arXiv subjects

Jian Zhang

Publications and source records attributed to Jian Zhang.

At least 199 records · Page 11Linked to original sources

arXiv2025

ReCon-GS: Continuum-Preserved Gaussian Streaming for Fast and Compact Reconstruction of Dynamic Scenes

Online free-viewpoint video (FVV) reconstruction is challenged by slow per-frame optimization, inconsistent motion estimation, and unsustainable storage demands. To address these challenges, we propose the Reconfigurable Continuum Gaussian Stream, dubbed ReCon-GS, a novel storage-aware framework that enables high fidelity online dynamic scene reconstruction and real-time rendering. Specifically, we dynamically allocate multi-level Anchor Gaussians in a density-adaptive fashion to capture inter-frame geometric deformations, thereby decomposing scene motion into compact coarse-to-fine representations. Then, we design a dynamic hierarchy reconfiguration strategy that preserves localized motion expressiveness through on-demand anchor re-hierarchization, while ensuring temporal consistency through intra-hierarchical deformation inheritance that confines transformation priors to their respective hierarchy levels. Furthermore, we introduce a storage-aware optimization mechanism that flexibly adjusts the density of Anchor Gaussians at different hierarchy levels, enabling a controllable trade-off between reconstruction fidelity and memory usage. Extensive experiments on three widely used datasets demonstrate that, compared to state-of-the-art methods, ReCon-GS improves training efficiency by approximately 15% and achieves superior FVV synthesis quality with enhanced robustness and stability. Moreover, at equivalent rendering quality, ReCon-GS slashes memory requirements by over 50% compared to leading state-of-the-art methods.

eess.IV↗

arXiv2025

ODesign: A World Model for Biomolecular Interaction Design

Biomolecular interactions underpin almost all biological processes, and their rational design is central to programming new biological functions. Generative AI models have emerged as powerful tools for molecular design, yet most remain specialized for individual molecular types and lack fine-grained control over interaction details. Here we present ODesign, an all-atom generative world model for all-to-all biomolecular interaction design. ODesign allows scientists to specify epitopes on arbitrary targets and generate diverse classes of binding partners with fine-grained control. Across entity-, token-, and atom-level benchmarks in the protein modality, ODesign demonstrates superior controllability and performance to modality-specific baselines. Extending beyond proteins, it generalizes to nucleic acid and small-molecule design, enabling interaction types such as protein-binding RNA/DNA and RNA/DNA-binding ligands that were previously inaccessible. By unifying multimodal biomolecular interactions within a single generative framework, ODesign moves toward a general-purpose molecular world model capable of programmable design. ODesign is available at https://odesign.lglab.ac.cn ,

q-bio.BM↗

arXiv2025

Kinematic, Elemental and Structural Dependences on Metallicity in the Galactic Bulge

We selected Bulge stars from APOGEE DR17 cross-matched with astrometric data from \textit{Gaia} DR3. Bulge stars were divided into sub-samples with line-of-sight velocity dispersion analyzed and the peaks of MDF were detected by both Gaussian Mixture Models (GMM) and \texttt{scipy.signal.find\_peaks}. GMM is also conducted to kinematically distinguish the metal-poor and metal-rich populations. Analyses were put on the Bulge stars (including retrograde stars), their elemental abundances, and the [Mg/Mn]-[Al/Fe] plane to investigate potential accreted components. Finally, the shapes (X-shaped/boxy) of Bulge stars with different metallicities were analyzed through least-squares fitting based on the analytical Bulge models. By studying the kinematic, elemental and structural dependences on metallicity for Bulge stars, our findings are concluded as follows: 1. Six peaks are detected in the Bulge MDF, encompassing values reported in previous studies, suggesting a complex composition of Bulge populations. 2. An inversion relationship is well-observed in metal-rich sub-samples, while absent in metal-poor sub-samples. 3. Metal-poor populations exhibit larger dispersions than metal-rich stars (which is also revealed by GMM decomposition), suggesting that metal-rich stars are kinematically coherent. 4. Retrograde stars are confined to $\sim1$ kpc of the Galactic center, with their relative fraction decreasing at higher [Fe/H] -- a trend potentially linked to the ``spin-up'' process of Galactic disks. 5. Metal-rich Bulge stars with [Al/Fe] $<-0.15$ are likely associated with from disk accreted substructure, while all elemental planes exhibit bimodality but Na abundances rise monotonically with metallicity. 6. In general, stars with all metallicities support a boxy profile.

astro-ph.GA↗

arXiv2025

FlashMP: Fast Discrete Transform-Based Solver for Preconditioning Maxwell's Equations on GPUs

Efficiently solving large-scale linear systems is a critical challenge in electromagnetic simulations, particularly when using the Crank-Nicolson Finite-Difference Time-Domain (CN-FDTD) method. Existing iterative solvers are commonly employed to handle the resulting sparse systems but suffer from slow convergence due to the ill-conditioned nature of the double-curl operator. Approximate preconditioners, like Successive Over-Relaxation (SOR) and Incomplete LU decomposition (ILU), provide insufficient convergence, while direct solvers are impractical due to excessive memory requirements. To address this, we propose FlashMP, a novel preconditioning system that designs a subdomain exact solver based on discrete transforms. FlashMP provides an efficient GPU implementation that achieves multi-GPU scalability through domain decomposition. Evaluations on AMD MI60 GPU clusters (up to 1000 GPUs) show that FlashMP reduces iteration counts by up to 16x and achieves speedups of 2.5x to 4.9x compared to baseline implementations in state-of-the-art libraries such as Hypre. Weak scalability tests show parallel efficiencies up to 84.1%.

cs.DC↗

arXiv2025

Frame-Difference Guided Dynamic Region Perception for CLIP Adaptation in Text-Video Retrieval

With the rapid growth of video data, text-video retrieval technology has become increasingly important in numerous application scenarios such as recommendation and search. Early text-video retrieval methods suffer from two critical drawbacks: first, they heavily rely on large-scale annotated video-text pairs, leading to high data acquisition costs; second, there is a significant modal gap between video and text features, which limits cross-modal alignment accuracy. With the development of vision-language model, adapting CLIP to video tasks has attracted great attention. However, existing adaptation methods generally lack enhancement for dynamic video features and fail to effectively suppress static redundant features. To address this issue, this paper proposes FDA-CLIP (Frame Difference Alpha-CLIP), which is a concise CLIP-based training framework for text-video alignment. Specifically, the method uses frame differences to generate dynamic region masks, which are input into Alpha-CLIP as an additional Alpha channel. This proactively guides the model to focus on semantically critical dynamic regions while suppressing static background redundancy. Experiments demonstrate that frame difference-guided video semantic encoding can effectively balance retrieval efficiency and accuracy.

cs.CV↗

arXiv2025

Learned Cost Model for Placement on Reconfigurable Dataflow Hardware

Mapping a dataflow-graph of an ML model onto a reconfigurable system is difficult, as different mappings have different throughputs and consume resource constraints differently. To solve this, a model to evaluate the throughput of mappings is necessary as measuring throughput completely is expensive. Many use a hand-designed analytical model, relying on proxy features or intuition, introducing error. We provide a Learned Approach that predicts throughput 31%-52% more accurately over a variety of graphs. In addition, our approach shows no accuracy degradation after removing performance annotations. We show that using this approach results in 5.6% faster compiled graphs.

cs.DC↗

arXiv2025

Humanoid-inspired Causal Representation Learning for Domain Generalization

This paper proposes the Humanoid-inspired Structural Causal Model (HSCM), a novel causal framework inspired by human intelligence, designed to overcome the limitations of conventional domain generalization models. Unlike approaches that rely on statistics to capture data-label dependencies and learn distortion-invariant representations, HSCM replicates the hierarchical processing and multi-level learning of human vision systems, focusing on modeling fine-grained causal mechanisms. By disentangling and reweighting key image attributes such as color, texture, and shape, HSCM enhances generalization across diverse domains, ensuring robust performance and interpretability. Leveraging the flexibility and adaptability of human intelligence, our approach enables more effective transfer and learning in dynamic, complex environments. Through both theoretical and empirical evaluations, we demonstrate that HSCM outperforms existing domain generalization models, providing a more principled method for capturing causal relationships and improving model robustness. The code is available at https://github.com/lambett/HSCM.

cs.AI↗

arXiv2025

Small Language Models Offer Significant Potential for Science Community

Recent advancements in natural language processing, particularly with large language models (LLMs), are transforming how scientists engage with the literature. While the adoption of LLMs is increasing, concerns remain regarding potential information biases and computational costs. Rather than LLMs, I developed a framework to evaluate the feasibility of precise, rapid, and cost-effective information retrieval from extensive geoscience literature using freely available small language models (MiniLMs). A curated corpus of approximately 77 million high-quality sentences, extracted from 95 leading peer-reviewed geoscience journals such as Geophysical Research Letters and Earth and Planetary Science Letters published during years 2000 to 2024, was constructed. MiniLMs enable a computationally efficient approach for extracting relevant domain-specific information from these corpora through semantic search techniques and sentence-level indexing. This approach, unlike LLMs such as ChatGPT-4 that often produces generalized responses, excels at identifying substantial amounts of expert-verified information with established, multi-disciplinary sources, especially for information with quantitative findings. Furthermore, by analyzing emotional tone via sentiment analysis and topical clusters through unsupervised clustering within sentences, MiniLM provides a powerful tool for tracking the evolution of conclusions, research priorities, advancements, and emerging questions within geoscience communities. Overall, MiniLM holds significant potential within the geoscience community for applications such as fact and image retrievals, trend analyses, contradiction analyses, and educational purposes.

cs.CL↗

arXiv2025

Synergistic modulation of band structure and phonon transport for higher thermoelectric performance of WSe2

Tungsten diselenide (WSe2) emerges as a promising thermoelectric (TE) candidate due to its high thermopower (S), cost-effectiveness, and environmentally friendly characteristics. However, pristine WSe2 exhibits limited electrical conductivity (sigma), a low power factor (PF), and high lattice thermal conductivity (k_L), which restrict its overall TE performance. Here, we show that through co-doping of Nb for W and Te for Se in WSe2, its power factor increases 17-fold, reaching 8.91 microW cm^-1 K^-2 at 850 K. Simultaneously, its lattice thermal conductivity (k_L) decreases from 1.70 W m^-1 K^-1 to 0.48 W m^-1 K^-1. Experiments and density functional theory (DFT) analysis demonstrate that the enhancement of PF is linked to an increased density of states, higher effective mass (md*), improved mobility (mu), and elevated electrical conductivity (sigma) owing to the replacement of Se2- with Te2-; while the observed 72% reduction in k_L results primarily from phonon scattering at Te-Se and Nb-W defects. As a result, a remarkable ZT_max ~ 1 is obtained at 850 K for the sample W0.95Nb0.05Se2-yTey with y = 0.3, which is about a 30-fold increase compared to WSe2, proving that Nb and Te co-doping in WSe2 can significantly boost its TE performance.

cond-mat.mtrl-sci↗

arXiv2025

FedL2T: Personalized Federated Learning with Two-Teacher Distillation for Seizure Prediction

The training of deep learning models in seizure prediction requires large amounts of Electroencephalogram (EEG) data. However, acquiring sufficient labeled EEG data is difficult due to annotation costs and privacy constraints. Federated Learning (FL) enables privacy-preserving collaborative training by sharing model updates instead of raw data. However, due to the inherent inter-patient variability in real-world scenarios, existing FL-based seizure prediction methods struggle to achieve robust performance under heterogeneous client settings. To address this challenge, we propose FedL2T, a personalized federated learning framework that leverages a novel two-teacher knowledge distillation strategy to generate superior personalized models for each client. Specifically, each client simultaneously learns from a globally aggregated model and a dynamically assigned peer model, promoting more direct and enriched knowledge exchange. To ensure reliable knowledge transfer, FedL2T employs an adaptive multi-level distillation strategy that aligns both prediction outputs and intermediate feature representations based on task confidence. In addition, a proximal regularization term is introduced to constrain personalized model updates, thereby enhancing training stability. Extensive experiments on two EEG datasets demonstrate that FedL2T consistently outperforms state-of-the-art FL methods, particularly under low-label conditions. Moreover, FedL2T exhibits rapid and stable convergence toward optimal performance, thereby reducing the number of communication rounds and associated overhead. These results underscore the potential of FedL2T as a reliable and personalized solution for seizure prediction in privacy-sensitive healthcare scenarios.

cs.LG↗

arXiv2025

On the Implicit Adversariality of Catastrophic Forgetting in Deep Continual Learning

Continual learning seeks the human-like ability to accumulate new skills in machine intelligence. Its central challenge is catastrophic forgetting, whose underlying cause has not been fully understood for deep networks. In this paper, we demystify catastrophic forgetting by revealing that the new-task training is implicitly an adversarial attack against the old-task knowledge. Specifically, the new-task gradients automatically and accurately align with the sharp directions of the old-task loss landscape, rapidly increasing the old-task loss. This adversarial alignment is intriguingly counter-intuitive because the sharp directions are too sparsely distributed to align with by chance. To understand it, we theoretically show that it arises from training's low-rank bias, which, through forward and backward propagation, confines the two directions into the same low-dimensional subspace, facilitating alignment. Gradient projection (GP) methods, a representative family of forgetting-mitigating methods, reduce adversarial alignment caused by forward propagation, but cannot address the alignment due to backward propagation. We propose backGP to address it, which reduces forgetting by 10.8% and improves accuracy by 12.7% on average over GP methods.

cs.LG↗

arXiv2025

ConstraintLLM: A Neuro-Symbolic Framework for Industrial-Level Constraint Programming

Constraint programming (CP) is a crucial technology for solving real-world constraint optimization problems (COPs), with the advantages of rich modeling semantics and high solving efficiency. Using large language models (LLMs) to generate formal modeling automatically for COPs is becoming a promising approach, which aims to build trustworthy neuro-symbolic AI with the help of symbolic solvers. However, CP has received less attention compared to works based on operations research (OR) models. We introduce ConstraintLLM, the first LLM specifically designed for CP modeling, which is trained on an open-source LLM with multi-instruction supervised fine-tuning. We propose the Constraint-Aware Retrieval Module (CARM) to increase the in-context learning capabilities, which is integrated in a Tree-of-Thoughts (ToT) framework with guided self-correction mechanism. Moreover, we construct and release IndusCP, the first industrial-level benchmark for CP modeling, which contains 140 challenging tasks from various domains. Our experiments demonstrate that ConstraintLLM achieves state-of-the-art solving accuracy across multiple benchmarks and outperforms the baselines by 2x on the new IndusCP benchmark. Code and data are available at: https://github.com/william4s/ConstraintLLM.

cs.AI↗

arXiv2025

Humanoid Policy ~ Human Policy

Training manipulation policies for humanoid robots with diverse data enhances their robustness and generalization across tasks and platforms. However, learning solely from robot demonstrations is labor-intensive, requiring expensive tele-operated data collection which is difficult to scale. This paper investigates a more scalable data source, egocentric human demonstrations, to serve as cross-embodiment training data for robot learning. We mitigate the embodiment gap between humanoids and humans from both the data and modeling perspectives. We collect an egocentric task-oriented dataset (PH2D) that is directly aligned with humanoid manipulation demonstrations. We then train a human-humanoid behavior policy, which we term Human Action Transformer (HAT). The state-action space of HAT is unified for both humans and humanoid robots and can be differentiably retargeted to robot actions. Co-trained with smaller-scale robot data, HAT directly models humanoid robots and humans as different embodiments without additional supervision. We show that human data improves both generalization and robustness of HAT with significantly better data collection efficiency. Code and data: https://human-as-robot.github.io/

cs.RO↗

arXiv2025

Quantum super Manin matrices

Manin matrices are quantum linear transformations of general quantum spaces. In this paper, we study the $q$-analogue of super Manin matrices and obtain several quantum versions of classical identities, such as Jacobi's ratio theorem, Schur's complement theorem, Cayley's complementary theorem, Muir's law, Sylvester's theorem, MacMahon Master Theorem and Newton's identities.

math.QA↗

arXiv2025

Automatic Building Code Review: A Case Study

Building officials, particularly those in resource-constrained or rural jurisdictions, face labor-intensive, error-prone, and costly manual reviews of design documents as projects increase in size and complexity. The growing adoption of Building Information Modeling (BIM) and Large Language Models (LLMs) presents opportunities for automated code review (ACR) solutions. This study introduces a novel agent-driven framework that integrates BIM-based data extraction with automated verification using both retrieval-augmented generation (RAG) and Model Context Protocol (MCP) agent pipelines. The framework employs LLM-enabled agents to extract geometry, schedules, and system attributes from heterogeneous file types, which are then processed for building code checking through two complementary mechanisms: (1) direct API calls to the US Department of Energy COMcheck engine, providing deterministic and audit-ready outputs, and (2) RAG-based reasoning over rule provisions, enabling flexible interpretation where coverage is incomplete or ambiguous. The framework was evaluated through case demonstrations, including automated extraction of geometric attributes (such as surface area, tilt, and insulation values), parsing of operational schedules, and validation of lighting allowances under ASHRAE Standard 90.1-2022. Comparative performance tests across multiple LLMs showed that GPT-4o achieved the best balance of efficiency and stability, while smaller models exhibited inconsistencies or failures. Results confirm that MCP agent pipelines outperform RAG reasoning pipelines in rigor and reliability. This work advances ACR research by demonstrating a scalable, interoperable, and production-ready approach that bridges BIM with authoritative code review tools.

cs.SE↗

arXiv2025

Plan before Solving: Problem-Aware Strategy Routing for Mathematical Reasoning with LLMs

Existing methods usually leverage a fixed strategy, such as natural language reasoning, code-augmented reasoning, tool-integrated reasoning, or ensemble-based reasoning, to guide Large Language Models (LLMs) to perform mathematical reasoning. Our analysis reveals that the single strategy cannot adapt to problem-specific requirements and thus overlooks the trade-off between effectiveness and efficiency. To address these issues, we propose Planning and Routing through Instance-Specific Modeling (PRISM), a novel framework that decouples mathematical reasoning into two stages: strategy planning and targeted execution. Specifically, we first curate a multi-strategy preference dataset, which we call MathStrat, capturing correctness, process quality, and computational efficiency for each problem--strategy pair. Then, we train a lightweight Strategy Adapter based on the dataset to obtain confidence distributions over the mentioned four reasoning strategies. At inference time, an adaptive routing policy dynamically tailors the reasoning approach based on predictor confidence. It directs the model to use single-strategy execution for high-confidence predictions, dual-strategy verification for competitive scenarios, or comprehensive multi-strategy exploration for uncertain cases. Extensive experiments across five mathematical reasoning benchmarks demonstrate that PRISM consistently outperforms individual strategies and ensemble baselines, achieving improvements ranging from 0.9% to 7.6% across different base models. The adaptive routing approach shows particularly strong benefits for mathematical reasoning tasks across diverse model architectures. Our code is released at https://github.com/reml-group/PRISM.

cs.AI↗

arXiv2025

WildSpeech-Bench: Benchmarking End-to-End SpeechLLMs in the Wild

Recent multi-modal Large Language Models (LLMs) such as GPT-4o have demonstrated strong capabilities of direct speech interaction. However, the lack of specialized and comprehensive benchmarks for end-to-end speech LLM evaluation hinders optimizing the user experience of Audio LLMs in real-world applications. Existing evaluation methods often adapt text-based benchmarks, overlooking speech's unique characteristics and challenges, including prosody, homophones, stuttering, and differing user expectations. Here, we introduce the first comprehensive benchmark designed to systematically evaluate end-to-end speechLLMs in practical speech conversations. We systematically curate real-world chat data relevant to spoken scenarios, introduce diversity in speaker attributes and acoustic conditions, and augment the dataset with speech-specific phenomena. We further design a query-aware evaluation method to use customized evaluation checklists and prompts to enhance the accuracy of automatic evaluation. We conduct comprehensive testing and detailed analysis of various mainstream speech models, revealing significant differences in model performance across different speech scenarios. The use of query-aware evaluation further enables a finer-grained assessment under various speech-specific scenarios. Our benchmark can provide valuable insights for speech model development and evaluation.

cs.CL↗

arXiv2025

GaussianSeal: Rooting Adaptive Watermarks for 3D Gaussian Generation Model

With the advancement of AIGC technologies, the modalities generated by models have expanded from images and videos to 3D objects, leading to an increasing number of works focused on 3D Gaussian Splatting (3DGS) generative models. Existing research on copyright protection for generative models has primarily concentrated on watermarking in image and text modalities, with little exploration into the copyright protection of 3D object generative models. In this paper, we propose the first bit watermarking framework for 3DGS generative models, named GaussianSeal, to enable the decoding of bits as copyright identifiers from the rendered outputs of generated 3DGS. By incorporating adaptive bit modulation modules into the generative model and embedding them into the network blocks in an adaptive way, we achieve high-precision bit decoding with minimal training overhead while maintaining the fidelity of the model's outputs. Experiments demonstrate that our method outperforms post-processing watermarking approaches for 3DGS objects, achieving superior performance of watermark decoding accuracy and preserving the quality of the generated results.

cs.CV↗