arXiv subjects

Yu Zhang

Publications and source records attributed to Yu Zhang.

At least 631 records · Page 35Linked to original sources

arXiv2025

EnvPoser: Environment-aware Realistic Human Motion Estimation from Sparse Observations with Uncertainty Modeling

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

cs.CV↗

arXiv2025

EMOVA: Empowering Language Models to See, Hear and Speak with Vivid Emotions

GPT-4o, an omni-modal model that enables vocal conversations with diverse emotions and tones, marks a milestone for omni-modal foundation models. However, empowering Large Language Models to perceive and generate images, texts, and speeches end-to-end with publicly available data remains challenging for the open-source community. Existing vision-language models rely on external tools for speech processing, while speech-language models still suffer from limited or totally without vision-understanding capabilities. To address this gap, we propose the EMOVA (EMotionally Omni-present Voice Assistant), to enable Large Language Models with end-to-end speech abilities while maintaining the leading vision-language performance. With a semantic-acoustic disentangled speech tokenizer, we surprisingly notice that omni-modal alignment can further enhance vision-language and speech abilities compared with the bi-modal aligned counterparts. Moreover, a lightweight style module is introduced for the flexible speech style controls including emotions and pitches. For the first time, EMOVA achieves state-of-the-art performance on both the vision-language and speech benchmarks, and meanwhile, supporting omni-modal spoken dialogue with vivid emotions.

cs.CV↗

arXiv2025

Formation and evolution of new primordial open cluster groups: Feedback-driven star formation

The formation mechanisms of open cluster (OCs) groups remain unclear due to limited sample sizes and data precision. Recent advancements in Gaia astrometric data provide an unprecedented opportunity to study OC groups in greater detail. This study aims to extend the sample of OC groups and investigate their formation and evolution mechanisms, with a focus on the role of stellar feedback in triggering star formation. We identify four new OC groups based on Gaia data, whose member OCs are spatially proximate and kinematically coherent. Their age spreads are consistent with the timescale of continuous star formation, suggesting that their member OCs formed sequentially from the same molecular cloud. N-body simulation results further reveal that these groups will gradually disperse, evolving into independent OCs. By analyzing the correlation between OC ages and their separation from potential SN explosion sites, we predict SN explosion regions around the birthplaces of OC groups. The strong correlation between OC ages and predicted SN explosion sites supports a supernova-triggered star formation scenario. Additionally, we trace pulsar (PSR) orbits to examine their association with these regions. We detected three PSRs near Group 1 and 26 PSRs near Group 2, whose birthplaces align with the predicted SN explosions regions. The presence of PSRs associated with OC groups provides additional observational evidence for SN explosions in this region, further supporting a supernova-triggered star formation scenario for G1 and G2. We propose that multiple SN explosions in a short period triggered the formation of Group 1 and Group 2, reinforcing the hierarchical star formation model. These results highlight the multi-scale interactions driving star and OC formation and provide new insights into the role of stellar feedback in shaping OC groups.

astro-ph.GA↗

arXiv2025

Federated Mixture-of-Expert for Non-Overlapped Cross-Domain Sequential Recommendation

In the real world, users always have multiple interests while surfing different services to enrich their daily lives, e.g., watching hot short videos/live streamings. To describe user interests precisely for a better user experience, the recent literature proposes cross-domain techniques by transferring the other related services (a.k.a. domain) knowledge to enhance the accuracy of target service prediction. In practice, naive cross-domain techniques typically require there exist some overlapped users, and sharing overall information across domains, including user historical logs, user/item embeddings, and model parameter checkpoints. Nevertheless, other domain's user-side historical logs and embeddings are not always available in real-world RecSys designing, since users may be totally non-overlapped across domains, or the privacy-preserving policy limits the personalized information sharing across domains. Thereby, a challenging but valuable problem is raised: How to empower target domain prediction accuracy by utilizing the other domain model parameters checkpoints only? To answer the question, we propose the FMoE-CDSR, which explores the non-overlapped cross-domain sequential recommendation scenario from the federated learning perspective.

cs.IR↗

arXiv2025

Addressing Information Loss and Interaction Collapse: A Dual Enhanced Attention Framework for Feature Interaction

The Transformer has proven to be a significant approach in feature interaction for CTR prediction, achieving considerable success in previous works. However, it also presents potential challenges in handling feature interactions. Firstly, Transformers may encounter information loss when capturing feature interactions. By relying on inner products to represent pairwise relationships, they compress raw interaction information, which can result in a degradation of fidelity. Secondly, due to the long-tail features distribution, feature fields with low information-abundance embeddings constrain the information abundance of other fields, leading to collapsed embedding matrices. To tackle these issues, we propose a Dual Attention Framework for Enhanced Feature Interaction, known as Dual Enhanced Attention. This framework integrates two attention mechanisms: the Combo-ID attention mechanism and the collapse-avoiding attention mechanism. The Combo-ID attention mechanism directly retains feature interaction pairs to mitigate information loss, while the collapse-avoiding attention mechanism adaptively filters out low information-abundance interaction pairs to prevent interaction collapse. Extensive experiments conducted on industrial datasets have shown the effectiveness of Dual Enhanced Attention.

cs.IR↗

arXiv2025

D2O: Dynamic Discriminative Operations for Efficient Long-Context Inference of Large Language Models

Generative inference in Large Language Models (LLMs) is impeded by the growing memory demands of Key-Value (KV) cache, especially for longer sequences. Traditional KV cache eviction strategies, which discard less critical KV pairs based on attention scores, often degrade generation quality, leading to issues such as context loss or hallucinations. In this work, we introduce Dynamic Discriminative Operations (D2O), a KV cache compression method that optimizes KV cache size dynamically and discriminatively at two levels without fine-tuning, while preserving essential context. At layer level, D2O leverages the varying densities of attention weights between shallow and deep layers to dynamically determine which layers should avoid excessive eviction via a novel dynamic allocation strategy to minimize information loss. At token level, D2O incorporates a compensation mechanism that maintains a similarity threshold to re-discriminate the importance of currently discarded tokens, determining whether they should be recalled and merged with similar tokens. We conduct experiments on various benchmarks and LLM architectures. Our results show that D2O not only achieves significant memory savings and enhances inference throughput by more than 3$\times$ but also maintains high-quality long-text generation.

cs.CL↗

arXiv2025

Nonequilibrium mean-field approach for quantum transport with off-diagonal disorder

For the nanoscale structures, disorder scattering plays a vital role in the carriers' transport, including electrons and high-frequency phonons. The capability for effectively treating the disorders, including both diagonal and off-diagonal disorders, is indispensable for quantum transport simulation of realistic device materials. In this work, we report a self-consistent nonequilibrium mean-field quantum transport approach, by combining the auxiliary coherent potential approximation (ACPA) and non-equilibrium Green's function method, for calculating the phonon transport through disordered material structures with the force-constant disorders (including the Anderson-type disorder). The nonequilibrium vertex correction (NVC) is derived in an extended local degree of freedom to account for both the multiple disorder scattering by force-constant disorder and the nonequilibrium quantum statistics. We have tested ACPA-NVC method with the fluctuation-dissipation theorem at the equilibrium and obtained very good agreement with supercell calculations for the phonon transmission. To demonstrate the applicability, we apply ACPA-NVC to calculate the thermal conductance for the disordered Ni/Pt interface, and important effects of force-constant disorder are revealed. ACPA-NVC method provides an effective quantum transport approach for simulating disordered nanoscale devices, and the generalization to simulate disordered nanoelectronic device is straightforward.

cond-mat.mes-hall↗

arXiv2025

Multimodal Human-AI Synergy for Medical Imaging Quality Control: A Hybrid Intelligence Framework with Adaptive Dataset Curation and Closed-Loop Evaluation

Medical imaging quality control (QC) is essential for accurate diagnosis, yet traditional QC methods remain labor-intensive and subjective. To address this challenge, in this study, we establish a standardized dataset and evaluation framework for medical imaging QC, systematically assessing large language models (LLMs) in image quality assessment and report standardization. Specifically, we first constructed and anonymized a dataset of 161 chest X-ray (CXR) radiographs and 219 CT reports for evaluation. Then, multiple LLMs, including Gemini 2.0-Flash, GPT-4o, and DeepSeek-R1, were evaluated based on recall, precision, and F1 score to detect technical errors and inconsistencies. Experimental results show that Gemini 2.0-Flash achieved a Macro F1 score of 90 in CXR tasks, demonstrating strong generalization but limited fine-grained performance. DeepSeek-R1 excelled in CT report auditing with a 62.23\% recall rate, outperforming other models. However, its distilled variants performed poorly, while InternLM2.5-7B-chat exhibited the highest additional discovery rate, indicating broader but less precise error detection. These findings highlight the potential of LLMs in medical imaging QC, with DeepSeek-R1 and Gemini 2.0-Flash demonstrating superior performance.

cs.CL↗

arXiv2025

Sphere Precoding for Robust Near-Field Communications

Near-field communication with large antenna arrays promises significant beamforming and multiplexing gains. These communication links, however, are very sensitive to user mobility as any small change in the user position may suddenly drop the signal power. This leads to critical challenges for the robustness of these near-field communication systems. In this paper, we propose \textit{sphere precoding}, which is a robust precoding design to address user mobility in near-field communications. To gain insights into the spatial correlation of near-field channels, we extend the one-ring channel model to what we call one-sphere channel model and derive the channel covariance considering user mobility. Based on the one-sphere channel model, a robust precoding design problem is defined to optimize the minimum signal-to-interference-plus-noise ratio (SINR) satisfaction probability among mobile users. By utilizing the eigen structure of channel covariance, we further design a relaxed convex problem to approximate the solution of the original non-convex problem. The low-complexity solution effectively shapes a sphere that maintains the signal power for the target user and also nulls its interference within spheres around the other users. Simulation results highlight the efficacy of the proposed solution in achieving robust precoding yet high achievable rates in near-field communication systems.

eess.SP↗

arXiv2025

Signal Processing Meets SGD: From Momentum to Filter

In deep learning, stochastic gradient descent (SGD) and its momentum-based variants are widely used for optimization. However, the internal dynamics of these methods remain underexplored. In this paper, we analyze gradient behavior through a signal processing lens, isolating key factors that influence gradient updates and revealing a critical limitation: momentum techniques lack the flexibility to adequately balance bias and variance components in gradients, resulting in gradient estimation inaccuracies. To address this issue, we introduce a novel method SGDF (SGD with Filter) based on Wiener Filter principles, which derives an optimal time-varying gain to refine gradient updates by minimizing the mean square error in gradient estimation. This method yields an optimal first-order gradient estimate, effectively balancing noise reduction and signal preservation. Furthermore, our approach could extend to adaptive optimizers, enhancing their generalization potential. Empirical results show that SGDF achieves superior convergence and generalization compared to traditional momentum methods, and performs competitively with state-of-the-art optimizers.

cs.LG↗

arXiv2025

Protein Large Language Models: A Comprehensive Survey

Protein-specific large language models (Protein LLMs) are revolutionizing protein science by enabling more efficient protein structure prediction, function annotation, and design. While existing surveys focus on specific aspects or applications, this work provides the first comprehensive overview of Protein LLMs, covering their architectures, training datasets, evaluation metrics, and diverse applications. Through a systematic analysis of over 100 articles, we propose a structured taxonomy of state-of-the-art Protein LLMs, analyze how they leverage large-scale protein sequence data for improved accuracy, and explore their potential in advancing protein engineering and biomedical research. Additionally, we discuss key challenges and future directions, positioning Protein LLMs as essential tools for scientific discovery in protein science. Resources are maintained at https://github.com/Yijia-Xiao/Protein-LLM-Survey.

q-bio.BM↗

arXiv2025

BHViT: Binarized Hybrid Vision Transformer

Model binarization has made significant progress in enabling real-time and energy-efficient computation for convolutional neural networks (CNN), offering a potential solution to the deployment challenges faced by Vision Transformers (ViTs) on edge devices. However, due to the structural differences between CNN and Transformer architectures, simply applying binary CNN strategies to the ViT models will lead to a significant performance drop. To tackle this challenge, we propose BHViT, a binarization-friendly hybrid ViT architecture and its full binarization model with the guidance of three important observations. Initially, BHViT utilizes the local information interaction and hierarchical feature aggregation technique from coarse to fine levels to address redundant computations stemming from excessive tokens. Then, a novel module based on shift operations is proposed to enhance the performance of the binary Multilayer Perceptron (MLP) module without significantly increasing computational overhead. In addition, an innovative attention matrix binarization method based on quantization decomposition is proposed to evaluate the token's importance in the binarized attention matrix. Finally, we propose a regularization loss to address the inadequate optimization caused by the incompatibility between the weight oscillation in the binary layers and the Adam Optimizer. Extensive experimental results demonstrate that our proposed algorithm achieves SOTA performance among binary ViT methods.

cs.CV↗

arXiv2025

Knowledge-Decoupled Synergetic Learning: An MLLM based Collaborative Approach to Few-shot Multimodal Dialogue Intention Recognition

Few-shot multimodal dialogue intention recognition is a critical challenge in the e-commerce domainn. Previous methods have primarily enhanced model classification capabilities through post-training techniques. However, our analysis reveals that training for few-shot multimodal dialogue intention recognition involves two interconnected tasks, leading to a seesaw effect in multi-task learning. This phenomenon is attributed to knowledge interference stemming from the superposition of weight matrix updates during the training process. To address these challenges, we propose Knowledge-Decoupled Synergetic Learning (KDSL), which mitigates these issues by utilizing smaller models to transform knowledge into interpretable rules, while applying the post-training of larger models. By facilitating collaboration between the large and small multimodal large language models for prediction, our approach demonstrates significant improvements. Notably, we achieve outstanding results on two real Taobao datasets, with enhancements of 6.37\% and 6.28\% in online weighted F1 scores compared to the state-of-the-art method, thereby validating the efficacy of our framework.

cs.CL↗

arXiv2025

Discrete Differential Evolution Particle Swarm Optimization Algorithm for Energy Saving Flexible Job Shop Scheduling Problem Considering Machine Multi States

As the continuous deepening of low-carbon emission reduction policies, the manufacturing industries urgently need sensible energy-saving scheduling schemes to achieve the balance between improving production efficiency and reducing energy consumption. In energy-saving scheduling, reasonable machine states-switching is a key point to achieve expected goals, i.e., whether the machines need to switch speed between different operations, and whether the machines need to add extra setup time between different jobs. Regarding this matter, this work proposes a novel machine multi states-based energy saving flexible job scheduling problem (EFJSP-M), which simultaneously takes into account machine multi speeds and setup time. To address the proposed EFJSP-M, a kind of discrete differential evolution particle swarm optimization algorithm (D-DEPSO) is designed. In specific, D-DEPSO includes a hybrid initialization strategy to improve the initial population performance, an updating mechanism embedded with differential evolution operators to enhance population diversity, and a critical path variable neighborhood search strategy to expand the solution space. At last, based on datasets DPs and MKs, the experiment results compared with five state-of-the-art algorithms demonstrate the feasible of EFJSP-M and the superior of D-DEPSO.

cs.NE↗

arXiv2025

Radio Observation of the Pulsar Wind Nebula in SNR G11.2-0.3

Pulsar wind nebulae (PWNe) are important sources for understanding galactic high-energy processes, but it is controversial until now about how high-energy particles in PWNe are accelerated and transported. Lacking radio counterparts of X-ray PWNe (the proposed acceleration sites) introduce difficulties to better understandings in multi wavelengths. Our recent 3, 6, and 16\,cm high-resolution observations of G11.2$-$0.3 PWN with the Australia Telescope Compact Array (ATCA) uniquely show morphological similarity with its X-ray PWN (a torus/jet feature). Spectral indices of the radio torus and jet are around -0.09 and -0.10, respectively. Meanwhile for the jet region, the spectral break between radio and X-ray spectra implies particle acceleration mechanisms other than a diffusive shock acceleration. Polarization results suggest a helical B-field inside the jet, the equipartition B-field strength of which is below 100\,$μ$G.

astro-ph.HE↗

arXiv2025

RevTogether: Supporting Science Story Revision with Multiple AI Agents

As a popular form of science communication, science stories attract readers because they combine engaging narratives with comprehensible scientific knowledge. However, crafting such stories requires substantial skill and effort, as writers must navigate complex scientific concepts and transform them into coherent and accessible narratives tailored to audiences with varying levels of scientific literacy. To address the challenge, we propose RevTogether, a multi-agent system (MAS) designed to support revision of science stories with human-like AI agents (using GPT-4o). RevTogether allows AI agents to simulate affects in addition to providing comments and writing suggestions, while offering varying degrees of user agency. Our preliminary user study with non-expert writers (N=3) highlighted the need for transparency in AI agents' decision-making processes to support learning and suggested that emotional interactions could enhance human-AI collaboration in science storytelling.

cs.HC↗

arXiv2025

Higgs-strahlung at the LHC in the inert doublet model

$pp \to W^{\pm} h, Zh$ processes at the LHC are studied in the framework of the inert doublet model (IDM). To quantify the effects of the IDM and their observability in these processes we revisit the NLO (QCD and EW) predictions in the Standard Model (SM) and their uncertainty. Taking all available current constraints on the parameter space of the IDM, we consider both the case of the IDM providing a good Dark Matter (DM) candidate within the freeze-out mechanism as well as when the DM restrictions are relaxed. In the former, deviations from the SM of only a few per mil in these cross sections at the LHC are found and may not be measured. In the latter, the deviations can reach a few percents and should be observable. Smaller discrepancies in this case require that the theoretical uncertainties be improved, in particular those arising from the parton distribution functions (PDFs). We stress the importance of the photon-induced real corrections and the need for further improvement in the extraction of the photon PDF. The analysis also showcases the development and exploitation of our automated tool for the computation of one-loop electroweak and QCD corrections for a New Physics model with internal tests such as those concerning the soft and collinear parts provided through both dipole subtraction and phase space slicing besides tests for ultra-violet finiteness and gauge-parameter independence.

hep-ph↗

arXiv2025

Image Watermarks are Removable Using Controllable Regeneration from Clean Noise

Image watermark techniques provide an effective way to assert ownership, deter misuse, and trace content sources, which has become increasingly essential in the era of large generative models. A critical attribute of watermark techniques is their robustness against various manipulations. In this paper, we introduce a watermark removal approach capable of effectively nullifying state-of-the-art watermarking techniques. Our primary insight involves regenerating the watermarked image starting from a clean Gaussian noise via a controllable diffusion model, utilizing the extracted semantic and spatial features from the watermarked image. The semantic control adapter and the spatial control network are specifically trained to control the denoising process towards ensuring image quality and enhancing consistency between the cleaned image and the original watermarked image. To achieve a smooth trade-off between watermark removal performance and image consistency, we further propose an adjustable and controllable regeneration scheme. This scheme adds varying numbers of noise steps to the latent representation of the watermarked image, followed by a controlled denoising process starting from this noisy latent representation. As the number of noise steps increases, the latent representation progressively approaches clean Gaussian noise, facilitating the desired trade-off. We apply our watermark removal methods across various watermarking techniques, and the results demonstrate that our methods offer superior visual consistency/quality and enhanced watermark removal performance compared to existing regeneration approaches. Our code is available at https://github.com/yepengliu/CtrlRegen.

cs.CR↗