMA) systems have emerged as a promising solution to enhance mURLLC performance by providing substantial enhancements in both spectral efficiency and massive connectivity, particularly through the development of finite blocklength coding (FBC) techniques. Nevertheless, owing to the dynamic nature of wireless network environments and the complex architecture of FBC-enhanced NOMA systems, the research on the efficient design of optimizing the system performance for maximizing system capacity while guaranteeing the tail distributions in terms of new statistical QoS constraints for delay and error-rate is still in its infancy. In an effort to address these challenges, we put forth the formulation and solution of {\epsilon}-effective capacity problems tailored for uplink FBC-enhanced NOMA systems, specifically catering to ensure statistical delay and error-rate bounded QoS requirements. In particular, we establish uplink two-user FBC-enhanced NOMA system models by applying the hybrid successive interference cancellation (SIC). We also develop the concept of the {\epsilon}-effective capacity and propose the optimal power allocation policies to maximize the {\epsilon}-effective capacity and {\epsilon}-effective energy efficiency while upper-bounding both delay and error-rate. We conduct a set of simulations to validate and evaluate our developed optimization schemes over FBC-enhanced NOMA systems.

We investigated two consecutive solar eruption events in the solar active region (AR) 12994 at the solar eastern limb on 2022 April 15. We found that the flare loops formed by the first eruption were involved in the second eruption. During the initial stage of the second flare, the middle part of these flare loops (E-loops) erupted outward along with the flux ropes below, while the parts of the flare loops (I-loops1 and I-loops2) on either side of the E-loops first rose and then contracted. Approximately 1 hour after the eruption, the heights of I-loops1 and I-loops2 decreased by 9 Mm and 45 Mm, respectively, compared to before the eruption. Their maximum descent velocities were 30 km/s and 130 km/s, respectively. The differential emission measure (DEM) results indicate that the plasma above I-loops1 and I-loops2 began to be heated about 23 minutes and 44 minutes after the start of the second flare, respectively. Within 20 minutes, the plasma temperature in these regions increased from ~3 MK to 6 MK. We proposed an adiabatic heating mechanism that magnetic energy would be converted into thermal and kinetic energy when the pre-stretched loops contract. Our calculations show that the magnetic energy required to heat the two high-temperature regions are 10^29-10^30 erg, which correspond to a loss of field strength of 2-3 G., Comment: The paper has been accepted for publication in the ApJ

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or 4-bit weight-only quantization, achieve limited performance improvements due to poor support for low-precision (e.g., 4-bit) activation. This work, for the first time, realizes practical W4A4KV4 serving for LLMs, fully utilizing the INT4 tensor cores on modern GPUs and reducing the memory bottleneck caused by the KV cache. Specifically, we propose a novel fine-grained mixed-precision quantization algorithm (FMPQ) that compresses most activations into 4-bit with negligible accuracy loss. To support mixed-precision matrix multiplication for W4A4 and W4A8, we develop a highly optimized W4Ax kernel. Our approach introduces a novel mixed-precision data layout to facilitate access and fast dequantization for activation and weight tensors, utilizing the GPU's software pipeline to hide the overhead of data loading and conversion. Additionally, we propose fine-grained streaming multiprocessor (SM) scheduling to achieve load balance across different SMs. We integrate the optimized W4Ax kernel into our inference framework, COMET, and provide efficient management to support popular LLMs such as LLaMA-3-70B. Extensive evaluations demonstrate that, when running LLaMA family models on a single A100-80G-SMX4, COMET achieves a kernel-level speedup of \textbf{$2.88\times$} over cuBLAS and a \textbf{$2.02 \times$} throughput improvement compared to TensorRT-LLM from an end-to-end framework perspective., Comment: 14 pages, 12 figures

We perform a theoretical study on the spectrum of the low-lying hidden-bottom ($q\bar{q}b\bar{b}$ with $q=$ $u$, $d$ and $s$) and double-bottom ($q\bar{q}bb$) tetraquark states within a nonrelativistic quark model, in which the instanton-induced interaction is taken as the residual spin-dependent hyperfine interaction between quarks. All the model parameters are fixed by fitting the spectrum of the ground hadron states. The numerical results indicate that masses of several $X_{q\bar{q}}$, $Z_{b}$, and $Z_{bs}$ tetraquark states are below and near thresholds of corresponding meson-meson channels, thus these states may form components of exotic meson states with reasonable probabilities. Especially, in present model, masses of several obtained states with quantum number $I^G(J^P)=1^+(1^{+})$ are close to $Z_b^\pm(10610)$, so one may expect these states to be non-negligible components of the experimentally observed $Z_{b}$ states. Concerning to the double-bottom tetraquark states, the present results are in general consistent with other previous works. Two possible stable $T_{bb}$ states with quark content $bb\bar{n}\bar{n}$ ($n=u$ or $d$ quark) lying at energies $10558$ MeV and $10650$ MeV are found, and one possible stable $bb\bar{n}\bar{s}$ state is found, whose energy is $\sim10687$ MeV., Comment: 15 pages, 7 figures, 12 tables

This article focuses on the existence of asymptotic colengths for families of $\fm_{R}$-primary ideals in a Noetherian local ring $(R,\fm)$. In any characteristic, we generalize graded families to weakly graded families of ideals, and in prime characteristic, we explore various families such as weakly $p$-families and weakly inverse $p$-families. The main contribution of this paper is providing a unified analytic method to prove the existence of limits. Additionally, we establish Brunn-Minkowski type inequalities, positivity results, and volume = multiplicity formulas for these families of ideals.

Time Series Forecasting (TSF) is key functionality in numerous fields, including in finance, weather services, and energy management. While TSF methods are emerging these days, many of them require domain-specific data collection and model training and struggle with poor generalization performance on new domains. Foundation models aim to overcome this limitation. Pre-trained on large-scale language or time series data, they exhibit promising inferencing capabilities in new or unseen data. This has spurred a surge in new TSF foundation models. We propose a new benchmark, FoundTS, to enable thorough and fair evaluation and comparison of such models. FoundTS covers a variety of TSF foundation models, including those based on large language models and those pretrained on time series. Next, FoundTS supports different forecasting strategies, including zero-shot, few-shot, and full-shot, thereby facilitating more thorough evaluations. Finally, FoundTS offers a pipeline that standardizes evaluation processes such as dataset splitting, loading, normalization, and few-shot sampling, thereby facilitating fair evaluations. Building on this, we report on an extensive evaluation of TSF foundation models on a broad range of datasets from diverse domains and with different statistical characteristics. Specifically, we identify pros and cons and inherent limitations of existing foundation models, and we identify directions for future model design. We make our code and datasets available at https://anonymous.4open.science/r/FoundTS-C2B0.

Recent advancements in large language model (LLM)-based agents have demonstrated that collective intelligence can significantly surpass the capabilities of individual agents, primarily due to well-crafted inter-agent communication topologies. Despite the diverse and high-performing designs available, practitioners often face confusion when selecting the most effective pipeline for their specific task: \textit{Which topology is the best choice for my task, avoiding unnecessary communication token overhead while ensuring high-quality solution?} In response to this dilemma, we introduce G-Designer, an adaptive, efficient, and robust solution for multi-agent deployment, which dynamically designs task-aware, customized communication topologies. Specifically, G-Designer models the multi-agent system as a multi-agent network, leveraging a variational graph auto-encoder to encode both the nodes (agents) and a task-specific virtual node, and decodes a task-adaptive and high-performing communication topology. Extensive experiments on six benchmarks showcase that G-Designer is: \textbf{(1) high-performing}, achieving superior results on MMLU with accuracy at $84.50\%$ and on HumanEval with pass@1 at $89.90\%$; \textbf{(2) task-adaptive}, architecting communication protocols tailored to task difficulty, reducing token consumption by up to $95.33\%$ on HumanEval; and \textbf{(3) adversarially robust}, defending against agent adversarial attacks with merely $0.3\%$ accuracy drop.

In the online digital world, users frequently engage with diverse items across multiple domains (e.g., e-commerce platforms, streaming services, and social media networks), forming complex heterogeneous interaction graphs. Leveraging this multi-domain information can undoubtedly enhance the performance of recommendation systems by providing more comprehensive user insights and alleviating data sparsity in individual domains. However, integrating multi-domain knowledge for the cross-domain recommendation is very hard due to inherent disparities in user behavior and item characteristics and the risk of negative transfer, where irrelevant or conflicting information from the source domains adversely impacts the target domain's performance. To address these challenges, we offer HAGO, a novel framework with $\textbf{H}$eterogeneous $\textbf{A}$daptive $\textbf{G}$raph co$\textbf{O}$rdinators, which dynamically integrate multi-domain graphs into a cohesive structure by adaptively adjusting the connections between coordinators and multi-domain graph nodes, thereby enhancing beneficial inter-domain interactions while mitigating negative transfer effects. Additionally, we develop a universal multi-domain graph pre-training strategy alongside HAGO to collaboratively learn high-quality node representations across domains. To effectively transfer the learned multi-domain knowledge to the target domain, we design an effective graph prompting method, which incorporates pre-trained embeddings with learnable prompts for the recommendation task. Our framework is compatible with various graph-based models and pre-training techniques, demonstrating broad applicability and effectiveness. Further experimental results show that our solutions outperform state-of-the-art methods in multi-domain recommendation scenarios and highlight their potential for real-world applications., Comment: Under review

Recent advancements in Multi-modal Large Language Models (MLLMs) have opened new avenues for applications in Embodied AI. Building on previous work, EgoThink, we introduce VidEgoThink, a comprehensive benchmark for evaluating egocentric video understanding capabilities. To bridge the gap between MLLMs and low-level control in Embodied AI, we design four key interrelated tasks: video question-answering, hierarchy planning, visual grounding and reward modeling. To minimize manual annotation costs, we develop an automatic data generation pipeline based on the Ego4D dataset, leveraging the prior knowledge and multimodal capabilities of GPT-4o. Three human annotators then filter the generated data to ensure diversity and quality, resulting in the VidEgoThink benchmark. We conduct extensive experiments with three types of models: API-based MLLMs, open-source image-based MLLMs, and open-source video-based MLLMs. Experimental results indicate that all MLLMs, including GPT-4o, perform poorly across all tasks related to egocentric video understanding. These findings suggest that foundation models still require significant advancements to be effectively applied to first-person scenarios in Embodied AI. In conclusion, VidEgoThink reflects a research trend towards employing MLLMs for egocentric vision, akin to human capabilities, enabling active observation and interaction in the complex real-world environments.

By analyzing $(27.12\pm0.14)\times10^8$ $\psi(3686)$ events collected with the BESIII detector operating at the BEPCII collider, the decays of $\chi_{cJ} \to p \bar{p} K^0_S K^- \pi^+ +c.c.(J=0, 1, 2)$ are observed for the first time with statistical significances greater than $10\sigma$. The branching fractions of these decays are determined to be $\mathcal{B}(\chi_{c0}\to p \bar p K^{0}_{S} K^- \pi^+ + c.c.)=(2.61\pm0.27\pm0.32)\times10^{-5},$ $\mathcal{B}(\chi_{c1}\to p \bar p K^{0}_{S} K^- \pi^+ + c.c.)=(4.16\pm0.24\pm0.46)\times10^{-5},$ and $\mathcal{B}(\chi_{c2}\to p \bar p K^{0}_{S} K^- \pi^+ + c.c.)=(5.63\pm0.28\pm0.46)\times10^{-5}$, respectively. The processes $\chi_{c1,2} \to \bar{p} \Lambda(1520) K^0_S \pi^{+} + c.c.$ are also observed, with statistical significances of 5.7$\sigma$ and 7.0$\sigma$, respectively. Evidence for $\chi_{c0} \to\bar{p} \Lambda(1520) K^0_S \pi^{+} + c.c.$ is found with statistical significances of 3.3$\sigma$ each. The corresponding branching fractions are determined to be $\mathcal{B}(\chi_{c0}\to \bar{p} \Lambda(1520) K^0_S \pi^{+} + c.c.) =(1.61^{+0.68}_{-0.64}\pm0.23)\times10^{-5}$, $\mathcal{B}(\chi_{c1}\to \bar{p} \Lambda(1520) K^0_S \pi^{+} + c.c.)=(4.06^{+0.80}_{-0.76}\pm0.52)\times10^{-5}$, and $\mathcal{B}(\chi_{c2}\to \bar{p} \Lambda(1520) K^0_S \pi^{+} + c.c.)=(4.09^{+0.87}_{-0.84}\pm0.42)\times10^{-5}$. Here, the first uncertainties are statistical and the second ones are systematic., Comment: 12 pages, 5 figures

The development of autonomous driving has boosted the research on autonomous racing. However, existing local trajectory planning methods have difficulty planning trajectories with optimal velocity profiles at racetracks with sharp corners, thus weakening the performance of autonomous racing. To address this problem, we propose a local trajectory planning method that integrates Velocity Prediction based on Model Predictive Contour Control (VPMPCC). The optimal parameters of VPMPCC are learned through Bayesian Optimization (BO) based on a proposed novel Objective Function adapted to Racing (OFR). Specifically, VPMPCC achieves velocity prediction by encoding the racetrack as a reference velocity profile and incorporating it into the optimization problem. This method optimizes the velocity profile of local trajectories, especially at corners with significant curvature. The proposed OFR balances racing performance with vehicle safety, ensuring safe and efficient BO training. In the simulation, the number of training iterations for OFR-based BO is reduced by 42.86% compared to the state-of-the-art method. The optimal simulation-trained parameters are then applied to a real-world F1TENTH vehicle without retraining. During prolonged racing on a custom-built racetrack featuring significant sharp corners, the mean velocity of VPMPCC reaches 93.18% of the vehicle's handling limits. The released code is available at https://github.com/zhouhengli/VPMPCC.

Affordance understanding, the task of identifying actionable regions on 3D objects, plays a vital role in allowing robotic systems to engage with and operate within the physical world. Although Visual Language Models (VLMs) have excelled in high-level reasoning and long-horizon planning for robotic manipulation, they still fall short in grasping the nuanced physical properties required for effective human-robot interaction. In this paper, we introduce PAVLM (Point cloud Affordance Vision-Language Model), an innovative framework that utilizes the extensive multimodal knowledge embedded in pre-trained language models to enhance 3D affordance understanding of point cloud. PAVLM integrates a geometric-guided propagation module with hidden embeddings from large language models (LLMs) to enrich visual semantics. On the language side, we prompt Llama-3.1 models to generate refined context-aware text, augmenting the instructional input with deeper semantic cues. Experimental results on the 3D-AffordanceNet benchmark demonstrate that PAVLM outperforms baseline methods for both full and partial point clouds, particularly excelling in its generalization to novel open-world affordance tasks of 3D objects. For more information, visit our project site: pavlm-source.github.io.

Visual localization involves estimating a query image's 6-DoF (degrees of freedom) camera pose, which is a fundamental component in various computer vision and robotic tasks. This paper presents LoGS, a vision-based localization pipeline utilizing the 3D Gaussian Splatting (GS) technique as scene representation. This novel representation allows high-quality novel view synthesis. During the mapping phase, structure-from-motion (SfM) is applied first, followed by the generation of a GS map. During localization, the initial position is obtained through image retrieval, local feature matching coupled with a PnP solver, and then a high-precision pose is achieved through the analysis-by-synthesis manner on the GS map. Experimental results on four large-scale datasets demonstrate the proposed approach's SoTA accuracy in estimating camera poses and robustness under challenging few-shot conditions., Comment: 8 pages

With the widespread use of Graph Neural Networks (GNNs) for representation learning from network data, the fairness of GNN models has raised great attention lately. Fair GNNs aim to ensure that node representations can be accurately classified, but not easily associated with a specific group. Existing advanced approaches essentially enhance the generalisation of node representation in combination with data augmentation strategy, and do not directly impose constraints on the fairness of GNNs. In this work, we identify that a fundamental reason for the unfairness of GNNs in social network learning is the phenomenon of social homophily, i.e., users in the same group are more inclined to congregate. The message-passing mechanism of GNNs can cause users in the same group to have similar representations due to social homophily, leading model predictions to establish spurious correlations with sensitive attributes. Inspired by this reason, we propose a method called Equity-Aware GNN (EAGNN) towards fair graph representation learning. Specifically, to ensure that model predictions are independent of sensitive attributes while maintaining prediction performance, we introduce constraints for fair representation learning based on three principles: sufficiency, independence, and separation. We theoretically demonstrate that our EAGNN method can effectively achieve group fairness. Extensive experiments on three datasets with varying levels of social homophily illustrate that our EAGNN method achieves the state-of-the-art performance across two fairness metrics and offers competitive effectiveness.

In the era of Large Language Models (LLMs), Mixture-of-Experts (MoE) architectures offer a promising approach to managing computational costs while scaling up model parameters. Conventional MoE-based LLMs typically employ static Top-K routing, which activates a fixed and equal number of experts for each token regardless of their significance within the context. In this paper, we propose a novel Ada-K routing strategy that dynamically adjusts the number of activated experts for each token, thereby improving the balance between computational efficiency and model performance. Specifically, our strategy incorporates learnable and lightweight allocator modules that decide customized expert resource allocation tailored to the contextual needs for each token. These allocators are designed to be fully pluggable, making it broadly applicable across all mainstream MoE-based LLMs. We leverage the Proximal Policy Optimization (PPO) algorithm to facilitate an end-to-end learning process for this non-differentiable decision-making framework. Extensive evaluations on four popular baseline models demonstrate that our Ada-K routing method significantly outperforms conventional Top-K routing. Compared to Top-K, our method achieves over 25% reduction in FLOPs and more than 20% inference speedup while still improving performance across various benchmarks. Moreover, the training of Ada-K is highly efficient. Even for Mixtral-8x22B, a MoE-based LLM with more than 140B parameters, the training time is limited to 8 hours. Detailed analysis shows that harder tasks, middle layers, and content words tend to activate more experts, providing valuable insights for future adaptive MoE system designs. Both the training code and model checkpoints will be publicly available., Comment: Coauthors do not reach a consensus on submitting the current version

Cyber Threat Intelligence (CTI) reports are factual records compiled by security analysts through their observations of threat events or their own practical experience with attacks. In order to utilize CTI reports for attack detection, existing methods have attempted to map the content of reports onto system-level attack provenance graphs to clearly depict attack procedures. However, existing studies on constructing graphs from CTI reports suffer from problems such as weak natural language processing (NLP) capabilities, discrete and fragmented graphs, and insufficient attack semantic representation. Therefore, we propose a system called CRUcialG for the automated reconstruction of attack scenario graphs (ASGs) by CTI reports. First, we use NLP models to extract systematic attack knowledge from CTI reports to form preliminary ASGs. Then, we propose a four-phase attack rationality verification framework from the tactical phase with attack procedure to evaluate the reasonability of ASGs. Finally, we implement the relation repair and phase supplement of ASGs by adopting a serialized graph generation model. We collect a total of 10,607 CTI reports and generate 5,761 complete ASGs. Experimental results on CTI reports from 30 security vendors and DARPA show that the similarity of ASG reconstruction by CRUcialG can reach 84.54%. Compared with SOTA (EXTRACTOR and AttackG), the recall of CRUcialG (extraction of real attack events) can reach 88.13% and 94.46% respectively, which is 40% higher than SOTA on average. The F1-score of attack phase verification is able to reach 90.04%.

Robust control problem has significant practical implication since external disturbances can significantly impact the performance of control method. Existing robust control method excels at control-affine system but fails at neural network dynamic models. Developing robust control methods for such systems remains a complex challenge. In this paper, we focus on robust tracking method for neural network dynamic models. We first propose reachability analysis tool designed for this system and then introduce how to reformulate robust tracking problem with the reachable sets. In addition, we prove the existence of feedback policy that bounds the growth of reachable set over infinite horizon. The effectiveness of proposed approach is validated through numerical tracking task simulations, where we compare it with a standard tube MPC method., Comment: 8 pages, 8 figures, conference

The combination of semi-supervised learning (SemiSL) and contrastive learning (CL) has been successful in medical image segmentation with limited annotations. However, these works often rely on pretext tasks that lack the specificity required for pixel-level segmentation, and still face overfitting issues due to insufficient supervision signals resulting from too few annotations. Therefore, this paper proposes an affinity-graph-guided semi-supervised contrastive learning framework (Semi-AGCL) by establishing additional affinity-graph-based supervision signals between the student and teacher network, to achieve medical image segmentation with minimal annotations without pretext. The framework first designs an average-patch-entropy-driven inter-patch sampling method, which can provide a robust initial feature space without relying on pretext tasks. Furthermore, the framework designs an affinity-graph-guided loss function, which can improve the quality of the learned representation and the model generalization ability by exploiting the inherent structure of the data, thus mitigating overfitting. Our experiments indicate that with merely 10% of the complete annotation set, our model approaches the accuracy of the fully annotated baseline, manifesting a marginal deviation of only 2.52%. Under the stringent conditions where only 5% of the annotations are employed, our model exhibits a significant enhancement in performance surpassing the second best baseline by 23.09% on the dice metric and achieving an improvement of 26.57% on the notably arduous CRAG and ACDC datasets., Comment: BIBM 2024

Diffusion Transformers (DiT) have attracted significant attention in research. However, they suffer from a slow convergence rate. In this paper, we aim to accelerate DiT training without any architectural modification. We identify the following issues in the training process: firstly, certain training strategies do not consistently perform well across different data. Secondly, the effectiveness of supervision at specific timesteps is limited. In response, we propose the following contributions: (1) We introduce a new perspective for interpreting the failure of the strategies. Specifically, we slightly extend the definition of Signal-to-Noise Ratio (SNR) and suggest observing the Probability Density Function (PDF) of SNR to understand the essence of the data robustness of the strategy. (2) We conduct numerous experiments and report over one hundred experimental results to empirically summarize a unified accelerating strategy from the perspective of PDF. (3) We develop a new supervision method that further accelerates the training process of DiT. Based on them, we propose FasterDiT, an exceedingly simple and practicable design strategy. With few lines of code modifications, it achieves 2.30 FID on ImageNet 256 resolution at 1000k iterations, which is comparable to DiT (2.27 FID) but 7 times faster in training., Comment: NeurIPS 2024 (poster)

Consistency models (CMs) are a powerful class of diffusion-based generative models optimized for fast sampling. Most existing CMs are trained using discretized timesteps, which introduce additional hyperparameters and are prone to discretization errors. While continuous-time formulations can mitigate these issues, their success has been limited by training instability. To address this, we propose a simplified theoretical framework that unifies previous parameterizations of diffusion models and CMs, identifying the root causes of instability. Based on this analysis, we introduce key improvements in diffusion process parameterization, network architecture, and training objectives. These changes enable us to train continuous-time CMs at an unprecedented scale, reaching 1.5B parameters on ImageNet 512x512. Our proposed training algorithm, using only two sampling steps, achieves FID scores of 2.06 on CIFAR-10, 1.48 on ImageNet 64x64, and 1.88 on ImageNet 512x512, narrowing the gap in FID scores with the best existing diffusion models to within 10%.

While large language models have shown impressive capabilities across a wide range of domains, they still encounter significant challenges in reasoning tasks that require gathering evidence over multiple turns and drawing logical conclusions. These challenges present significant obstacles for LLM chat user interfaces, which rely on multi-turn interactions to facilitate effective collaboration. This limitation leads to real-world issues; for example, service chatbots must gather necessary information from customers over multiple turns to diagnose and resolve problems effectively. Despite the multi-turn nature of many real-world LLM use cases, most existing benchmarks rely on carefully curated single-turn tests, which often blur the line between memorization and genuine reasoning. To address this, we introduce the Wason Inductive Logic Test (WILT), a simple yet challenging multi-turn reasoning benchmark designed to resist memorization. WILT is inspired by the Wason 2-4-6 task, where participants must infer a boolean function involving three variables (e.g., $x < y < z$) by proposing test cases (such as $(2, 4, 6)$). In WILT, each test starts from a clean slate, with only the initial instructions provided, preventing models from relying on pre-learned responses. Over several turns, models must interact with the environment by suggesting test cases to narrow the possible hypotheses and ultimately infer the hidden function based on the outcomes. Our findings reveal that LLMs struggle with this task, exhibiting distinct strengths and weaknesses: some are better at narrowing down the hypothesis space by proposing valuable test cases, while others are more adept at deducing the hidden function from observed cases. Despite these variations, the best-performing model achieves only 28% accuracy, highlighting a significant gap in LLM performance on complex multi-turn reasoning tasks., Comment: Submitted to ICLR 2025. Preprint version 1

Recent reports on the signatures of high-temperature superconductivity with a critical temperature Tc close to 80 K have triggered great research interest and extensive follow-up studies. Although zero-resistance state has been successfully achieved under improved hydrostatic pressure conditions, there is no clear evidence of superconducting diamagnetism in pressurized $\mathrm{La_{3}Ni_{2}O_{7-\delta}}$ due to the low superconducting volume fraction and limited magnetic measurement techniques under high pressure conditions. Here, using shallow nitrogen-vacancy centers implanted on the culet of diamond anvils as in-situ quantum sensors, we observe convincing evidence for the Meissner effect in polycrystalline samples $\mathrm{La_{3}Ni_{2}O_{7-\delta}}$ and $\mathrm{La_{2}PrNi_{2}O_{7}}$: the magnetic field expulsion during both field cooling and field warming processes. The correlated measurements of Raman spectra and NV-based magnetic imaging indicate an incomplete structural transformation related to the displacement of oxygen ions emerging in the non-superconducting region. Furthermore, comparative experiments on different pressure transmitting media (silicone oil and KBr) and nickelates ($\mathrm{La_{3}Ni_{2}O_{7-\delta}}$ and $\mathrm{La_{2}PrNi_{2}O_{7}}$) reveal that an improved hydrostatic pressure conditions and the substitution of La by Pr in $\mathrm{La_{3}Ni_{2}O_{7-\delta}}$ can dramatically increase the superconductivity. Our work clarifies the controversy about the Meissner effect of bilayer nickelate and contributes to a deeper understanding of the mechanism of nickelate high-temperature superconductors.

In the Milky Way and other main-sequence galaxies, stars form exclusively in molecular gas, which is traced by CO emission. However, low metallicity dwarf galaxies are often `CO-dark' in the sense that CO emission is not observable even at the high resolution and sensitivities of modern observing facilities. In this work we use ultra high-resolution simulations of four low-metalicity dwarf galaxies (which resolve star formation down to the scale of star-forming cores, 0.01 pc) combined with a time-dependent treatment of the chemistry of the interstellar medium, to investigate the star formation environment in this previously hidden regime. By generating synthetic observations of our models we show that the galaxies have high to extremely high dark gas fractions (0.13 to 1.00 dependent on beam size and conditions), yet despite this form stars. However, when examined on smaller scales, we find that the stars still form in regions dominated by molecular gas, it is simply that these are far smaller than the scale of the beam (1.5"). Thus, while stars in CO-dark dwarf galaxies form in small molecular cores like larger galaxies, their cloud-scale environment is very different., Comment: Re-submitted to MNRAS after referee report, comments and questions welcome, 23 pages, 16 figures

With the rapid advances in diffusion models, generating decent images from text prompts is no longer challenging. The key to text-to-image generation is how to optimize the results of a text-to-image generation model so that they can be better aligned with human intentions or prompts. Existing optimization methods commonly treat the entire image uniformly and conduct global optimization. These methods overlook the fact that when viewing an image, the human visual system naturally prioritizes attention toward salient areas, often neglecting less or non-salient regions. That is, humans are likely to neglect optimizations in non-salient areas. Consequently, although model retaining is conducted under the guidance of additional large and multimodality models, existing methods, which perform uniform optimizations, yield sub-optimal results. To address this alignment challenge effectively and efficiently, we propose Saliency Guided Optimization Of Diffusion Latents (SGOOL). We first employ a saliency detector to mimic the human visual attention system and mark out the salient regions. To avoid retraining an additional model, our method directly optimizes the diffusion latents. Besides, SGOOL utilizes an invertible diffusion process and endows it with the merits of constant memory implementation. Hence, our method becomes a parameter-efficient and plug-and-play fine-tuning method. Extensive experiments have been done with several metrics and human evaluation. Experimental results demonstrate the superiority of SGOOL in image quality and prompt alignment.

Charge distribution offers a unique fingerprint of important properties of electronic systems, including dielectric response, charge ordering and charge fractionalization. We develop a new architecture for charge sensing in two-dimensional electronic systems in a strong magnetic field. We probe local change of the chemical potential in a proximitized detector layer using scanning tunneling microscopy (STS), allowing us to infer the chemical potential and the charge profile in the sample. Our technique has both high energy (<0.3 meV) and spatial (<10 nm) resolution exceeding that of previous studies by an order of magnitude. We apply our technique to study the chemical potential of quantum Hall liquids in monolayer graphene under high magnetic fields and their responses to charge impurities. The chemical potential measurement provides a local probe of the thermodynamic gap of quantum Hall ferromagnets and fractional quantum Hall states. The screening charge profile reveals spatially oscillatory response of the quantum Hall liquids to charge impurities, and is consistent with the composite Fermi liquid picture close to the half-filling. Our technique also paves the way to map moir\'e potentials, probe Wigner crystals, and investigate fractional charges in quantum Hall and Chern insulators.

Large language models (LLMs) have demonstrated remarkable potential in solving complex tasks across diverse domains, typically by employing agentic workflows that follow detailed instructions and operational sequences. However, constructing these workflows requires significant human effort, limiting scalability and generalizability. Recent research has sought to automate the generation and optimization of these workflows, but existing methods still rely on initial manual setup and fall short of achieving fully automated and effective workflow generation. To address this challenge, we reformulate workflow optimization as a search problem over code-represented workflows, where LLM-invoking nodes are connected by edges. We introduce AFlow, an automated framework that efficiently explores this space using Monte Carlo Tree Search, iteratively refining workflows through code modification, tree-structured experience, and execution feedback. Empirical evaluations across six benchmark datasets demonstrate AFlow's efficacy, yielding a 5.7% average improvement over state-of-the-art baselines. Furthermore, AFlow enables smaller models to outperform GPT-4o on specific tasks at 4.55% of its inference cost in dollars. The code will be available at https://github.com/geekan/MetaGPT.

Driving world models have gained increasing attention due to their ability to model complex physical dynamics. However, their superb modeling capability is yet to be fully unleashed due to the limited video diversity in current driving datasets. We introduce DrivingDojo, the first dataset tailor-made for training interactive world models with complex driving dynamics. Our dataset features video clips with a complete set of driving maneuvers, diverse multi-agent interplay, and rich open-world driving knowledge, laying a stepping stone for future world model development. We further define an action instruction following (AIF) benchmark for world models and demonstrate the superiority of the proposed dataset for generating action-controlled future predictions., Comment: Accepted to NeurIPS 2024. Project page: https://drivingdojo.github.io/

Recently, diffusion models have achieved great success in mono-channel audio generation. However, when it comes to stereo audio generation, the soundscapes often have a complex scene of multiple objects and directions. Controlling stereo audio with spatial contexts remains challenging due to high data costs and unstable generative models. To the best of our knowledge, this work represents the first attempt to address these issues. We first construct a large-scale, simulation-based, and GPT-assisted dataset, BEWO-1M, with abundant soundscapes and descriptions even including moving and multiple sources. Beyond text modality, we have also acquired a set of images and rationally paired stereo audios through retrieval to advance multimodal generation. Existing audio generation models tend to generate rather random and indistinct spatial audio. To provide accurate guidance for latent diffusion models, we introduce the SpatialSonic model utilizing spatial-aware encoders and azimuth state matrices to reveal reasonable spatial guidance. By leveraging spatial guidance, our unified model not only achieves the objective of generating immersive and controllable spatial audio from text and image but also enables interactive audio generation during inference. Finally, under fair settings, we conduct subjective and objective evaluations on simulated and real-world data to compare our approach with prevailing methods. The results demonstrate the effectiveness of our method, highlighting its capability to generate spatial audio that adheres to physical rules.

The form of the entanglement Hamiltonian varies with the parameters of the original system. Whether there is a singularity is the key problem for demonstrating/negating the universality of the relation between the entanglement spectrum and edge energy spectrum. We carefully study the phase diagram of a 1D Ising entanglement Hamiltonian as an example to clarify the long-standing controversy of the general relation between the entanglement Hamiltonian and original Hamiltonian. Interestingly, even if the singularities indeed exist, the Li-Haldane-Poilblanc conjecture, i.e., the general relation between the entanglement spectrum and edge energy spectrum, seemingly still holds., Comment: 13 pages, 14 figures

As the 50G optical access gradually matures, it is time to discuss Beyond 50G optical access. According to the evolution rules of optical access standards, Beyond 50G optical access data rate may achieve 200Gb/s. Direct detection faces great challenges for Beyond 50G optical access, which makes coherent detection a potential solution. Similar to 50G optical timing-division-multiple access (TDMA), burst-mode digital signal processing (BM-DSP) is also required for Beyond 50G coherent optical TDMA (CO-TDMA). This paper proposes coherent BM-DSP (Co-BM-DSP) based on approximately 10ns designed preambles to process the burst signal for 200G CO-TDMA, which can fast estimate the state of polarization, frequency offset, sampling phase offset, synchronization position, and equalizer coefficients. Meanwhile, for obtaining the equalizer coefficients based on the designed preamble, the channel estimation based on the minimum-mean-square-error criterion is theoretically proven to have a unique solution for ensuring reliability. In conclusion, the proposed Co-BM-DSP based on the designed preambles paves the way for the applications of Beyond 50G CO-TDMA., Comment: This paper has been submitted to the Journal of Lightwave Technology

Generating realistic 3D human-human interactions from textual descriptions remains a challenging task. Existing approaches, typically based on diffusion models, often generate unnatural and unrealistic results. In this work, we introduce InterMask, a novel framework for generating human interactions using collaborative masked modeling in discrete space. InterMask first employs a VQ-VAE to transform each motion sequence into a 2D discrete motion token map. Unlike traditional 1D VQ token maps, it better preserves fine-grained spatio-temporal details and promotes spatial awareness within each token. Building on this representation, InterMask utilizes a generative masked modeling framework to collaboratively model the tokens of two interacting individuals. This is achieved by employing a transformer architecture specifically designed to capture complex spatio-temporal interdependencies. During training, it randomly masks the motion tokens of both individuals and learns to predict them. In inference, starting from fully masked sequences, it progressively fills in the tokens for both individuals. With its enhanced motion representation, dedicated architecture, and effective learning strategy, InterMask achieves state-of-the-art results, producing high-fidelity and diverse human interactions. It outperforms previous methods, achieving an FID of $5.154$ (vs $5.535$ for in2IN) on the InterHuman dataset and $0.399$ (vs $5.207$ for InterGen) on the InterX dataset. Additionally, InterMask seamlessly supports reaction generation without the need for model redesign or fine-tuning., Comment: Project webpage: https://gohar-malik.github.io/intermask

We explore the Fano resonance in ZrTe5, using Raman scattering measurements. We identified two closely spaced B2g phonon modes, B2g I and B2g II, around 9 meV and 10 meV, respectively. Interestingly, only B2g I exhibited the Fano resonance, an outcome of quantum interference between discrete phonon modes and continuous electronic excitations. This is consistent with the much stronger electron-phonon coupling of B2g I mode demonstrated by first-principles calculations. Additionally, temperature-dependent measurements highlight an enhanced Fano asymmetry at elevated temperatures, originating from the thermal effect on the joint electron-hole density of states. This study offers insights into the complex interrelation of electron-phonon coupling, thermal effect, and Fano resonances in ZrTe5.

Foundation models have become a cornerstone in deep learning, with techniques like Low-Rank Adaptation (LoRA) offering efficient fine-tuning of large models. Similarly, methods such as Retrieval-Augmented Generation (RAG), which leverage vectorized databases, have further improved model performance by grounding outputs in external information. While these approaches have demonstrated notable success, they often require extensive training or labeled data, which can limit their adaptability in resource-constrained environments. To address these challenges, we introduce Retrieval-based Parameter Ensemble (RPE), a new method that creates a vectorized database of LoRAs, enabling efficient retrieval and application of model adaptations to new tasks. RPE minimizes the need for extensive training and eliminates the requirement for labeled data, making it particularly effective for zero-shot learning. Additionally, RPE is well-suited for privacy-sensitive domains like healthcare, as it modifies model parameters without accessing raw data. When applied to tasks such as medical report generation and image segmentation, RPE not only proved effective but also surpassed supervised fine-tuning methods in certain cases, highlighting its potential to enhance both computational efficiency and privacy in deep learning applications.

Facial expression datasets remain limited in scale due to privacy concerns, the subjectivity of annotations, and the labor-intensive nature of data collection. This limitation poses a significant challenge for developing modern deep learning-based facial expression analysis models, particularly foundation models, that rely on large-scale data for optimal performance. To tackle the overarching and complex challenge, we introduce SynFER (Synthesis of Facial Expressions with Refined Control), a novel framework for synthesizing facial expression image data based on high-level textual descriptions as well as more fine-grained and precise control through facial action units. To ensure the quality and reliability of the synthetic data, we propose a semantic guidance technique to steer the generation process and a pseudo-label generator to help rectify the facial expression labels for the synthetic images. To demonstrate the generation fidelity and the effectiveness of the synthetic data from SynFER, we conduct extensive experiments on representation learning using both synthetic data and real-world data. Experiment results validate the efficacy of the proposed approach and the synthetic data. Notably, our approach achieves a 67.23% classification accuracy on AffectNet when training solely with synthetic data equivalent to the AffectNet training set size, which increases to 69.84% when scaling up to five times the original size. Our code will be made publicly available.

Backdoor attacks pose a significant threat to Deep Neural Networks (DNNs) as they allow attackers to manipulate model predictions with backdoor triggers. To address these security vulnerabilities, various backdoor purification methods have been proposed to purify compromised models. Typically, these purified models exhibit low Attack Success Rates (ASR), rendering them resistant to backdoored inputs. However, Does achieving a low ASR through current safety purification methods truly eliminate learned backdoor features from the pretraining phase? In this paper, we provide an affirmative answer to this question by thoroughly investigating the Post-Purification Robustness of current backdoor purification methods. We find that current safety purification methods are vulnerable to the rapid re-learning of backdoor behavior, even when further fine-tuning of purified models is performed using a very small number of poisoned samples. Based on this, we further propose the practical Query-based Reactivation Attack (QRA) which could effectively reactivate the backdoor by merely querying purified models. We find the failure to achieve satisfactory post-purification robustness stems from the insufficient deviation of purified models from the backdoored model along the backdoor-connected path. To improve the post-purification robustness, we propose a straightforward tuning defense, Path-Aware Minimization (PAM), which promotes deviation along backdoor-connected paths with extra model updates. Extensive experiments demonstrate that PAM significantly improves post-purification robustness while maintaining a good clean accuracy and low ASR. Our work provides a new perspective on understanding the effectiveness of backdoor safety tuning and highlights the importance of faithfully assessing the model's safety., Comment: NeurIPS 2024 Spotlight paper. The first two authors contributed equally

Predicting ground-state conformation from the corresponding molecular graph is crucial for many chemical applications, such as molecular modeling, molecular docking, and molecular property prediction. Recently, many learning-based methods have been proposed to replace time-consuming simulations for this task. However, these methods are often inefficient and sub-optimal as they merely rely on molecular graph information to make predictions from scratch. In this work, considering that molecular low-quality conformations are readily available, we propose a novel framework called ConfOpt to predict molecular ground-state conformation from the perspective of conformation optimization. Specifically, ConfOpt takes the molecular graph and corresponding low-quality 3D conformation as inputs, and then derives the ground-state conformation by iteratively optimizing the low-quality conformation under the guidance of the molecular graph. During training, ConfOpt concurrently optimizes the predicted atomic 3D coordinates and the corresponding interatomic distances, resulting in a strong predictive model. Extensive experiments demonstrate that ConfOpt significantly outperforms existing methods, thus providing a new paradigm for efficiently and accurately predicting molecular ground-state conformation.

Hypomimia is a non-motor symptom of Parkinson's disease that manifests as delayed facial movements and expressions, along with challenges in articulation and emotion. Currently, subjective evaluation by neurologists is the primary method for hypomimia detection, and conventional rehabilitation approaches heavily rely on verbal prompts from rehabilitation physicians. There remains a deficiency in accessible, user-friendly and scientifically rigorous assistive tools for hypomimia treatments. To investigate this, we developed HypomimaCoach, an Action Unit (AU)-based digital therapy system for hypomimia detection and rehabilitation in Parkinson's disease. The HypomimaCoach system was designed to facilitate engagement through the incorporation of both relaxed and controlled rehabilitation exercises, while also stimulating initiative through the integration of digital therapies that incorporated traditional face training methods. We extract action unit(AU) features and their relationship for hypomimia detection. In order to facilitate rehabilitation, a series of training programmes have been devised based on the Action Units (AUs) and patients are provided with real-time feedback through an additional AU recognition model, which guides them through their training routines. A pilot study was conducted with seven participants in China, all of whom exhibited symptoms of Parkinson's disease hypomimia. The results of the pilot study demonstrated a positive impact on participants' self-efficacy, with favourable feedback received. Furthermore, physician evaluations validated the system's applicability in a therapeutic setting for patients with Parkinson's disease, as well as its potential value in clinical applications.

Given the wide adoption of multimodal sensors (e.g., camera, lidar, radar) by autonomous vehicles (AVs), deep analytics to fuse their outputs for a robust perception become imperative. However, existing fusion methods often make two assumptions rarely holding in practice: i) similar data distributions for all inputs and ii) constant availability for all sensors. Because, for example, lidars have various resolutions and failures of radars may occur, such variability often results in significant performance degradation in fusion. To this end, we present tREADi, an adaptive inference system that accommodates the variability of multimodal sensory data and thus enables robust and efficient perception. t-READi identifies variation-sensitive yet structure-specific model parameters; it then adapts only these parameters while keeping the rest intact. t-READi also leverages a cross-modality contrastive learning method to compensate for the loss from missing modalities. Both functions are implemented to maintain compatibility with existing multimodal deep fusion methods. The extensive experiments evidently demonstrate that compared with the status quo approaches, t-READi not only improves the average inference accuracy by more than 6% but also reduces the inference latency by almost 15x with the cost of only 5% extra memory overhead in the worst case under realistic data and modal variations., Comment: 14 pages, 16 figures

Recent advancements in learned 3D representations have enabled significant progress in solving complex robotic manipulation tasks, particularly for rigid-body objects. However, manipulating granular materials such as beans, nuts, and rice, remains challenging due to the intricate physics of particle interactions, high-dimensional and partially observable state, inability to visually track individual particles in a pile, and the computational demands of accurate dynamics prediction. Current deep latent dynamics models often struggle to generalize in granular material manipulation due to a lack of inductive biases. In this work, we propose a novel approach that learns a visual dynamics model over Gaussian splatting representations of scenes and leverages this model for manipulating granular media via Model-Predictive Control. Our method enables efficient optimization for complex manipulation tasks on piles of granular media. We evaluate our approach in both simulated and real-world settings, demonstrating its ability to solve unseen planning tasks and generalize to new environments in a zero-shot transfer. We also show significant prediction and manipulation performance improvements compared to existing granular media manipulation methods., Comment: project website https://weichengtseng.github.io/gs-granular-mani/

Tidal energy is one of the key components in increasing the penetration rate of renewable energy. The penetration of tidal energy in the electrical grid depends on the accuracy of tidal current speed forecasting. Modeling inaccuracies hinder forecast accuracy. Previous research has primarily used physical models to forecast tidal current speed. However, tidal current variations influenced by the orbital periods of celestial bodies make accurate physical modeling challenging. Researching the multiple periodicity of tides is crucial for accurately forecasting tidal current speed. In this article, we propose the Wavelet-Enhanced Convolutional Network (WCN) to learn multiple periodicity. The framework embeds intra-period and inter-period variations of one-dimensional tidal current data into the rows and columns of a two-dimensional tensor. Then, the two-dimensional variations of the sequence can be processed by convolutional kernels. We integrate a time-frequency analysis method into the framework to further address local periodic features. Additionally, to enhance the framework's stability, we optimize the framework's hyperparameters with the Tree-structured Parzen Estimator algorithm. The proposed framework avoids the lack of learning multiple periodicity. Compared with benchmarks, the proposed framework reduces the mean absolute error and mean square error in 10-step forecasting by, at most, 90.36% and 97.56%, respectively.

3D object generation from a single image involves estimating the full 3D geometry and texture of unseen views from an unposed RGB image captured in the wild. Accurately reconstructing an object's complete 3D structure and texture has numerous applications in real-world scenarios, including robotic manipulation, grasping, 3D scene understanding, and AR/VR. Recent advancements in 3D object generation have introduced techniques that reconstruct an object's 3D shape and texture by optimizing the efficient representation of Gaussian Splatting, guided by pre-trained 2D or 3D diffusion models. However, a notable disparity exists between the training datasets of these models, leading to distinct differences in their outputs. While 2D models generate highly detailed visuals, they lack cross-view consistency in geometry and texture. In contrast, 3D models ensure consistency across different views but often result in overly smooth textures. We propose bridging the gap between 2D and 3D diffusion models to address this limitation by integrating a two-stage frequency-based distillation loss with Gaussian Splatting. Specifically, we leverage geometric priors in the low-frequency spectrum from a 3D diffusion model to maintain consistent geometry and use a 2D diffusion model to refine the fidelity and texture in the high-frequency spectrum of the generated 3D structure, resulting in more detailed and fine-grained outcomes. Our approach enhances geometric consistency and visual quality, outperforming the current SOTA. Additionally, we demonstrate the easy adaptability of our method for efficient object pose estimation and tracking.

While server-side Large Language Models (LLMs) demonstrate proficiency in function calling and complex reasoning, deploying Small Language Models (SLMs) directly on devices brings opportunities to improve latency and privacy but also introduces unique challenges for accuracy and memory. We introduce CAMPHOR, an innovative on-device SLM multi-agent framework designed to handle multiple user inputs and reason over personal context locally, ensuring privacy is maintained. CAMPHOR employs a hierarchical architecture where a high-order reasoning agent decomposes complex tasks and coordinates expert agents responsible for personal context retrieval, tool interaction, and dynamic plan generation. By implementing parameter sharing across agents and leveraging prompt compression, we significantly reduce model size, latency, and memory usage. To validate our approach, we present a novel dataset capturing multi-agent task trajectories centered on personalized mobile assistant use-cases. Our experiments reveal that fine-tuned SLM agents not only surpass closed-source LLMs in task completion F1 by~35\% but also eliminate the need for server-device communication, all while enhancing privacy.

With the rapid advancement of Internet technology, the threat of malware to computer systems and network security has intensified. Malware affects individual privacy and security and poses risks to critical infrastructures of enterprises and nations. The increasing quantity and complexity of malware, along with its concealment and diversity, challenge traditional detection techniques. Static detection methods struggle against variants and packed malware, while dynamic methods face high costs and risks that limit their application. Consequently, there is an urgent need for novel and efficient malware detection techniques to improve accuracy and robustness. This study first employs the minhash algorithm to convert binary files of malware into grayscale images, followed by the extraction of global and local texture features using GIST and LBP algorithms. Additionally, the study utilizes IDA Pro to decompile and extract opcode sequences, applying N-gram and tf-idf algorithms for feature vectorization. The fusion of these features enables the model to comprehensively capture the behavioral characteristics of malware. In terms of model construction, a CNN-BiLSTM fusion model is designed to simultaneously process image features and opcode sequences, enhancing classification performance. Experimental validation on multiple public datasets demonstrates that the proposed method significantly outperforms traditional detection techniques in terms of accuracy, recall, and F1 score, particularly in detecting variants and obfuscated malware with greater stability. The research presented in this paper offers new insights into the development of malware detection technologies, validating the effectiveness of feature and model fusion, and holds promising application prospects.