arXiv subjects

Chao Zhang

Publications and source records attributed to Chao Zhang.

At least 253 records · Page 14Linked to original sources

arXiv2025

3D Human-Human Interaction Anomaly Detection

Human-centric anomaly detection (AD) has been primarily studied to specify anomalous behaviors in a single person. However, as humans by nature tend to act in a collaborative manner, behavioral anomalies can also arise from human-human interactions. Detecting such anomalies using existing single-person AD models is prone to low accuracy, as these approaches are typically not designed to capture the complex and asymmetric dynamics of interactions. In this paper, we introduce a novel task, Human-Human Interaction Anomaly Detection (H2IAD), which aims to identify anomalous interactive behaviors within collaborative 3D human actions. To address H2IAD, we then propose Interaction Anomaly Detection Network (IADNet), which is formalized with a Temporal Attention Sharing Module (TASM). Specifically, in designing TASM, we share the encoded motion embeddings across both people such that collaborative motion correlations can be effectively synchronized. Moreover, we notice that in addition to temporal dynamics, human interactions are also characterized by spatial configurations between two people. We thus introduce a Distance-Based Relational Encoding Module (DREM) to better reflect social cues in H2IAD. The normalizing flow is eventually employed for anomaly scoring. Extensive experiments on human-human motion benchmarks demonstrate that IADNet outperforms existing Human-centric AD baselines in H2IAD.

cs.CV↗

arXiv2025

ESS: An Offload-Centric Latent-Cache Management Architecture for DeepSeek-V3.2-Exp

DeepSeek-V3.2-Exp introduces a sparse attention mechanism that significantly reduces inference latency in long-context scenarios. Although the overall throughput has improved greatly, the Decode-stage of PD disaggregation remains to be a major bottleneck. This bottleneck primarily stems from the conflict between linear growth of Latent-Cache with sequence length and the limited GPU memory capacity, which constrains the feasible batch-size and thereby suppresses Decode-stage throughput. To address this challenge, we propose ESS (Extended Sparse Server), an offload-centric system design tailored for DeepSeek-V3.2-Exp. ESS selectively offloads Latent-Cache to CPU memory while preserving latency-critical components on GPU. By freeing up GPU memory, ESS effectively decoupling batch-size scaling from GPU memory constraints. This design significantly improves Decode-stage throughput, thereby reducing deployment costs in real-world settings. Our high-fidelity simulations show that ESS delivers 69.4\% throughput improvement at 32K context length and up to 123\% throughput improvement at 128K, demonstrating its effectiveness for large-context inference workloads. These results highlight ESS as a practical and scalable solution for long-context LLM serving.

cs.DC↗

arXiv2025

Benchmarking Real-World Medical Image Classification with Noisy Labels: Challenges, Practice, and Outlook

Learning from noisy labels remains a major challenge in medical image analysis, where annotation demands expert knowledge and substantial inter-observer variability often leads to inconsistent or erroneous labels. Despite extensive research on learning with noisy labels (LNL), the robustness of existing methods in medical imaging has not been systematically assessed. To address this gap, we introduce LNMBench, a comprehensive benchmark for Label Noise in Medical imaging. LNMBench encompasses \textbf{10} representative methods evaluated across 7 datasets, 6 imaging modalities, and 3 noise patterns, establishing a unified and reproducible framework for robustness evaluation under realistic conditions. Comprehensive experiments reveal that the performance of existing LNL methods degrades substantially under high and real-world noise, highlighting the persistent challenges of class imbalance and domain variability in medical data. Motivated by these findings, we further propose a simple yet effective improvement to enhance model robustness under such conditions. The LNMBench codebase is publicly released to facilitate standardized evaluation, promote reproducible research, and provide practical insights for developing noise-resilient algorithms in both research and real-world medical applications.The codebase is publicly available on https://github.com/myyy777/LNMBench.

cs.CV↗

arXiv2025

Derived Representation Type and Field Extensions

Let $A$ be a finite-dimensional algebra over a field $k$. We define $A$ to be $\mathbf{C}$-dichotomic if it has the dichotomy property of the representation type on complexes of projective $A$-modules. $\mathbf{C}$-dichotomy implies the dichotomy properties of representation type on the levels of homotopy category and derived category. If $k$ admits a finite separable field extension $K/k$ such that $K$ is algebraically closed, the real number field for example, we prove that $A$ is $\mathbf{C}$-dichotomic. As a consequence, the second derived Brauer-Thrall type theorem holds for $A$, i.e., $A$ is either derived discrete or strongly derived unbounded.

math.RT↗

arXiv2025

Distribution-Aware Exploration for Adaptive HNSW Search

Hierarchical Navigable Small World (HNSW) is widely adopted for approximate nearest neighbor search (ANNS) for its ability to deliver high recall with low latency on large-scale, high-dimensional embeddings. The exploration factor, commonly referred to as ef, is a key parameter in HNSW-based vector search that balances accuracy and efficiency. However, existing systems typically rely on manually and statically configured ef values that are uniformly applied across all queries. This results in a distribution-agnostic configuration that fails to account for the non-uniform and skewed nature of real-world embedding data and query workloads. As a consequence, HNSW-based systems suffer from two key practical issues: (i) the absence of recall guarantees, and (ii) inefficient ANNS performance due to over- or under-searching. In this paper, we propose Adaptive-ef (Ada-ef), a data-driven, update-friendly, query-adaptive approach that dynamically configures ef for each query at runtime to approximately meet a declarative target recall with minimal computation. The core of our approach is a theoretically grounded statistical model that captures the similarity distribution between each query and the database vectors. Based on this foundation, we design a query scoring mechanism that distinguishes between queries requiring only small ef and those that need larger ef to meet a target recall, and accordingly assigns an appropriate ef to each query. Experimental results on real-world embeddings produced by state-of-the-art Transformer models from OpenAI and Cohere show that, compared with state-of-the-art learning-based adaptive approaches, our method achieves the target recall while avoiding both over- and under-searching, reducing online query latency by up to 4x, offline computation time by 50x, and offline memory usage by 100x.

cs.DB↗

arXiv2025

Tree Thinking in the Genomic Era: Unifying Models Across Cells, Populations, and Species

The ongoing explosion of genome sequence data is transforming how we reconstruct and understand the histories of biological systems. Across biological scales, from individual cells to populations and species, trees-based models provide a common framework for representing ancestry. Once limited to species phylogenetics, "tree thinking" now extends deeply to population genomics and cell biology, revealing the genealogical structure of genetic and phenotypic variation within and across organisms. Recently, there have been great methodological and computational advances on tree-based methods, including methods for inferring ancestral recombination graphs in populations, phylogenetic frameworks for comparative genomics, and lineage-tracing techniques in developmental and cancer biology. Despite differences in data types and biological contexts, these approaches share core statistical and algorithmic challenges: efficiently inferring branching histories from genomic information, integrating temporal and spatial signals, and connecting genealogical structures to evolutionary and functional processes. Recognizing these shared foundations opens opportunities for cross-fertilization between fields that are traditionally studied in isolation. By examining how tree-based methods are applied across cellular, population, and species scales, we identify the conceptual parallels that unite them and the distinct challenges that each domain presents. These comparisons offer new perspectives that can inform algorithmic innovations and lead to more powerful inference strategies across the full spectrum of biological systems.

q-bio.PE↗

arXiv2025

Modulation of Electroosmotic Flow through Short Nanopores by Charged Exterior Surfaces

Electroosmotic flow (EOF) through nanoporous membranes has broad applications in micro- and nanofluidic systems, particularly in biomedical diagnostics and chemical analysis. The use of short nanopores enables high fluid flux, and the presence of exterior surface charges can further enhance ion flux through short nanopores. Here, systematic simulations are conducted to explore the modulation of EOF by exterior surface charges. Our results indicate that charged exterior surfaces can provide an additional effective pathway for fluid flow, significantly increasing both the EOF velocity and output pressure. By analyzing the dependence of EOF velocity on the area of the charged exterior surface, we derive the effective width (Lcs_eff) of the charged ring region extending beyond the pore boundary. This parameter is quantitatively examined under various nanopore configurations and applied conditions. Lcs_eff is found to be proportional to the pore diameter, surface charge density, and applied voltage, while inversely proportional to pore length and salt concentration. These findings provide valuable insights into the modulation of EOF by exterior surface charges and offer theoretical guidance for optimizing the structural and functional properties of nanoporous membranes in practical applications of EOF.

physics.chem-ph↗

arXiv2025

Look as You Think: Unifying Reasoning and Visual Evidence Attribution for Verifiable Document RAG via Reinforcement Learning

Aiming to identify precise evidence sources from visual documents, visual evidence attribution for visual document retrieval-augmented generation (VD-RAG) ensures reliable and verifiable predictions from vision-language models (VLMs) in multimodal question answering. Most existing methods adopt end-to-end training to facilitate intuitive answer verification. However, they lack fine-grained supervision and progressive traceability throughout the reasoning process. In this paper, we introduce the Chain-of-Evidence (CoE) paradigm for VD-RAG. CoE unifies Chain-of-Thought (CoT) reasoning and visual evidence attribution by grounding reference elements in reasoning steps to specific regions with bounding boxes and page indexes. To enable VLMs to generate such evidence-grounded reasoning, we propose Look As You Think (LAT), a reinforcement learning framework that trains models to produce verifiable reasoning paths with consistent attribution. During training, LAT evaluates the attribution consistency of each evidence region and provides rewards only when the CoE trajectory yields correct answers, encouraging process-level self-verification. Experiments on vanilla Qwen2.5-VL-7B-Instruct with Paper- and Wiki-VISA benchmarks show that LAT consistently improves the vanilla model in both single- and multi-image settings, yielding average gains of 8.23% in soft exact match (EM) and 47.0% in IoU@0.5. Meanwhile, LAT not only outperforms the supervised fine-tuning baseline, which is trained to directly produce answers with attribution, but also exhibits stronger generalization across domains.

cs.AI↗

arXiv2025

LongCat-Flash-Omni Technical Report

We introduce LongCat-Flash-Omni, a state-of-the-art open-source omni-modal model with 560 billion parameters, excelling at real-time audio-visual interaction. By adopting a curriculum-inspired progressive training strategy that transitions from simpler to increasingly complex modality sequence modeling tasks, LongCat-Flash-Omni attains comprehensive multimodal capabilities while maintaining strong unimodal capability. Building upon LongCat-Flash, which adopts a high-performance Shortcut-connected Mixture-of-Experts (MoE) architecture with zero-computation experts, LongCat-Flash-Omni integrates efficient multimodal perception and speech reconstruction modules. Despite its immense size of 560B parameters (with 27B activated), LongCat-Flash-Omni achieves low-latency real-time audio-visual interaction. For training infrastructure, we developed a modality-decoupled parallelism scheme specifically designed to manage the data and model heterogeneity inherent in large-scale multimodal training. This innovative approach demonstrates exceptional efficiency by sustaining over 90% of the throughput achieved by text-only training. Extensive evaluations show that LongCat-Flash-Omni achieves state-of-the-art performance on omni-modal benchmarks among open-source models. Furthermore, it delivers highly competitive results across a wide range of modality-specific tasks, including text, image, and video understanding, as well as audio understanding and generation. We provide a comprehensive overview of the model architecture design, training procedures, and data strategies, and open-source the model to foster future research and development in the community.

cs.MM↗

arXiv2025

Generic effective sources for first-order in mass-ratio gravitational self-force calculations in Schwarzschild spacetime

The numerical calculation of gravitational self-force in extreme mass ratio inspiral systems is fundamentally challenging due to the singular nature of point-particle sources. To overcome these difficulties, the effective source method offers an innovative alternative by replacing traditional regularization techniques with a reformulation of the problem. In this paper, we present the first fully analytic framework for constructing effective sources to compute the gravitational self-force for generic orbits in Schwarzschild spacetime. By reformulating the singular field through angular modulation in terms of a tetrad decomposition, the effective source can be constructed with the linear combination of scalar modes. The derived effective source is continuous across the particle's worldline, enabling efficient numerical implementation in $1+1$ dimensions.

gr-qc↗

arXiv2025

EVA-Net: Interpretable Anomaly Detection for Brain Health via Learning Continuous Aging Prototypes from One-Class EEG Cohorts

The brain age is a key indicator of brain health. While electroencephalography (EEG) is a practical tool for this task, existing models struggle with the common challenge of imperfect medical data, such as learning a ``normal'' baseline from weakly supervised, healthy-only cohorts. This is a critical anomaly detection task for identifying disease, but standard models are often black boxes lacking an interpretable structure. We propose EVA-Net, a novel framework that recasts brain age as an interpretable anomaly detection problem. EVA-Net uses an efficient, sparsified-attention Transformer to model long EEG sequences. To handle noise and variability in imperfect data, it employs a Variational Information Bottleneck to learn a robust, compressed representation. For interpretability, this representation is aligned to a continuous prototype network that explicitly learns the normative healthy aging manifold. Trained on 1297 healthy subjects, EVA-Net achieves state-of-the-art accuracy. We validated its anomaly detection capabilities on an unseen cohort of 27 MCI and AD patients. This pathological group showed significantly higher brain-age gaps and a novel Prototype Alignment Error, confirming their deviation from the healthy manifold. EVA-Net provides an interpretable framework for healthcare intelligence using imperfect medical data.

cs.LG↗

arXiv2025

Xiangqi-R1: Enhancing Spatial Strategic Reasoning in LLMs for Chinese Chess via Reinforcement Learning

Game playing has long served as a fundamental benchmark for evaluating Artificial General Intelligence. While Large Language Models (LLMs) have demonstrated impressive capabilities in general reasoning, their effectiveness in spatial strategic reasoning, which is critical for complex and fully observable board games, remains insufficiently explored. In this work, we adopt Chinese Chess (Xiangqi) as a challenging and rich testbed due to its intricate rules and spatial complexity. To advance LLMs' strategic competence in such environments, we propose a training framework tailored to Xiangqi, built upon a large-scale dataset of five million board-move pairs enhanced with expert annotations and engine evaluations. Building on this foundation, we introduce Xiangqi-R1, a 7B-parameter model trained in multi-stage manner. Our Experimental results indicate that, despite their size and power, general-purpose LLMs struggle to achieve satisfactory performance in these tasks. Compared to general-purpose LLMs, Xiangqi-R1 greatly advances with an 18% rise in move legality and a 22% boost in analysis accuracy. Our results point to a promising path for creating general strategic intelligence in complex areas.

cs.AI↗

arXiv2025

BrainHGT: A Hierarchical Graph Transformer for Interpretable Brain Network Analysis

Graph Transformer shows remarkable potential in brain network analysis due to its ability to model graph structures and complex node relationships. Most existing methods typically model the brain as a flat network, ignoring its modular structure, and their attention mechanisms treat all brain region connections equally, ignoring distance-related node connection patterns. However, brain information processing is a hierarchical process that involves local and long-range interactions between brain regions, interactions between regions and sub-functional modules, and interactions among functional modules themselves. This hierarchical interaction mechanism enables the brain to efficiently integrate local computations and global information flow, supporting the execution of complex cognitive functions. To address this issue, we propose BrainHGT, a hierarchical Graph Transformer that simulates the brain's natural information processing from local regions to global communities. Specifically, we design a novel long-short range attention encoder that utilizes parallel pathways to handle dense local interactions and sparse long-range connections, thereby effectively alleviating the over-globalizing issue. To further capture the brain's modular architecture, we designe a prior-guided clustering module that utilizes a cross-attention mechanism to group brain regions into functional communities and leverage neuroanatomical prior to guide the clustering process, thereby improving the biological plausibility and interpretability. Experimental results indicate that our proposed method significantly improves performance of disease identification, and can reliably capture the sub-functional modules of the brain, demonstrating its interpretability.

cs.LG↗

arXiv2025

Regularity theory for degenerate fully nonlinear nonlocal equations with a Hamiltonian term

We investigate a class of degenerate fully nonlinear nonlocal elliptic equations with Hamiltonian terms. By precisely characterizing the interaction between the degeneracy law of equations and the growth behavior of the Hamiltonian terms, we establish the Lipschitz regularity of viscosity solutions by the Ishii-Lions method, and further show the gradient Hölder continuity for solutions via utilizing perturbation techniques. Additionally, under minimal assumptions on the degeneracy pattern, the $C^1$-differentiability property of solutions is explored as well.

math.AP↗

arXiv2025

Gravitational wave cosmology

Gravitational waves (GWs) originating from cosmological sources offer direct insights into the physics of the primordial Universe, the fundamental nature of gravity, and the cosmic expansion of the Universe. In this review paper, we present a comprehensive overview of our recent advances in GW cosmology, supported by the national key research and development program of China, focusing on cosmological GW sources and their implications for fundamental physics and cosmology. We first discuss the generation mechanisms and characteristics of stochastic gravitational wave backgrounds generated by physical processes occurred in the early Universe, including those from inflation, phase transitions, and topological defects, and summarize current and possible future constraints from pulsar timing array and space-based detectors. Next, we explore the formation and observational prospects of primordial black holes as GW sources and their potential connection to dark matter. We then analyze how GWs are affected by large-scale structure, cosmological perturbations, and possible modifications of gravity on GW propagation, and how these effects can be used to test fundamental symmetry of gravity. Finally, we discuss the application of GW standard sirens in measuring the Hubble constant, the expansion history, and dark energy parameters, including their combination with electromagnetic observations. These topics together show how GW observations, especially with upcoming space-based detectors, such as LISA, Taiji, and Tianqin, can provide new information about the physics of the early Universe, cosmological evolution, and the nature of gravity.

gr-qc↗

arXiv2025

Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs

Despite the impressive generative abilities of black-box large language models (LLMs), their inherent opacity hinders further advancements in capabilities such as reasoning, planning, and personalization. Existing works aim to enhance LLM capabilities via domain-specific adaptation, which require additional training on accessible model parameters, an infeasible option for black-box LLMs. To address this challenge, we introduce Matryoshka Pilot (M-Pilot), a lightweight white-box LLM controller that guides a large-scale black-box LLM generator by decomposing complex tasks into a series of intermediate outputs. Specifically, we consider the black-box LLM as an environment, with M-Pilot serving as a policy to provide intermediate guidance through prompts for driving the black-box LLM. M-Pilot is trained to pivot the outputs of the black-box LLM aligning with preferences during iterative interaction, which enables controllable multi-turn generation and self-improvement in optimizing intermediate guidance. Empirical evaluations on diverse tasks demonstrate that our method effectively enhances the capabilities of black-box LLMs in complex, long-horizon tasks. Our code is publicly available at: https://github.com/lichangh20/Matryoshka.

cs.LG↗

arXiv2025

The Relationship Between Environmental Regulation and Urbanization: a panel data analysis of Chinese prefecture-level cities

Since the Industrial Revolution, the world economy has experienced rapid development, and China's economy has also achieved an unprecedented takeoff in the past. Behind the economic growth, population surge, and continuous improvement of people's living standards lies the enormous consumption of fossil energy and environmental pollution. This kind of pollution has caused irreparable damage to the world. The most concerned environmental issue globally at present is the global warming caused by carbon dioxide emissions. China is in a stage of rapid development, and as the largest developing country, China's development path has a significant impact on global climate change. At the same time, the global community also puts pressure on China to limit carbon dioxide emissions. To address energy shortages and environmental issues, countries around the world have introduced corresponding energy and environmental regulations. Due to different culture and government systems, the effects of energy and environmental regulations in various countries are also different. Therefore, it is still necessary to discuss China's energy and environmental regulations.This paper uses data from prefecture-level cities between 2003 and 2008 to discuss the impact of the "Eleventh Five-Year Plan" environmental regulations on urbanization rates. It first provides a theoretical analysis of the relationship between environmental regulation and urbanization, finding that environmental regulation can influence urban population mobility through both crowding-in and crowding-out effects.

econ.GN↗

arXiv2025

Robustness of bipolaronic superconductivity to electron-density-phonon coupling

We study bipolaron formation and bipolaronic superconductivity on a square lattice, where electrons couple to both local Holstein phonons via on-site charge density and nonlocal bond Su-Schrieffer-Heeger phonons via modulation of hopping amplitudes. Using an unbiased Diagrammatic Monte Carlo method, we investigate how the interplay between these two types of electron-phonon coupling affects the bipolaron binding energy, effective mass, spatial extent (quantified by the mean-squared radius), and the superconducting transition temperature $T_c$. We find that, in some parameter space, the moderate Holstein coupling, though detrimental to $T_c$ when acting alone, can enhance superconductivity when combined with the bond SSH coupling by further compressing the bipolaron without significantly increasing its mass. Similarly, introducing bond SSH coupling into a Holstein bipolaron reduces its size while keeping the effective mass nearly unchanged, leading a higher $T_c$. These effects give rise to nonmonotonic behavior and reveal a cooperative regime in which both couplings work together to enhance superconductivity. We further examine phonon frequency asymmetry, particularly the case $ω_H/t = 2ω_B/t$, and show that in the deep adiabatic regime, adding Holstein coupling can even raise $T_c$ when combined with bond SSH coupling. These results highlight the distinct and complementary roles of local Holstein and non-local bond SSH electron-phonon couplings, and suggest strategies for optimizing high-$T_c$ superconductivity in systems with multiple phonon modes.

cond-mat.supr-con↗