arXiv subjects

Bin Li

Publications and source records attributed to Bin Li.

At least 217 records · Page 12Linked to original sources

arXiv2025

Spectral-Prior Guided Multistage Physics-Informed Neural Networks for Highly Accurate PDE Solutions

Physics-Informed Neural Networks (PINNs) are becoming a popular method for solving PDEs, due to their mesh-free nature and their ability to handle high-dimensional problems where traditional numerical solvers often struggle. Despite their promise, the practical application of PINNs is still constrained by several fac- tors, a primary one being their often-limited accuracy. This paper is dedicated to enhancing the accuracy of PINNs by introducing spectral-prior guided multistage strategy. We propose two methods: Spectrum- Informed Multistage Physics-Informed Neural Networks (SI-MSPINNs) and Multistage Physics-Informed Neural Networks with Spectrum Weighted Random Fourier Features (RFF-MSPINNs). The SI-MSPINNs integrate the core mechanism of Spectrum-Informed Multistage Neural Network (SI-MSNNs) and PINNs, in which we extract the Dominant Spectral Pattern (DSP) of residuals by the discrete Fourier transform. This DSP guides the network initialization to alleviate spectral bias, and gradually optimizes the resolution accuracy using a multistage strategy. The RFF-MSPINNs combines random Fourier features with spectral weighting methods, dynamically adjusting the frequency sampling distribution based on the residual power spectral density, allowing the network to prioritize learning high-energy physical modes. Through experimental verification of the Burgers equation and the Helmholtz equation, we show that both models significantly improve the accuracy of the original PINNs.

math.NA↗

arXiv2025

From Intent to Execution: Multimodal Chain-of-Thought Reinforcement Learning for Precise CAD Code Generation

Computer-Aided Design (CAD) plays a vital role in engineering and manufacturing, yet current CAD workflows require extensive domain expertise and manual modeling effort. Recent advances in large language models (LLMs) have made it possible to generate code from natural language, opening new opportunities for automating parametric 3D modeling. However, directly translating human design intent into executable CAD code remains highly challenging, due to the need for logical reasoning, syntactic correctness, and numerical precision. In this work, we propose CAD-RL, a multimodal Chain-of-Thought (CoT) guided reinforcement learning post training framework for CAD modeling code generation. Our method combines CoT-based Cold Start with goal-driven reinforcement learning post training using three task-specific rewards: executability reward, geometric accuracy reward, and external evaluation reward. To ensure stable policy learning under sparse and high-variance reward conditions, we introduce three targeted optimization strategies: Trust Region Stretch for improved exploration, Precision Token Loss for enhanced dimensions parameter accuracy, and Overlong Filtering to reduce noisy supervision. To support training and benchmarking, we release ExeCAD, a noval dataset comprising 16,540 real-world CAD examples with paired natural language and structured design language descriptions, executable CADQuery scripts, and rendered 3D models. Experiments demonstrate that CAD-RL achieves significant improvements in reasoning quality, output precision, and code executability over existing VLMs.

cs.LG↗

arXiv2025

Interpretable Oracle Bone Script Decipherment through Radical and Pictographic Analysis with LVLMs

As the oldest mature writing system, Oracle Bone Script (OBS) has long posed significant challenges for archaeological decipherment due to its rarity, abstractness, and pictographic diversity. Current deep learning-based methods have made exciting progress on the OBS decipherment task, but existing approaches often ignore the intricate connections between glyphs and the semantics of OBS. This results in limited generalization and interpretability, especially when addressing zero-shot settings and undeciphered OBS. To this end, we propose an interpretable OBS decipherment method based on Large Vision-Language Models, which synergistically combines radical analysis and pictograph-semantic understanding to bridge the gap between glyphs and meanings of OBS. Specifically, we propose a progressive training strategy that guides the model from radical recognition and analysis to pictographic analysis and mutual analysis, thus enabling reasoning from glyph to meaning. We also design a Radical-Pictographic Dual Matching mechanism informed by the analysis results, significantly enhancing the model's zero-shot decipherment performance. To facilitate model training, we propose the Pictographic Decipherment OBS Dataset, which comprises 47,157 Chinese characters annotated with OBS images and pictographic analysis texts. Experimental results on public benchmarks demonstrate that our approach achieves state-of-the-art Top-10 accuracy and superior zero-shot decipherment capabilities. More importantly, our model delivers logical analysis processes, possibly providing archaeologically valuable reference results for undeciphered OBS, and thus has potential applications in digital humanities and historical research. The dataset and code will be released in https://github.com/PKXX1943/PD-OBS.

cs.CV↗

arXiv2025

Visuomotor Grasping with World Models for Surgical Robots

Grasping is a fundamental task in robot-assisted surgery (RAS), and automating it can reduce surgeon workload while enhancing efficiency, safety, and consistency beyond teleoperated systems. Most prior approaches rely on explicit object pose tracking or handcrafted visual features, limiting their generalization to novel objects, robustness to visual disturbances, and the ability to handle deformable objects. Visuomotor learning offers a promising alternative, but deploying it in RAS presents unique challenges, such as low signal-to-noise ratio in visual observations, demands for high safety and millimeter-level precision, as well as the complex surgical environment. This paper addresses three key challenges: (i) sim-to-real transfer of visuomotor policies to ex vivo surgical scenes, (ii) visuomotor learning using only a single stereo camera pair -- the standard RAS setup, and (iii) object-agnostic grasping with a single policy that generalizes to diverse, unseen surgical objects without retraining or task-specific models. We introduce Grasp Anything for Surgery V2 (GASv2), a visuomotor learning framework for surgical grasping. GASv2 leverages a world-model-based architecture and a surgical perception pipeline for visual observations, combined with a hybrid control system for safe execution. We train the policy in simulation using domain randomization for sim-to-real transfer and deploy it on a real robot in both phantom-based and ex vivo surgical settings, using only a single pair of endoscopic cameras. Extensive experiments show our policy achieves a 65% success rate in both settings, generalizes to unseen objects and grippers, and adapts to diverse disturbances, demonstrating strong performance, generality, and robustness.

cs.RO↗

arXiv2025

IADGPT: Unified LVLM for Few-Shot Industrial Anomaly Detection, Localization, and Reasoning via In-Context Learning

Few-Shot Industrial Anomaly Detection (FS-IAD) has important applications in automating industrial quality inspection. Recently, some FS-IAD methods based on Large Vision-Language Models (LVLMs) have been proposed with some achievements through prompt learning or fine-tuning. However, existing LVLMs focus on general tasks but lack basic industrial knowledge and reasoning capabilities related to FS-IAD, making these methods far from specialized human quality inspectors. To address these challenges, we propose a unified framework, IADGPT, designed to perform FS-IAD in a human-like manner, while also handling associated localization and reasoning tasks, even for diverse and novel industrial products. To this end, we introduce a three-stage progressive training strategy inspired by humans. Specifically, the first two stages gradually guide IADGPT in acquiring fundamental industrial knowledge and discrepancy awareness. In the third stage, we design an in-context learning-based training paradigm, enabling IADGPT to leverage a few-shot image as the exemplars for improved generalization to novel products. In addition, we design a strategy that enables IADGPT to output image-level and pixel-level anomaly scores using the logits output and the attention map, respectively, in conjunction with the language output to accomplish anomaly reasoning. To support our training, we present a new dataset comprising 100K images across 400 diverse industrial product categories with extensive attribute-level textual annotations. Experiments indicate IADGPT achieves considerable performance gains in anomaly detection and demonstrates competitiveness in anomaly localization and reasoning. We will release our dataset in camera-ready.

cs.CV↗

arXiv2025

Emotion-Qwen: A Unified Framework for Emotion and Vision Understanding

Accurate emotion understanding in videos necessitates effectively recognizing and interpreting emotional states by integrating visual, textual, auditory, and contextual cues. Although recent Large Multimodal Models (LMMs) have exhibited significant progress in general vision-language (VL) tasks, their performance often deteriorates in emotion-specific scenarios, exhibiting catastrophic forgetting when fine-tuned on emotion-centric tasks. To overcome these limitations, we propose Emotion-Qwen, a unified multimodal framework designed to simultaneously enable robust emotion understanding and preserve general VL reasoning capabilities. Emotion-Qwen introduces a novel Hybrid Compressor based on a Mixture-of-Experts (MoE) architecture, dynamically routing inputs to optimally balance emotion-specific processing and general multimodal reasoning. We further propose a carefully structured three-stage pre-training pipeline, leveraging extensive general and emotion-focused datasets to strengthen multimodal representation robustness and model adaptability. Additionally, we develop the Video Emotion Reasoning (VER) dataset, a large-scale bilingual resource containing over 40K video clips annotated with detailed context-aware emotional descriptions, significantly facilitating research on fine-grained emotional reasoning. Extensive experiments confirm that Emotion-Qwen achieves state-of-the-art performance across multiple emotion recognition and reasoning benchmarks, while maintaining highly competitive results in general VL tasks.

cs.MM↗

arXiv2025

See the Forest and the Trees: A Synergistic Reasoning Framework for Knowledge-Based Visual Question Answering

Multimodal Large Language Models (MLLMs) have pushed the frontiers of Knowledge-Based Visual Question Answering (KBVQA), yet their reasoning is fundamentally bottlenecked by a reliance on uni-dimensional evidence. This "seeing only the trees, but not the forest" approach prevents robust, multi-faceted understanding. Inspired by the principle of seeing both the forest and trees, we propose Synergos-VQA, a novel synergistic reasoning framework. At its core, Synergos-VQA concurrently generates and fuses three complementary evidence streams at inference time: (1) Holistic Evidence to perceive the entire scene (the "forest"), (2) Structural Evidence from a prototype-driven module to identify key objects (the "trees"), and (3) Causal Evidence from a counterfactual probe to ensure the reasoning is robustly grounded. By synergistically fusing this multi-faceted evidence, our framework achieves a more comprehensive and reliable reasoning process. Extensive experiments show that Synergos-VQA decisively establishes a new state-of-the-art on three challenging benchmarks, including OK-VQA and A-OKVQA. Furthermore, our approach demonstrates strong plug-and-play capabilities, significantly boosting various open-source MLLMs and proving that superior methodological design can outperform sheer model scale.

cs.CV↗

arXiv2025

CLUE: Leveraging Low-Rank Adaptation to Capture Latent Uncovered Evidence for Image Forgery Localization

The increasing accessibility of image editing tools and generative AI has led to a proliferation of visually convincing forgeries, compromising the authenticity of digital media. In this paper, in addition to leveraging distortions from conventional forgeries, we repurpose the mechanism of a state-of-the-art (SOTA) text-to-image synthesis model by exploiting its internal generative process, turning it into a high-fidelity forgery localization tool. To this end, we propose CLUE (Capture Latent Uncovered Evidence), a framework that employs Low- Rank Adaptation (LoRA) to parameter-efficiently reconfigure Stable Diffusion 3 (SD3) as a forensic feature extractor. Our approach begins with the strategic use of SD3's Rectified Flow (RF) mechanism to inject noise at varying intensities into the latent representation, thereby steering the LoRAtuned denoising process to amplify subtle statistical inconsistencies indicative of a forgery. To complement the latent analysis with high-level semantic context and precise spatial details, our method incorporates contextual features from the image encoder of the Segment Anything Model (SAM), which is parameter-efficiently adapted to better trace the boundaries of forged regions. Extensive evaluations demonstrate CLUE's SOTA generalization performance, significantly outperforming prior methods. Furthermore, CLUE shows superior robustness against common post-processing attacks and Online Social Networks (OSNs). Code is publicly available at https://github.com/SZAISEC/CLUE.

cs.CV↗

arXiv2025

Low-Cost Test-Time Adaptation for Robust Video Editing

Video editing is a critical component of content creation that transforms raw footage into coherent works aligned with specific visual and narrative objectives. Existing approaches face two major challenges: temporal inconsistencies due to failure in capturing complex motion patterns, and overfitting to simple prompts arising from limitations in UNet backbone architectures. While learning-based methods can enhance editing quality, they typically demand substantial computational resources and are constrained by the scarcity of high-quality annotated data. In this paper, we present Vid-TTA, a lightweight test-time adaptation framework that personalizes optimization for each test video during inference through self-supervised auxiliary tasks. Our approach incorporates a motion-aware frame reconstruction mechanism that identifies and preserves crucial movement regions, alongside a prompt perturbation and reconstruction strategy that strengthens model robustness to diverse textual descriptions. These innovations are orchestrated by a meta-learning driven dynamic loss balancing mechanism that adaptively adjusts the optimization process based on video characteristics. Extensive experiments demonstrate that Vid-TTA significantly improves video temporal consistency and mitigates prompt overfitting while maintaining low computational overhead, offering a plug-and-play performance boost for existing video editing models.

cs.CV↗

arXiv2025

MATE: Motion-Augmented Temporal Consistency for Event-based Point Tracking

Tracking Any Point (TAP) plays a crucial role in motion analysis. Video-based approaches rely on iterative local matching for tracking, but they assume linear motion during the blind time between frames, which leads to point loss under large displacements or nonlinear motion. The high temporal resolution and motion blur-free characteristics of event cameras provide continuous, fine-grained motion information, capturing subtle variations with microsecond precision. This paper presents an event-based framework for tracking any point, which tackles the challenges posed by spatial sparsity and motion sensitivity in events through two tailored modules. Specifically, to resolve ambiguities caused by event sparsity, a motion-guidance module incorporates kinematic vectors into the local matching process. Additionally, a variable motion aware module is integrated to ensure temporally consistent responses that are insensitive to varying velocities, thereby enhancing matching precision. To validate the effectiveness of the approach, two event dataset for tracking any point is constructed by simulation. The method improves the $Survival_{50}$ metric by 17.9% over event-only tracking of any point baseline. Moreover, on standard feature tracking benchmarks, it outperforms all existing methods, even those that combine events and video frames.

cs.CV↗

arXiv2025

LumiCRS: Asymmetric Contrastive Prototype Learning for Long-Tail Conversational Recommender Systems

Conversational recommender systems (CRSs) often suffer from an extreme long-tail distribution of dialogue data, causing a strong bias toward head-frequency blockbusters that sacrifices diversity and exacerbates the cold-start problem. An empirical analysis of DCRS and statistics on the REDIAL corpus show that only 10% of head movies account for nearly half of all mentions, whereas about 70% of tail movies receive merely 26% of the attention. This imbalance gives rise to three critical challenges: head over-fitting, body representation drift, and tail sparsity. To address these issues, we propose LumiCRS, an end-to-end framework that mitigates long-tail imbalance through three mutually reinforcing layers: (i) an Adaptive Comprehensive Focal Loss (ACFL) that dynamically adjusts class weights and focusing factors to curb head over-fitting and reduce popularity bias; (ii) Prototype Learning for Long-Tail Recommendation, which selects semantic, affective, and contextual prototypes to guide clustering and stabilize body and tail representations; and (iii) a GPT-4o-driven prototype-guided dialogue augmentation module that automatically generates diverse long-tail conversational snippets to alleviate tail sparsity and distribution shift. Together, these strategies enable LumiCRS to markedly improve recommendation accuracy, diversity, and fairness: on the REDIAL and INSPIRED benchmarks, LumiCRS boosts Recall@10 and Tail-Recall@10 by 7-15% over fifteen strong baselines, while human evaluations confirm superior fluency, informativeness, and long-tail relevance. These results demonstrate the effectiveness of multi-layer collaboration in building an efficient and fair long-tail conversational recommender.

cs.AI↗

arXiv2025

Approximate Revenue Maximization for Diffusion Auctions

Reserve prices are widely used in practice. The problem of designing revenue-optimal auctions based on reserve price has drawn much attention in the auction design community. Although they have been extensively studied, most developments rely on the significant assumption that the target audience of the sale is directly reachable by the auctioneer, while a large portion of bidders in the economic network unaware of the sale are omitted. This work follows the diffusion auction design, which aims to extend the target audience of optimal auction theory to all entities in economic networks. We investigate the design of simple and provably near-optimal network auctions via reserve price. Using Bayesian approximation analysis, we provide a simple and explicit form of the reserve price function tailored to the most representative network auction. We aim to balance setting a sufficiently high reserve price to induce high revenue in a successful sale, and attracting more buyers from the network to increase the probability of a successful sale. This reserve price function preserves incentive compatibility for network auctions, allowing the seller to extract additional revenue beyond that achieved by the Myerson optimal auction. Specifically, if the seller has $ρ$ direct neighbours in a network of size $n$, this reserve price guarantees a $1-{1 \over ρ}$ approximation to the theoretical upper bound, i.e., the maximum possible revenue from any network of size $n$. This result holds for any size and any structure of the networked market.

econ.TH↗

arXiv2025

Strategyproofness and Monotone Allocation of Auction in Social Networks

Strategyproofness in network auctions requires that bidders not only report their valuations truthfully, but also do their best to invite neighbours from the social network. In contrast to canonical auctions, where the value-monotone allocation in Myerson's Lemma is a cornerstone, a general principle of allocation rules for strategyproof network auctions is still missing. We show that, due to the absence of such a principle, even extensions to multi-unit network auctions with single-unit demand present unexpected difficulties, and all pioneering researches fail to be strategyproof. For the first time in this field, we identify two categories of monotone allocation rules on networks: Invitation-Depressed Monotonicity (ID-MON) and Invitation-Promoted Monotonicity (IP-MON). They encompass all existing allocation rules of network auctions as specific instances. For any given ID-MON or IP-MON allocation rule, we characterize the existence and sufficient conditions for the strategyproof payment rules, and show that among all such payment rules, the revenue-maximizing one exists and is computationally feasible. With these results, the obstacle of combinatorial network auction with single-minded bidders is now resolved.

cs.GT↗

arXiv2025

Beyond Task-Specific Reasoning: A Unified Conditional Generative Framework for Abstract Visual Reasoning

Abstract visual reasoning (AVR) enables humans to quickly discover and generalize abstract rules to new scenarios. Designing intelligent systems with human-like AVR abilities has been a long-standing topic in the artificial intelligence community. Deep AVR solvers have recently achieved remarkable success in various AVR tasks. However, they usually use task-specific designs or parameters in different tasks. In such a paradigm, solving new tasks often means retraining the model, and sometimes retuning the model architectures, which increases the cost of solving AVR problems. In contrast to task-specific approaches, this paper proposes a novel Unified Conditional Generative Solver (UCGS), aiming to address multiple AVR tasks in a unified framework. First, we prove that some well-known AVR tasks can be reformulated as the problem of estimating the predictability of target images in problem panels. Then, we illustrate that, under the proposed framework, training one conditional generative model can solve various AVR tasks. The experiments show that with a single round of multi-task training, UCGS demonstrates abstract reasoning ability across various AVR tasks. Especially, UCGS exhibits the ability of zero-shot reasoning, enabling it to perform abstract reasoning on problems from unseen AVR tasks in the testing phase.

cs.CV↗

arXiv2025

ClinKD: Cross-Modal Clinical Knowledge Distiller For Multi-Task Medical Images

Medical Visual Question Answering (Med-VQA) represents a critical and challenging subtask within the general VQA domain. Despite significant advancements in general VQA, multimodal large language models (MLLMs) still exhibit substantial limitations when handling multi-task VQA scenarios. These limitations manifest through erroneous spatial localization and misinterpretation of medical images, which primarily arise from two fundamental issues: inadequate image-text alignment and insufficient domain-specified knowledge for medical applications. To address these issues, we introduce the Cross-Modal Clinical Knowledge Distiller (ClinKD), an innovative framework designed to enhance image-text alignment and establish more effective medical knowledge transformation mechanisms, which enables MLLMs to perform better even when lacking prior medical knowledge. Our extensive experimental evaluations demonstrate that the ClinKD achieves state-of-the-art performance on several datasets which are challenging for Med-VQA task. The results indicate that our approach not only significantly improves image-text alignment but also effectively enables MLLMs to adapt to the medical knowledge. The source code for ClinKD is available at: https://github.com/overloadedHenry/ClinKD.

cs.CV↗

arXiv2025

UAV-Assisted Integrated Communication and Over-the-Air Computation with Interference Awareness

Over the air computation (AirComp) is a promising technique that addresses big data collection and fast wireless data aggregation. However, in a network where wireless communication and AirComp coexist, mutual interference becomes a critical challenge. In this paper, we propose to employ an unmanned aerial vehicle (UAV) to enable integrated communication and AirComp, where we capitalize on UAV mobility with alleviated interference for performance enhancement. Particularly, we aim to maximize the sum of user transmission rate with the guaranteed AirComp accuracy requirement, where we jointly optimize the transmission strategy, signal normalizing factor, scheduling strategy, and UAV trajectory. We decouple the formulated problem into two layers where the outer layer is for UAV trajectory and scheduling, and the inner layer is for transmission and computation. Then, we solve the inner layer problem through alternating optimization, and the outer layer is solved through soft actor critic based deep reinforcement learning. Simulation results show the convergence of the proposed learning process and also demonstrate the performance superiority of our proposal as compared with the baselines in various situations.

eess.SP↗

arXiv2025

Gradient Purification: Defense Against Poisoning Attack in Decentralized Federated Learning

Decentralized federated learning (DFL) is inherently vulnerable to data poisoning attacks, as malicious clients can transmit manipulated gradients to neighboring clients. Existing defense methods either reject suspicious gradients per iteration or restart DFL aggregation after excluding all malicious clients. They all neglect the potential benefits that may exist within contributions from malicious clients. In this paper, we propose a novel gradient purification defense, termed GPD, to defend against data poisoning attacks in DFL. It aims to separately mitigate the harm in gradients and retain benefits embedded in model weights, thereby enhancing overall model accuracy. For each benign client in GPD, a recording variable is designed to track historically aggregated gradients from one of its neighbors. It allows benign clients to precisely detect malicious neighbors and mitigate all aggregated malicious gradients at once. Upon mitigation, benign clients optimize model weights using purified gradients. This optimization not only retains previously beneficial components from malicious clients but also exploits canonical contributions from benign clients. We analyze the convergence of GPD, as well as its ability to harvest high accuracy. Extensive experiments demonstrate that, GPD is capable of mitigating data poisoning attacks under both iid and non-iid data distributions. It also significantly outperforms state-of-the-art defense methods in terms of model accuracy.

cs.LG↗

arXiv2025

M$^3$-Med: A Benchmark for Multi-lingual, Multi-modal, and Multi-hop Reasoning in Medical Instructional Video Understanding

With the rapid progress of artificial intelligence (AI) in multi-modal understanding, there is increasing potential for video comprehension technologies to support professional domains such as medical education. However, existing benchmarks suffer from two primary limitations: (1) Linguistic Singularity: they are largely confined to English, neglecting the need for multilingual resources; and (2) Shallow Reasoning: their questions are often designed for surface-level information retrieval, failing to properly assess deep multi-modal integration. To address these limitations, we present M3-Med, the first benchmark for Multi-lingual, Multi-modal, and Multi-hop reasoning in Medical instructional video understanding. M3-Med consists of medical questions paired with corresponding video segments, annotated by a team of medical experts. A key innovation of M3-Med is its multi-hop reasoning task, which requires a model to first locate a key entity in the text, then find corresponding visual evidence in the video, and finally synthesize information across both modalities to derive the answer. This design moves beyond simple text matching and poses a substantial challenge to a model's deep cross-modal understanding capabilities. We define two tasks: Temporal Answer Grounding in Single Video (TAGSV) and Temporal Answer Grounding in Video Corpus (TAGVC). We evaluated several state-of-the-art models and Large Language Models (LLMs) on M3-Med. The results reveal a significant performance gap between all models and human experts, especially on the complex multi-hop questions where model performance drops sharply. M3-Med effectively highlights the current limitations of AI models in deep cross-modal reasoning within specialized domains and provides a new direction for future research.

cs.CV↗