Search

Cameras and LiDAR are essential sensors for autonomous vehicles. Camera-LiDAR data fusion compensate for deficiencies of stand-alone sensors but relies on precise extrinsic calibration. Many learning-based calibration methods predict extrinsic parameters in a single step. Driven by the growing demand for higher accuracy, a few approaches utilize multi-range models or integrate multiple methods to improve extrinsic parameter predictions, but these strategies incur extended training times and require additional storage for separate models. To address these issues, we propose a single-model iterative approach based on surrogate diffusion to significantly enhance the capacity of individual calibration methods. By applying a buffering technique proposed by us, the inference time of our surrogate diffusion is 43.7% less than that of multi-range models. Additionally, we create a calibration network as our denoiser, featuring both projection-first and encoding-first branches for effective point feature extraction. Extensive experiments demonstrate that our diffusion model outperforms other single-model iterative methods and delivers competitive results compared to multi-range models. Our denoiser exceeds state-of-the-art calibration methods, reducing the rotation error by 24.5% compared to the second-best method. Furthermore, with the proposed diffusion applied, it achieves 20.4% less rotation error and 9.6% less translation error., Comment: 11 pages, 4 figures, 3 tables

Multimodal emotion recognition in conversation (MER) aims to accurately identify emotions in conversational utterances by integrating multimodal information. Previous methods usually treat multimodal information as equal quality and employ symmetric architectures to conduct multimodal fusion. However, in reality, the quality of different modalities usually varies considerably, and utilizing a symmetric architecture is difficult to accurately recognize conversational emotions when dealing with uneven modal information. Furthermore, fusing multi-modality information in a single granularity may fail to adequately integrate modal information, exacerbating the inaccuracy in emotion recognition. In this paper, we propose a novel Cross-Modality Augmented Transformer with Hierarchical Variational Distillation, called CMATH, which consists of two major components, i.e., Multimodal Interaction Fusion and Hierarchical Variational Distillation. The former is comprised of two submodules, including Modality Reconstruction and Cross-Modality Augmented Transformer (CMA-Transformer), where Modality Reconstruction focuses on obtaining high-quality compressed representation of each modality, and CMA-Transformer adopts an asymmetric fusion strategy which treats one modality as the central modality and takes others as auxiliary modalities. The latter first designs a variational fusion network to fuse the fine-grained representations learned by CMA- Transformer into a coarse-grained representations. Then, it introduces a hierarchical distillation framework to maintain the consistency between modality representations with different granularities. Experiments on the IEMOCAP and MELD datasets demonstrate that our proposed model outperforms previous state-of-the-art baselines. Implementation codes can be available at https://github.com/ cjw-MER/CMATH.

We propose a compressive yet effective mesh representation, Blocked and Patchified Tokenization (BPT), facilitating the generation of meshes exceeding 8k faces. BPT compresses mesh sequences by employing block-wise indexing and patch aggregation, reducing their length by approximately 75\% compared to the original sequences. This compression milestone unlocks the potential to utilize mesh data with significantly more faces, thereby enhancing detail richness and improving generation robustness. Empowered with the BPT, we have built a foundation mesh generative model training on scaled mesh data to support flexible control for point clouds and images. Our model demonstrates the capability to generate meshes with intricate details and accurate topology, achieving SoTA performance on mesh generation and reaching the level for direct product usage., Comment: Homepage: https://whaohan.github.io/bpt , Code: https://github.com/whaohan/bpt

Beyond-triple fact representations including hyper-relational facts with auxiliary key-value pairs, temporal facts with additional timestamps, and nested facts implying relationships between facts, are gaining significant attention. However, existing link prediction models are usually designed for one specific type of facts, making it difficult to generalize to other fact representations. To overcome this limitation, we propose a Unified Hierarchical Representation learning framework (UniHR) for unified knowledge graph link prediction. It consists of a unified Hierarchical Data Representation (HiDR) module and a unified Hierarchical Structure Learning (HiSL) module as graph encoder. The HiDR module unifies hyper-relational KGs, temporal KGs, and nested factual KGs into triple-based representations. Then HiSL incorporates intra-fact and inter-fact message passing, focusing on enhancing the semantic information within individual facts and enriching the structural information between facts. Experimental results across 7 datasets from 3 types of KGs demonstrate that our UniHR outperforms baselines designed for one specific kind of KG, indicating strong generalization capability of HiDR form and the effectiveness of HiSL module. Code and data are available at https://github.com/Lza12a/UniHR.

Large Language Models (LLMs) are increasingly recognized for their practical applications. However, these models often encounter challenges in dynamically changing knowledge, as well as in managing unknown static knowledge. Retrieval-Augmented Generation (RAG) tackles this challenge and has shown a significant impact on LLMs. Actually, we find that the impact of RAG on the question answering capabilities of LLMs can be categorized into three groups: beneficial, neutral, and harmful. By minimizing retrieval requests that yield neutral or harmful results, we can effectively reduce both time and computational costs, while also improving the overall performance of LLMs. This insight motivates us to differentiate between types of questions using certain metrics as indicators, to decrease the retrieval ratio without compromising performance. In our work, we propose a method that is able to identify different types of questions from this view by training a Knowledge Boundary Model (KBM). Experiments conducted on 11 English and Chinese datasets illustrate that the KBM effectively delineates the knowledge boundary, significantly decreasing the proportion of retrievals required for optimal end-to-end performance. Specifically, we evaluate the effectiveness of KBM in three complex scenarios: dynamic knowledge, long-tail static knowledge, and multi-hop problems, as well as its functionality as an external LLM plug-in.

While 3D generative models have greatly improved artists' workflows, the existing diffusion models for 3D generation suffer from slow generation and poor generalization. To address this issue, we propose a two-stage approach named Hunyuan3D-1.0 including a lite version and a standard version, that both support text- and image-conditioned generation. In the first stage, we employ a multi-view diffusion model that efficiently generates multi-view RGB in approximately 4 seconds. These multi-view images capture rich details of the 3D asset from different viewpoints, relaxing the tasks from single-view to multi-view reconstruction. In the second stage, we introduce a feed-forward reconstruction model that rapidly and faithfully reconstructs the 3D asset given the generated multi-view images in approximately 7 seconds. The reconstruction network learns to handle noises and in-consistency introduced by the multi-view diffusion and leverages the available information from the condition image to efficiently recover the 3D structure. Our framework involves the text-to-image model, i.e., Hunyuan-DiT, making it a unified framework to support both text- and image-conditioned 3D generation. Our standard version has 3x more parameters than our lite and other existing model. Our Hunyuan3D-1.0 achieves an impressive balance between speed and quality, significantly reducing generation time while maintaining the quality and diversity of the produced assets., Comment: Technical Report; 3D Generation

Data races are critical issues in multithreaded program, leading to unpredictable, catastrophic and difficult-to-diagnose problems. Despite the extensive in-house testing, data races often escape to deployed software and manifest in production runs. Existing approaches suffer from either prohibitively high runtime overhead or incomplete detection capability. In this paper, we introduce HardRace, a data race monitor to detect races on-the-fly while with sufficiently low runtime overhead and high detection capability. HardRace firstly employs sound static analysis to determine a minimal set of essential memory accesses relevant to data races. It then leverages hardware trace instruction, i.e., Intel PTWRITE, to selectively record only these memory accesses and thread synchronization events during execution with negligible runtime overhead. Given the tracing data, HardRace performs standard data race detection algorithms to timely report potential races occurred in production runs. The experimental evaluations show that HardRace outperforms state-of-the-art tools like ProRace and Kard in terms of both runtime overhead and detection capability -- HardRace can detect all kinds of data races in read-world applications while maintaining a negligible overhead, less than 2% on average.

In this work, a formalism is presented for the helicity amplitude analysis of the decays $\psi(2S) \to \gamma_1 \chi_{cJ},~ \chi_{cJ} \to \gamma_2 V (V=\rho^0,~\phi,~\omega)$~(the subscript 1,2 is used to distinguish the two radiative photons), and the polarization expressions of the P-wave charmonia $\chi_{cJ}$ and the vector mesons $\rho^0, \phi, \omega$ for experimental measurements at Electron-Positron Collider. In addition, we derive the formulae of the angular distributions of the $\chi_{c1,2} \to \gamma V$ to extract the degree of transverse polarization $P_T$ of $e^+ e^-$ pairs with symmetric beam energy as well as the ratios of two helicity amplitudes $x$ (in $\chi_{c1}$ decays) and $x,~y$ (in $\chi_{c2}$ decays) representing the relative magnitudes of transverse to longitudinal polarization amplitude, and validate it by performing the Monte Carlo simulation. Finally, the statistical sensitivity of $P_T$, $x$ and $y$ are estimated based on the large $\psi(2S)$ data samples collected at the current and proposed future $e^+e^-$ collider experiment., Comment: 26 pages, 13 figures. Submitted to CPC

Large language models (LLMs) have significantly advanced performance across a spectrum of natural language processing (NLP) tasks. Yet, their application to knowledge graphs (KGs), which describe facts in the form of triplets and allow minimal hallucinations, remains an underexplored frontier. In this paper, we investigate the integration of LLMs with KGs by introducing a specialized KG Language (KGL), where a sentence precisely consists of an entity noun, a relation verb, and ends with another entity noun. Despite KGL's unfamiliar vocabulary to the LLM, we facilitate its learning through a tailored dictionary and illustrative sentences, and enhance context understanding via real-time KG context retrieval and KGL token embedding augmentation. Our results reveal that LLMs can achieve fluency in KGL, drastically reducing errors compared to conventional KG embedding methods on KG completion. Furthermore, our enhanced LLM shows exceptional competence in generating accurate three-word sentences from an initial entity and interpreting new unseen terms out of KGs., Comment: NeurIPS 2024 (spotlight)

Traditional image codecs emphasize signal fidelity and human perception, often at the expense of machine vision tasks. Deep learning methods have demonstrated promising coding performance by utilizing rich semantic embeddings optimized for both human and machine vision. However, these compact embeddings struggle to capture fine details such as contours and textures, resulting in imperfect reconstructions. Furthermore, existing learning-based codecs lack scalability. To address these limitations, this paper introduces a content-adaptive diffusion model for scalable image compression. The proposed method encodes fine textures through a diffusion process, enhancing perceptual quality while preserving essential features for machine vision tasks. The approach employs a Markov palette diffusion model combined with widely used feature extractors and image generators, enabling efficient data compression. By leveraging collaborative texture-semantic feature extraction and pseudo-label generation, the method accurately captures texture information. A content-adaptive Markov palette diffusion model is then applied to represent both low-level textures and high-level semantic content in a scalable manner. This framework offers flexible control over compression ratios by selecting intermediate diffusion states, eliminating the need for retraining deep learning models at different operating points. Extensive experiments demonstrate the effectiveness of the proposed framework in both image reconstruction and downstream machine vision tasks such as object detection, segmentation, and facial landmark detection, achieving superior perceptual quality compared to state-of-the-art methods.

3D face editing is a significant task in multimedia, aimed at the manipulation of 3D face models across various control signals. The success of 3D-aware GAN provides expressive 3D models learned from 2D single-view images only, encouraging researchers to discover semantic editing directions in its latent space. However, previous methods face challenges in balancing quality, efficiency, and generalization. To solve the problem, we explore the possibility of introducing the strength of diffusion model into 3D-aware GANs. In this paper, we present Face Clan, a fast and text-general approach for generating and manipulating 3D faces based on arbitrary attribute descriptions. To achieve disentangled editing, we propose to diffuse on the latent space under a pair of opposite prompts to estimate the mask indicating the region of interest on latent codes. Based on the mask, we then apply denoising to the masked latent codes to reveal the editing direction. Our method offers a precisely controllable manipulation method, allowing users to intuitively customize regions of interest with the text description. Experiments demonstrate the effectiveness and generalization of our Face Clan for various pre-trained GANs. It offers an intuitive and wide application for text-guided face editing that contributes to the landscape of multimedia content creation.

Neural radiance fields have recently revolutionized novel-view synthesis and achieved high-fidelity renderings. However, these methods sacrifice the geometry for the rendering quality, limiting their further applications including relighting and deformation. How to synthesize photo-realistic rendering while reconstructing accurate geometry remains an unsolved problem. In this work, we present AniSDF, a novel approach that learns fused-granularity neural surfaces with physics-based encoding for high-fidelity 3D reconstruction. Different from previous neural surfaces, our fused-granularity geometry structure balances the overall structures and fine geometric details, producing accurate geometry reconstruction. To disambiguate geometry from reflective appearance, we introduce blended radiance fields to model diffuse and specularity following the anisotropic spherical Gaussian encoding, a physics-based rendering pipeline. With these designs, AniSDF can reconstruct objects with complex structures and produce high-quality renderings. Furthermore, our method is a unified model that does not require complex hyperparameter tuning for specific objects. Extensive experiments demonstrate that our method boosts the quality of SDF-based methods by a great scale in both geometry reconstruction and novel-view synthesis., Comment: Project Page: https://g-1nonly.github.io/AniSDF_Website/

Vision-based tactile sensors (VBTSs) provide high-resolution tactile images crucial for robot in-hand manipulation. However, force sensing in VBTSs is underutilized due to the costly and time-intensive process of acquiring paired tactile images and force labels. In this study, we introduce a transferable force prediction model, TransForce, designed to leverage collected image-force paired data for new sensors under varying illumination colors and marker patterns while improving the accuracy of predicted forces, especially in the shear direction. Our model effectively achieves translation of tactile images from the source domain to the target domain, ensuring that the generated tactile images reflect the illumination colors and marker patterns of the new sensors while accurately aligning the elastomer deformation observed in existing sensors, which is beneficial to force prediction of new sensors. As such, a recurrent force prediction model trained with generated sequential tactile images and existing force labels is employed to estimate higher-accuracy forces for new sensors with lowest average errors of 0.69N (5.8\% in full work range) in $x$-axis, 0.70N (5.8\%) in $y$-axis, and 1.11N (6.9\%) in $z$-axis compared with models trained with single images. The experimental results also reveal that pure marker modality is more helpful than the RGB modality in improving the accuracy of force in the shear direction, while the RGB modality show better performance in the normal direction.

We introduce Seed-Music, a suite of music generation systems capable of producing high-quality music with fine-grained style control. Our unified framework leverages both auto-regressive language modeling and diffusion approaches to support two key music creation workflows: controlled music generation and post-production editing. For controlled music generation, our system enables vocal music generation with performance controls from multi-modal inputs, including style descriptions, audio references, musical scores, and voice prompts. For post-production editing, it offers interactive tools for editing lyrics and vocal melodies directly in the generated audio. We encourage readers to listen to demo audio examples at https://team.doubao.com/seed-music "https://team.doubao.com/seed-music"., Comment: Seed-Music technical report, 20 pages, 5 figures

In recent years, a more advanced form of phishing has arisen on Ethereum, surpassing early-stage, simple transaction phishing. This new form, which we refer to as payload-based transaction phishing (PTXPHISH), manipulates smart contract interactions through the execution of malicious payloads to deceive users. PTXPHISH has rapidly emerged as a significant threat, leading to incidents that caused losses exceeding \$70 million in 2023 reports. Despite its substantial impact, no previous studies have systematically explored PTXPHISH In this paper, we present the first comprehensive study of the PTXPHISH on Ethereum. Firstly, we conduct a long-term data collection and put considerable effort into establishing the first ground-truth PTXPHISH dataset, consisting of 5,000 phishing transactions. Based on the dataset, we dissect PTXPHISH, categorizing phishing tactics into four primary categories and eleven sub-categories. Secondly, we propose a rule-based multi-dimensional detection approach to identify PTXPHISH, achieving over 99% accuracy in the ground-truth dataset. Finally, we conducted a large-scale detection spanning 300 days and discovered a total of 130,637 phishing transactions on Ethereum, resulting in losses exceeding $341.9 million. Our in-depth analysis of these phishing transactions yielded valuable and insightful findings. Furthermore, our work has made significant contributions to mitigating real-world threats. We have reported 1,726 phishing addresses to the community, accounting for 42.7% of total community contributions during the same period. Additionally, we have sent 2,539 on-chain alert messages, assisting 1,980 victims. This research serves as a valuable reference in combating the emerging PTXPHISH and safeguarding users' assets.

Horizontal collaboration between operators can save traffic operation costs, a concept that has been particularly validated in the logistics field. Due to the increasing transportation demand and the introduction of charging times for electric vehicles, there is growing pressure on airport ground support services. This study introduces the concept of coalition to airport ground support services. Unlike most studies on horizontal collaboration, the scheduling for airport ground support services needs to particularly consider punctuality issues. In this study, we separately establish electric vehicle scheduling models for operator-separate and operator-cooperated modes and design an algorithm based on the concept of the Adaptive Large Neighborhood Search algorithm, aiming to obtain the electric vehicle scheduling plan with minimum cost and delay time. Furthermore, the study proposes a cost allocation method that considers the degree of sharing among operators to ensure the feasibility of coalition. Finally, we conducted numerical experiments based on actual airport operation data. The experiments verified the effectiveness of the algorithm and the cost allocation method. Compared to solvers, our algorithm can obtain feasible solutions in a shorter time while ensuring that the objective function gap is within 2%. Additionally, the improved cost allocation method is fairer compared to the traditional Shapley method. Numerical experiments also show that coalition can save 15-25% of airport operating costs and 26-39% of delay time, with savings varying based on the sharing parameters. Through quantitative analysis such as sensitivity analysis, the study provides insights into the variation patterns of overall and individual shared utilities and offers suggestions and decision-making mechanisms for the configuration and operation of airport ground operators.

Disentanglement of visual features of primitives (i.e., attributes and objects) has shown exceptional results in Compositional Zero-shot Learning (CZSL). However, due to the feature divergence of an attribute (resp. object) when combined with different objects (resp. attributes), it is challenging to learn disentangled primitive features that are general across different compositions. To this end, we propose the solution of cross-composition feature disentanglement, which takes multiple primitive-sharing compositions as inputs and constrains the disentangled primitive features to be general across these compositions. More specifically, we leverage a compositional graph to define the overall primitive-sharing relationships between compositions, and build a task-specific architecture upon the recently successful large pre-trained vision-language model (VLM) CLIP, with dual cross-composition disentangling adapters (called L-Adapter and V-Adapter) inserted into CLIP's frozen text and image encoders, respectively. Evaluation on three popular CZSL benchmarks shows that our proposed solution significantly improves the performance of CZSL, and its components have been verified by solid ablation studies., Comment: work in progress

Optical tactile sensors play a pivotal role in robot perception and manipulation tasks. The membrane of these sensors can be painted with markers or remain markerless, enabling them to function in either marker or markerless mode. However, this uni-modal selection means the sensor is only suitable for either manipulation or perception tasks. While markers are vital for manipulation, they can also obstruct the camera, thereby impeding perception. The dilemma of selecting between marker and markerless modes presents a significant obstacle. To address this issue, we propose a novel mode-switchable optical tactile sensing approach that facilitates transitions between the two modes. The marker-to-markerless transition is achieved through a generative model, whereas its inverse transition is realized using a sparsely supervised regressive model. Our approach allows a single-mode optical sensor to operate effectively in both marker and markerless modes without the need for additional hardware, making it well-suited for both perception and manipulation tasks. Extensive experiments validate the effectiveness of our method. For perception tasks, our approach decreases the number of categories that include misclassified samples by 2 and improves contact area segmentation IoU by 3.53%. For manipulation tasks, our method attains a high success rate of 92.59% in slip detection. Code, dataset and demo videos are available at the project website: https://gitouni.github.io/Marker-Markerless-Transition/, Comment: 8 pages, 10 figures

Dialogue serves as the most natural manner of human-computer interaction (HCI). Recent advancements in speech language models (SLM) have significantly enhanced speech-based conversational AI. However, these models are limited to turn-based conversation, lacking the ability to interact with humans in real-time spoken scenarios, for example, being interrupted when the generated content is not satisfactory. To address these limitations, we explore full duplex modeling (FDM) in interactive speech language models (iSLM), focusing on enhancing real-time interaction and, more explicitly, exploring the quintessential ability of interruption. We introduce a novel model design, namely listening-while-speaking language model (LSLM), an end-to-end system equipped with both listening and speaking channels. Our LSLM employs a token-based decoder-only TTS for speech generation and a streaming self-supervised learning (SSL) encoder for real-time audio input. LSLM fuses both channels for autoregressive generation and detects turn-taking in real time. Three fusion strategies -- early fusion, middle fusion, and late fusion -- are explored, with middle fusion achieving an optimal balance between speech generation and real-time interaction. Two experimental settings, command-based FDM and voice-based FDM, demonstrate LSLM's robustness to noise and sensitivity to diverse instructions. Our results highlight LSLM's capability to achieve duplex communication with minimal impact on existing systems. This study aims to advance the development of interactive speech dialogue systems, enhancing their applicability in real-world contexts., Comment: Demo can be found at https://ddlbojack.github.io/LSLM

Spiking Neural Networks (SNNs) are extensively utilized in brain-inspired computing and neuroscience research. To enhance the speed and energy efficiency of SNNs, several many-core accelerators have been developed. However, maintaining the accuracy of SNNs often necessitates frequent explicit synchronization among all cores, which presents a challenge to overall efficiency. In this paper, we propose an asynchronous architecture for Spiking Neural Networks (SNNs) that eliminates the need for inter-core synchronization, thus enhancing speed and energy efficiency. This approach leverages the pre-determined dependencies of neuromorphic cores established during compilation. Each core is equipped with a scheduler that monitors the status of its dependencies, allowing it to safely advance to the next timestep without waiting for other cores. This eliminates the necessity for global synchronization and minimizes core waiting time despite inherent workload imbalances. Comprehensive evaluations using five different SNN workloads show that our architecture achieves a 1.86x speedup and a 1.55x increase in energy efficiency compared to state-of-the-art synchronization architectures.

Quantum learning tasks often leverage randomly sampled quantum circuits to characterize unknown systems. An efficient approach known as "circuit reusing," where each circuit is executed multiple times, reduces the cost compared to implementing new circuits. This work investigates the optimal reusing parameter that minimizes the variance of measurement outcomes for a given experimental cost. We establish a theoretical framework connecting the variance of experimental estimators with the reusing parameter R. An optimal R is derived when the implemented circuits and their noise characteristics are known. Additionally, we introduce a near-optimal reusing strategy that is applicable even without prior knowledge of circuits or noise, achieving variances close to the theoretical minimum. To validate our framework, we apply it to randomized benchmarking and analyze the optimal R for various typical noise channels. We further conduct experiments on a superconducting platform, revealing a non-linear relationship between R and the cost, contradicting previous assumptions in the literature. Our theoretical framework successfully incorporates this non-linearity and accurately predicts the experimentally observed optimal R. These findings underscore the broad applicability of our approach to experimental realizations of quantum learning protocols., Comment: 19 pages, 12 figures. Comments are welcomed!

Optical tactile sensors provide robots with rich force information for robot grasping in unstructured environments. The fast and accurate calibration of three-dimensional contact forces holds significance for new sensors and existing tactile sensors which may have incurred damage or aging. However, the conventional neural-network-based force calibration method necessitates a large volume of force-labeled tactile images to minimize force prediction errors, with the need for accurate Force/Torque measurement tools as well as a time-consuming data collection process. To address this challenge, we propose a novel deep domain-adaptation force calibration method, designed to transfer the force prediction ability from a calibrated optical tactile sensor to uncalibrated ones with various combinations of domain gaps, including marker presence, illumination condition, and elastomer modulus. Experimental results show the effectiveness of the proposed unsupervised force calibration method, with lowest force prediction errors of 0.102N (3.4\% in full force range) for normal force, and 0.095N (6.3\%) and 0.062N (4.1\%) for shear forces along the x-axis and y-axis, respectively. This study presents a promising, general force calibration methodology for optical tactile sensors., Comment: 2024 IEEE/RSJ International Conference on Intelligent Robots and Systems

Retrieval-Augmented Generation (RAG) is applied to solve hallucination problems and real-time constraints of large language models, but it also induces vulnerabilities against retrieval corruption attacks. Existing research mainly explores the unreliability of RAG in white-box and closed-domain QA tasks. In this paper, we aim to reveal the vulnerabilities of Retrieval-Enhanced Generative (RAG) models when faced with black-box attacks for opinion manipulation. We explore the impact of such attacks on user cognition and decision-making, providing new insight to enhance the reliability and security of RAG models. We manipulate the ranking results of the retrieval model in RAG with instruction and use these results as data to train a surrogate model. By employing adversarial retrieval attack methods to the surrogate model, black-box transfer attacks on RAG are further realized. Experiments conducted on opinion datasets across multiple topics show that the proposed attack strategy can significantly alter the opinion polarity of the content generated by RAG. This demonstrates the model's vulnerability and, more importantly, reveals the potential negative impact on user cognition and decision-making, making it easier to mislead users into accepting incorrect or biased information., Comment: 10 pages, 3 figures, under review

Inverse rendering methods have achieved remarkable performance in reconstructing high-fidelity 3D objects with disentangled geometries, materials, and environmental light. However, they still face huge challenges in reflective surface reconstruction. Although recent methods model the light trace to learn specularity, the ignorance of indirect illumination makes it hard to handle inter-reflections among multiple smooth objects. In this work, we propose Ref-MC2 that introduces the multi-time Monte Carlo sampling which comprehensively computes the environmental illumination and meanwhile considers the reflective light from object surfaces. To address the computation challenge as the times of Monte Carlo sampling grow, we propose a specularity-adaptive sampling strategy, significantly reducing the computational complexity. Besides the computational resource, higher geometry accuracy is also required because geometric errors accumulate multiple times. Therefore, we further introduce a reflection-aware surface model to initialize the geometry and refine it during inverse rendering. We construct a challenging dataset containing scenes with multiple objects and inter-reflections. Experiments show that our method outperforms other inverse rendering methods on various object groups. We also show downstream applications, e.g., relighting and material editing, to illustrate the disentanglement ability of our method., Comment: 10 pages,6 figures, Accepted by NeurIPS 2024

Modern automatic speech recognition (ASR) model is required to accurately transcribe diverse speech signals (from different domains, languages, accents, etc) given the specific contextual information in various application scenarios. Classic end-to-end models fused with extra language models perform well, but mainly in data matching scenarios and are gradually approaching a bottleneck. In this work, we introduce Seed-ASR, a large language model (LLM) based speech recognition model. Seed-ASR is developed based on the framework of audio conditioned LLM (AcLLM), leveraging the capabilities of LLMs by inputting continuous speech representations together with contextual information into the LLM. Through stage-wise large-scale training and the elicitation of context-aware capabilities in LLM, Seed-ASR demonstrates significant improvement over end-to-end models on comprehensive evaluation sets, including multiple domains, accents/dialects and languages. Additionally, Seed-ASR can be further deployed to support specific needs in various scenarios without requiring extra language models. Compared to recently released large ASR models, Seed-ASR achieves 10%-40% reduction in word (or character, for Chinese) error rates on Chinese and English public test sets, further demonstrating its powerful performance.

Generative models have shown significant achievements in audio generation tasks. However, existing models struggle with complex and detailed prompts, leading to potential performance degradation. We hypothesize that this problem stems from the simplicity and scarcity of the training data. This work aims to create a large-scale audio dataset with rich captions for improving audio generation models. We first develop an automated pipeline to generate detailed captions by transforming predicted visual captions, audio captions, and tagging labels into comprehensive descriptions using a Large Language Model (LLM). The resulting dataset, Sound-VECaps, comprises 1.66M high-quality audio-caption pairs with enriched details including audio event orders, occurred places and environment information. We then demonstrate that training the text-to-audio generation models with Sound-VECaps significantly improves the performance on complex prompts. Furthermore, we conduct ablation studies of the models on several downstream audio-language tasks, showing the potential of Sound-VECaps in advancing audio-text representation learning. Our dataset and models are available online., Comment: 5 pages with 1 appendix

Patients often delay or reject medical tests due to information avoidance, which hinders timely reception of necessary treatments. This paper studies the optimal information policy to persuade an information-avoidant patient to undergo the test and make the best choice that maximizes his health. The patient sequentially decides whether to take the test and the optimal treatment plan. The information provided is about the background knowledge of the disease, and disclosure can take place both before and after the test decision. The optimal information policy depends on whether the patient is willing to be tested when he is completely pessimistic. If so, the optimal policy features warning-in-advance: the disclosure only takes place before the test, and the bad news guarantees the patient to be tested and be treated even without further information. If not, the optimal policy constructs an information greenhouse: an information structure that provides high anticipatory utility is committed when the patient is tested and the test result is bad. Extensions to ex ante participation constraint and general information preference are also considered.

In the commercial sphere, such as operations and maintenance, advertising, and marketing recommendations, intelligent decision-making utilizing data mining and neural network technologies is crucial, especially in resource allocation to optimize ROI. This study delves into the Cost-aware Binary Treatment Assignment Problem (C-BTAP) across different industries, with a focus on the state-of-the-art Direct ROI Prediction (DRP) method. However, the DRP model confronts issues like covariate shift and insufficient training data, hindering its real-world effectiveness. Addressing these challenges is essential for ensuring dependable and robust predictions in varied operational contexts. This paper presents a robust Direct ROI Prediction (rDRP) method, designed to address challenges in real-world deployment of neural network-based uplift models, particularly under conditions of covariate shift and insufficient training data. The rDRP method, enhancing the standard DRP model, does not alter the model's structure or require retraining. It utilizes conformal prediction and Monte Carlo dropout for interval estimation, adapting to model uncertainty and data distribution shifts. A heuristic calibration method, inspired by a Kaggle competition, combines point and interval estimates. The effectiveness of these approaches is validated through offline tests and online A/B tests in various settings, demonstrating significant improvements in target rewards compared to the state-of-the-art method., Comment: Accepted by ICDE 2024; Link: https://icde2024.github.io/papers.html

Neural codec language model (LM) has demonstrated strong capability in zero-shot text-to-speech (TTS) synthesis. However, the codec LM often suffers from limitations in inference speed and stability, due to its auto-regressive nature and implicit alignment between text and audio. In this work, to handle these challenges, we introduce a new variant of neural codec LM, namely TacoLM. Specifically, TacoLM introduces a gated attention mechanism to improve the training and inference efficiency and reduce the model size. Meanwhile, an additional gated cross-attention layer is included for each decoder layer, which improves the efficiency and content accuracy of the synthesized speech. In the evaluation of the Librispeech corpus, the proposed TacoLM achieves a better word error rate, speaker similarity, and mean opinion score, with 90% fewer parameters and 5.2 times speed up, compared with VALL-E. Demo and code is available at https://ereboas.github.io/TacoLM/., Comment: INTERSPEECH 2024

Knowledge Base Question Answering (KBQA) has been a long-standing field to answer questions based on knowledge bases. Recently, the evolving dynamics of knowledge have attracted a growing interest in Temporal Knowledge Graph Question Answering (TKGQA), an emerging task to answer temporal questions. However, this field grapples with ambiguities in defining temporal questions and lacks a systematic categorization of existing methods for TKGQA. In response, this paper provides a thorough survey from two perspectives: the taxonomy of temporal questions and the methodological categorization for TKGQA. Specifically, we first establish a detailed taxonomy of temporal questions engaged in prior studies. Subsequently, we provide a comprehensive review of TKGQA techniques of two categories: semantic parsing-based and TKG embedding-based. Building on this review, the paper outlines potential research directions aimed at advancing the field of TKGQA. This work aims to serve as a comprehensive reference for TKGQA and to stimulate further research., Comment: 8 pages, 3 figures

We measure the high-mass stellar initial mass function (IMF) from resolved stars in M33 young stellar clusters. Leveraging \textit{Hubble Space Telescope's} high resolving power, we fully model the IMF probabilistically. We first model the optical CMD of each cluster to constrain its power-law slope $\Gamma$, marginalized over other cluster parameters in the fit (e.g., cluster age, mass, and radius). We then probabilistically model the distribution of MF slopes for a highly strict cluster sample of 9 clusters more massive than log(Mass/M$_{\odot}$)=3.6; above this mass, all clusters have well-populated main sequences of massive stars and should have accurate recovery of their MF slopes, based on extensive tests with artificial clusters. We find the ensemble IMF is best described by a mean high-mass slope of $\overline{\Gamma} = 1.49\pm0.18$, with an intrinsic scatter of $\sigma^{2}_{\Gamma} = 0.02^{+0.16}_{0.00}$, consistent with a universal IMF. We find no dependence of the IMF on environmental impacts such as the local star formation rate or galactocentric radius within M33, which serves as a proxy for metallicity. This $\overline{\Gamma}$ measurement is consistent with similar measurements in M31, despite M33 having a much higher star formation rate intensity. While this measurement is formally consistent with the canonical Kroupa ($\Gamma = 1.30$) IMF, as well as the Salpeter ($\Gamma = 1.35)$) value, it is the second Local Group cluster sample to show evidence for a somewhat steeper high-mass IMF slope. We explore the impacts a steeper IMF slope has on a number of astronomical sub-fields., Comment: Accepted for publication in ApJ. 9 Figures, 1 Table

Despite significant advancements in text generation and reasoning, Large Language Models (LLMs) still face challenges in accurately performing complex arithmetic operations. Language model systems often enable LLMs to generate code for arithmetic operations to achieve accurate calculations. However, this approach compromises speed and security, and fine-tuning risks the language model losing prior capabilities. We propose a framework that enables exact arithmetic in a single autoregressive step, providing faster, more secure, and more interpretable LLM systems with arithmetic capabilities. We use the hidden states of a LLM to control a symbolic architecture that performs arithmetic. Our implementation using Llama 3 with OccamNet as a symbolic model (OccamLlama) achieves 100\% accuracy on single arithmetic operations ($+,-,\times,\div,\sin{},\cos{},\log{},\exp{},\sqrt{}$), outperforming GPT 4o with and without a code interpreter. Furthermore, OccamLlama outperforms GPT 4o with and without a code interpreter on average across a range of mathematical problem solving benchmarks, demonstrating that OccamLLMs can excel in arithmetic tasks, even surpassing much larger models. We will make our code public shortly.

We introduce Seed-TTS, a family of large-scale autoregressive text-to-speech (TTS) models capable of generating speech that is virtually indistinguishable from human speech. Seed-TTS serves as a foundation model for speech generation and excels in speech in-context learning, achieving performance in speaker similarity and naturalness that matches ground truth human speech in both objective and subjective evaluations. With fine-tuning, we achieve even higher subjective scores across these metrics. Seed-TTS offers superior controllability over various speech attributes such as emotion and is capable of generating highly expressive and diverse speech for speakers in the wild. Furthermore, we propose a self-distillation method for speech factorization, as well as a reinforcement learning approach to enhance model robustness, speaker similarity, and controllability. We additionally present a non-autoregressive (NAR) variant of the Seed-TTS model, named $\text{Seed-TTS}_\text{DiT}$, which utilizes a fully diffusion-based architecture. Unlike previous NAR-based TTS systems, $\text{Seed-TTS}_\text{DiT}$ does not depend on pre-estimated phoneme durations and performs speech generation through end-to-end processing. We demonstrate that this variant achieves comparable performance to the language model-based variant and showcase its effectiveness in speech editing. We encourage readers to listen to demos at \url{https://bytedancespeech.github.io/seedtts_tech_report}.

We propose Quantum-informed Tensor Adaptation (QuanTA), a novel, easy-to-implement, fine-tuning method with no inference overhead for large-scale pre-trained language models. By leveraging quantum-inspired methods derived from quantum circuit structures, QuanTA enables efficient high-rank fine-tuning, surpassing the limitations of Low-Rank Adaptation (LoRA)--low-rank approximation may fail for complicated downstream tasks. Our approach is theoretically supported by the universality theorem and the rank representation theorem to achieve efficient high-rank adaptations. Experiments demonstrate that QuanTA significantly enhances commonsense reasoning, arithmetic reasoning, and scalability compared to traditional methods. Furthermore, QuanTA shows superior performance with fewer trainable parameters compared to other approaches and can be designed to integrate with existing fine-tuning algorithms for further improvement, providing a scalable and efficient solution for fine-tuning large language models and advancing state-of-the-art in natural language processing.

Learning high-quality multi-modal entity representations is an important goal of multi-modal knowledge graph (MMKG) representation learning, which can enhance reasoning tasks within the MMKGs, such as MMKG completion (MMKGC). The main challenge is to collaboratively model the structural information concealed in massive triples and the multi-modal features of the entities. Existing methods focus on crafting elegant entity-wise multi-modal fusion strategies, yet they overlook the utilization of multi-perspective features concealed within the modalities under diverse relational contexts. To address this issue, we introduce a novel framework with Mixture of Modality Knowledge experts (MoMoK for short) to learn adaptive multi-modal entity representations for better MMKGC. We design relation-guided modality knowledge experts to acquire relation-aware modality embeddings and integrate the predictions from multi-modalities to achieve joint decisions. Additionally, we disentangle the experts by minimizing their mutual information. Experiments on four public MMKG benchmarks demonstrate the outstanding performance of MoMoK under complex scenarios., Comment: Work in progress. Code and data will be released at https://github.com/zjukg/MoMoK