arXiv subjects

Weiwei Fu

Publications and source records attributed to Weiwei Fu.

9 recordsLinked to original sources

arXiv2026

MyoMechanix: Biomechanically-Grounded Compositional Skilled Activity Understanding and Coaching

Existing action quality assessment (AQA) datasets and methods rely primarily on visual inputs such as RGB and pose, overlooking physiological dynamics such as muscle mechanics and often modeling actions as monolithic patterns. These limitations hinder fine-grained, biomechanically grounded feedback. We introduce MyoMechanix, a multimodal ecosystem for weight-loaded actions that aligns motion with muscle activity. Expert-annotated, it contains 7,500+ samples of 20 actions from 38 subjects, with synchronized multiview RGB video, 3D pose, sEMG, and additional physiological signals, forming the largest multimodal AQA benchmark to date. We further construct the Fitness Knowledge Graph (FKG), which organizes expert annotations into structured relationships among actions, phases, key steps, errors, and corrective feedback, enabling compositional scoring and interpretable assessment. Building on these representations, we develop CUBIST (Compositional Ontological Reasoning Engine), which performs decomposition-analysis-recomposition for fine-grained error attribution and feedback generation. We also establish MyoMechanix-AQA, MyoMechanix-VideoQA, and a novel MyoMechanix-Video2EMG task. Experiments show that multimodal sensing and structured representations improve performance, interpretability, and error attribution, with CUBIST achieving state-of-the-art results; VideoQA enhances language-grounded action understanding; and Video2EMG suggests video-based alternatives to costly EMG sensing. MyoMechanix advances skilled activity understanding toward biomechanically grounded, multimodal, and compositional reasoning for Physical AI applications in fitness, rehabilitation, healthcare, and machine learning. Project page: https://haoyin116.github.io/MyoMechanix/

cs.CV↗

arXiv2025

FLEX: A Largescale Multimodal, Multiview Dataset for Learning Structured Representations for Fitness Action Quality Assessment

Action Quality Assessment (AQA) -- the task of quantifying how well an action is performed -- has great potential for detecting errors in gym weight training, where accurate feedback is critical to prevent injuries and maximize gains. Existing AQA datasets, however, are limited to single-view competitive sports and RGB video, lacking multimodal signals and professional assessment of fitness actions. We introduce FLEX, the first large-scale, multimodal, multiview dataset for fitness AQA that incorporates surface electromyography (sEMG). FLEX contains over 7,500 multiview recordings of 20 weight-loaded exercises performed by 38 subjects of diverse skill levels, with synchronized RGB video, 3D pose, sEMG, and physiological signals. Expert annotations are organized into a Fitness Knowledge Graph (FKG) linking actions, key steps, error types, and feedback, supporting a compositional scoring function for interpretable quality assessment. FLEX enables multimodal fusion, cross-modal prediction -- including the novel Video$\rightarrow$EMG task -- and biomechanically oriented representation learning. Building on the FKG, we further introduce FLEX-VideoQA, a structured question-answering benchmark with hierarchical queries that drive cross-modal reasoning in vision-language models. Baseline experiments demonstrate that multimodal inputs, multiview video, and fine-grained annotations significantly enhance AQA performance. FLEX thus advances AQA toward richer multimodal settings and provides a foundation for AI-powered fitness assessment and coaching. Dataset and code are available at \href{https://github.com/HaoYin116/FLEX}{https://github.com/HaoYin116/FLEX}. Link to Project \href{https://haoyin116.github.io/FLEX_Dataset}{page}.

cs.CV↗

arXiv2025

TPC: Cross-Temporal Prediction Connection for Vision-Language Model Hallucination Reduction

Vision-language models (VLMs) have achieved remarkable advancements, capitalizing on the impressive capabilities of large language models (LLMs) across diverse tasks. Despite this, a critical challenge known as hallucination occurs when models overconfidently describe objects or attributes absent from the image, a problem exacerbated by the tendency of VLMs to rely on linguistic priors. This limitation reduces model reliability in high-stakes applications. In this work, we have observed the characteristic of logits' continuity consistency enhancement and introduced a straightforward and efficient method, Cross-Temporal Prediction Connection (TPC), designed to enhance the semantic consistency of logits by connecting them temporally across timesteps. TPC amplifies information flow and improves coherence, effectively reducing hallucination. Extensive experiments show that TPC surpasses existing representatives, delivering superior performance in both accuracy and efficiency while maintaining robustness in open-ended text generation tasks.

cs.CV↗

arXiv2025

A Decade of Action Quality Assessment: Largest Systematic Survey of Trends, Challenges, and Future Directions

Action Quality Assessment (AQA) -- the ability to quantify the quality of human motion, actions, or skill levels and provide feedback -- has far-reaching implications in areas such as low-cost physiotherapy, sports training, and workforce development. As such, it has become a critical field in computer vision & video understanding over the past decade. Significant progress has been made in AQA methodologies, datasets, & applications, yet a pressing need remains for a comprehensive synthesis of this rapidly evolving field. In this paper, we present a thorough survey of the AQA landscape, systematically reviewing over 200 research papers using the preferred reporting items for systematic reviews & meta-analyses (PRISMA) framework. We begin by covering foundational concepts & definitions, then move to general frameworks & performance metrics, & finally discuss the latest advances in methodologies & datasets. This survey provides a detailed analysis of research trends, performance comparisons, challenges, & future directions. Through this work, we aim to offer a valuable resource for both newcomers & experienced researchers, promoting further exploration & progress in AQA. Data are available at https://haoyin116.github.io/Survey_of_AQA/

cs.AI↗

arXiv2025

Mitigating Hallucinations in Large Vision-Language Models with Internal Fact-based Contrastive Decoding

Large Visual Language Models (LVLMs) integrate visual and linguistic modalities, exhibiting exceptional performance across various multimodal tasks. Nevertheless, LVLMs remain vulnerable to the issue of object hallucinations. Previous efforts to mitigate this issue focus on supervised fine-tuning (SFT) or incorporating external knowledge, both of which entail significant costs related to training and the acquisition of external data. To address these challenges, we propose a novel model-agnostic approach termed Internal Fact-based Contrastive Decoding (IFCD), designed to mitigate and suppress hallucinations during the inference process of LVLMs by exploiting the LVLMs' own hallucinations. IFCD is grounded in experimental observations that alterations to the LVLMs' internal representations tend to amplify hallucinations caused by language bias. By contrasting disturbed distribution, IFCD calibrates the LVLMs' output and effectively removes the hallucinatory logits from the final predictions. Experimental results validate that IFCD significantly alleviates both object-level and attribute-level hallucinations while achieving an average 9% accuracy improvement on POPE and 8% accuracy improvement on MME object hallucinations subset compared with direct decoding, respectively.

cs.CV↗

arXiv2024

ICSFuzz: Collision Detector Bug Discovery in Autonomous Driving Simulators

With the increasing adoption of autonomous vehicles, ensuring the reliability of autonomous driving systems (ADSs) deployed on autonomous vehicles has become a significant concern. Driving simulators have emerged as crucial platforms for testing autonomous driving systems, offering realistic, dynamic, and configurable environments. However, existing simulation-based ADS testers have largely overlooked the reliability of the simulators, potentially leading to overlooked violation scenarios and subsequent safety security risks during real-world deployment. In our investigations, we identified that collision detectors in simulators could fail to detect and report collisions in certain collision scenarios, referred to as ignored collision scenarios. This paper aims to systematically discover ignored collision scenarios to improve the reliability of autonomous driving simulators. To this end, we present ICSFuzz, a black-box fuzzing approach to discover ignored collision scenarios efficiently. Drawing upon the fact that the ignored collision scenarios are a sub-type of collision scenarios, our approach starts with the determined collision scenarios. Following the guidance provided by empirically studied factors contributing to collisions, we selectively mutate arbitrary collision scenarios in a step-wise manner toward the ignored collision scenarios and effectively discover them. We compare ICSFuzz with DriveFuzz, a state-of-the-art simulation-based ADS testing method, by replacing its oracle with our ignored-collision-aware oracle. The evaluation demonstrates that ICSFuzz outperforms DriveFuzz by finding 10-20x more ignored collision scenarios with a 20-70x speedup. All the discovered ignored collisions have been confirmed by developers with one CVE ID assigned.

cs.CR↗

arXiv2024

TeleChat Technical Report

In this technical report, we present TeleChat, a collection of large language models (LLMs) with parameters of 3 billion, 7 billion and 12 billion. It includes pretrained language models as well as fine-tuned chat models that is aligned with human preferences. TeleChat is initially pretrained on an extensive corpus containing a diverse collection of texts from both English and Chinese languages, including trillions of tokens. Subsequently, the model undergoes fine-tuning to align with human preferences, following a detailed methodology that we describe. We evaluate the performance of TeleChat on various tasks, including language understanding, mathematics, reasoning, code generation, and knowledge-based question answering. Our findings indicate that TeleChat achieves comparable performance to other open-source models of similar size across a wide range of public benchmarks. To support future research and applications utilizing LLMs, we release the fine-tuned model checkpoints of TeleChat's 7B and 12B variant, along with code and a portion of our pretraining data, to the public community.

cs.CL↗

arXiv2022

Phase-probability shaping for speckle-free holographic lithography

Optical holography has undergone rapid development since its invention in 1948, but the accompanying speckles with randomly distributed intensity are still untamed now due to the fundamental difficulty of eliminating intrinsic fluctuations from irregular complex-field superposition. Despite spatial, temporal and spectral averages for speckle reduction, it is extremely challenging to reconstruct high-homogeneity, edge-sharp and shape-unlimited images via holography. Here we predict that holographic speckles can be removed by narrowing the probability density distribution of encoded phase to homogenize optical superposition. Guided by this physical insight, a machine-learning-assisted probability-shaping (MAPS) method is developed to prohibit the fluctuations of intensity in a computer-generated hologram (CGH), which empowers the experimental reconstruction of irregular images with ultralow speckle contrast (C=0.08) and record-high edge sharpness (~1000 mm-1). It breaks the ultimate barrier of demonstrating high-end CGH lithography, thus enabling us to successfully pattern arbitrary-shape and edge-sharp structures such as vortex gratings and two-dimensional random barcodes.

physics.optics↗

arXiv2022

Evaluation of CMIP models with IOMB: Rates of contemporary ocean carbon uptake linked with vertical temperature gradients and transport to the ocean interior

The International Ocean Model Benchmarking (IOMB) software package is a new community resource used here to evaluate surface and upper ocean variables from CMIP5 and CMIP6 Earth System Models (ESMs) Our analysis reveals general improvement in the multi-model mean of CMIP6 compared to CMIP5 for most of the variables we examined including surface nutrients, temperature, and salinity. We find that both CMIP5 and CMIP6 ocean models underestimate anthropogenic carbon dioxide uptake after the 1970s. For the period of 1994 to 2007, the multi-model mean from CMIP6 yields a mean cumulative carbon uptake of 27.2 +-2.2 Pg C, which is about 15% lower than the 32.0+-5.7 Pg C estimate derived from two sets of observations. Negative biases in the change in anthropogenic carbon inventory exist in the northern North Atlantic and at mid-latitudes in the southern hemisphere (30-60{\deg}S). For the few models that provided simulations of chlorofluorocarbon (CFC), we demonstrate that regions with negative anthropogenic DIC biases coincide with regions that have a negative bias in CFC concentrations. This relationship suggests that underestimates of anthropogenic carbon storage in some models originates, in part, from weak transport between the surface and interior ocean. To examine the robustness of this attribution across the full suite of CMIP5 and CMIP6 models, we examined the vertical temperature gradient between 200 and 1000m as a metric for stratification and exchange between the surface and deeper waters. On a global scale across different models and different MIPs we find a linear relationship between the bias of vertical temperature gradients and the bias in anthropogenic carbon uptake, consistent with the hypothesis that model biases in the ocean carbon sink are related to biases in surface-to-interior transport.

physics.ao-ph↗