arXiv subjects

Bin Chen

Publications and source records attributed to Bin Chen.

At least 181 records · Page 10Linked to original sources

arXiv2026

Generalization Bounds for Transformer Channel Decoders

Transformer channel decoders, such as the Error Correction Code Transformer (ECCT), have shown strong empirical performance in channel decoding, yet their generalization behavior remains theoretically unclear. This paper studies the generalization performance of ECCT from a learning-theoretic perspective. By establishing a connection between multiplicative noise estimation errors and bit-error-rate (BER), we derive an upper bound on the generalization gap via bit-wise Rademacher complexity. The resulting bound characterizes the dependence on code length, model parameters, and training set size, and applies to both single-layer and multi-layer ECCTs. We further show that parity-check-based masked attention induces sparsity that reduces the covering number, leading to a tighter generalization bound. To the best of our knowledge, this work provides the first theoretical generalization guarantees for this class of decoders.

cs.IT↗

arXiv2026

GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

We present GLM-4.1V-Thinking, GLM-4.5V, and GLM-4.6V, a family of vision-language models (VLMs) designed to advance general-purpose multimodal understanding and reasoning. In this report, we share our key findings in the development of the reasoning-centric training framework. We first develop a capable vision foundation model with significant potential through large-scale pre-training, which arguably sets the upper bound for the final performance. We then propose Reinforcement Learning with Curriculum Sampling (RLCS) to unlock the full potential of the model, leading to comprehensive capability enhancement across a diverse range of tasks, including STEM problem solving, video understanding, content recognition, coding, grounding, GUI-based agents, and long document interpretation. In a comprehensive evaluation across 42 public benchmarks, GLM-4.5V achieves state-of-the-art performance on nearly all tasks among open-source models of similar size, and demonstrates competitive or even superior results compared to closed-source models such as Gemini-2.5-Flash on challenging tasks including Coding and GUI Agents. Meanwhile, the smaller GLM-4.1V-9B-Thinking remains highly competitive-achieving superior results to the much larger Qwen2.5-VL-72B on 29 benchmarks. We open-source both GLM-4.1V-9B-Thinking and GLM-4.5V. We further introduce the GLM-4.6V series, open-source multimodal models with native tool use and a 128K context window. A brief overview is available at https://z.ai/blog/glm-4.6v. Code, models and more information are released at https://github.com/zai-org/GLM-V.

cs.CV↗

arXiv2025

Splatwizard: A Benchmark Toolkit for 3D Gaussian Splatting Compression

The recent advent of 3D Gaussian Splatting (3DGS) has marked a significant breakthrough in real-time novel view synthesis. However, the rapid proliferation of 3DGS-based algorithms has created a pressing need for standardized and comprehensive evaluation tools, especially for compression task. Existing benchmarks often lack the specific metrics necessary to holistically assess the unique characteristics of different methods, such as rendering speed, rate distortion trade-offs memory efficiency, and geometric accuracy. To address this gap, we introduce Splatwizard, a unified benchmark toolkit designed specifically for benchmarking 3DGS compression models. Splatwizard provides an easy-to-use framework to implement new 3DGS compression model and utilize state-of-the-art techniques proposed by previous work. Besides, an integrated pipeline that automates the calculation of key performance indicators, including image-based quality metrics, chamfer distance of reconstruct mesh, rendering frame rates, and computational resource consumption is included in the framework as well. Code is available at https://github.com/splatwizard/splatwizard

cs.CV↗

arXiv2025

Entropy-Based Evidence for Bitcoin's Discrete Time Mechanism

Bitcoin derives a verifiable temporal order from probabilistic block discovery and cumulative proof-of-work rather than from a trusted global clock. We show that block arrivals exhibit stable exponential behavior across difficulty epochs, and that the proof-of-work process maintains a high-entropy search state that collapses discretely upon the discovery of a valid block. This entropy-based interpretation provides a mechanistic account of Bitcoin's non-continuous temporal structure. In a distributed network, however, entropy collapse is not completed instantaneously across all participants. Using empirical observations of temporary forks, we show that collapse completion unfolds over a finite propagation-bounded interval, while remaining rapid in practice.

cs.IT↗

arXiv2025

One Perturbation is Enough: On Generating Universal Adversarial Perturbations against Vision-Language Pre-training Models

Vision-Language Pre-training (VLP) models have exhibited unprecedented capability in many applications by taking full advantage of the multimodal alignment. However, previous studies have shown they are vulnerable to maliciously crafted adversarial samples. Despite recent success, these methods are generally instance-specific and require generating perturbations for each input sample. In this paper, we reveal that VLP models are also vulnerable to the instance-agnostic universal adversarial perturbation (UAP). Specifically, we design a novel Contrastive-training Perturbation Generator with Cross-modal conditions (C-PGC) to achieve the attack. In light that the pivotal multimodal alignment is achieved through the advanced contrastive learning technique, we devise to turn this powerful weapon against themselves, i.e., employ a malicious version of contrastive learning to train the C-PGC based on our carefully crafted positive and negative image-text pairs for essentially destroying the alignment relationship learned by VLP models. Besides, C-PGC fully utilizes the characteristics of Vision-and-Language (V+L) scenarios by incorporating both unimodal and cross-modal information as effective guidance. Extensive experiments show that C-PGC successfully forces adversarial samples to move away from their original area in the VLP model's feature space, thus essentially enhancing attacks across various victim models and V+L tasks. The GitHub repository is available at https://github.com/ffhibnese/CPGC_VLP_Universal_Attacks.

cs.CV↗

arXiv2025

Searches for Prompt Low-Frequency Radio Counterparts to Gravitational Wave Event S250206dm with the OVRO-LWA Time Machine

We report on a search for prompt, low-frequency radio emission from the gravitational-wave (GW) merger S250206dm using the Owens Valley Radio Observatory Long Wavelength Array (OVRO-LWA). Early alerts favored a neutron-star-containing merger, making this a compelling target. Motivated by theoretical predictions of coherent radio bursts from mergers involving a neutron star, we utilized the OVRO-LWA Time Machine system to analyze voltage data recorded around the time of the event. The Time Machine is a two-stage voltage buffer and processing pipeline that continuously buffers raw data from all antennas across the array's nearly full-hemisphere instantaneous field of view, enabling retrospective beamforming, dedispersion, and fast-transient candidate identification. For this event, we analyzed a 30-minute interval beginning 3.5 minutes after the merger, which included two minutes of pre-alert data recovered by the ring buffer. We searched the 50% localization probability region with millisecond time resolution in the 69-86 MHz frequency band. No radio counterpart was detected above a 7-sigma fluence detection threshold of ~150 Jy ms. Using Bayesian analysis, we place a 95% confidence upper limit on the source luminosity of L95 = 4 x 10^41 erg s^-1. These constraints start to probe the bright end of the coherent-emission parameter space predicted by jet-ISM shock processes, magnetar and blitzar-like mechanisms, and recent simulation-based scenarios for neutron-star-containing mergers. This study presents the first sensitive, large-area, millisecond-timescale search for prompt low-frequency radio emission from a GW merger with the OVRO-LWA, establishing a framework in which about ten additional events will yield stringent population-level constraints.

astro-ph.HE↗

arXiv2025

Integrable Sigma Models and Universal Root $T\bar{T}$ Deformation via Courant-Hilbert Approach

We develop a unified Courant--Hilbert framework for constructing two-dimensional integrable sigma models deformed by two couplings: a marginal one $γ$ and an irrelevant one $λ$. The integrability condition is encoded in a nonlinear partial differential equation (PDE) for two invariants $(P_1, P_2)$, whose general solution could be expressed through an arbitrary generating function $\ell(τ)$. This formulation encompasses and extends known models, such as ModMax and Born-Infeld, while introducing new classes of solvable models with closed-form Lagrangians, including those with logarithmic and $q$-deformations. All resulting theories obey a universal root-$T\overline{T}$ flow equation, consistent under dimensional reduction from four-dimensional duality-invariant electrodynamics. Using perturbative expansions, we recover ModMax in the free limit, determine the $γ$-dependence of the coupling functions, and show how different flow equations, including a single-trace form, naturally emerge. Our results reveal deep structural connections between self-duality, integrability, and deformation dynamics across different dimensions.

hep-th↗

arXiv2025

Experimental Demonstration and Transformation Mechanism of Quenchable Two-dimensional Diamond

Two-dimensional (2D) diamond has aroused tremendous interest in nanoelectronics and optoelectronics, owing to its superior properties and flexible characteristics compared to bulk diamond. Despite significant efforts, great challenges lie in the experimental synthesis and transformation conditions of 2D diamond. Herein, we have demonstrated the experimental preparation of high quality 2D diamond with controlled thickness and distinguished properties, realized by laser-heating few-layer graphene in diamond anvil cell. The quenched 2D diamond exhibited narrow T2g Raman peak (linewidth ~3.6 cm-1) and intense photoluminescence of SiV- (linewidth ~6.1 nm) and NV0 centers. In terms of transformation mechanism, atomic structures of hybrid phase interfaces suggested that the intermediate rhombohedral phase subtly mediate hexagonal graphite to cubic diamond transition. Furthermore, the tunable optical bandgap and thermal stability of 2D diamond sensitively depend on its sp3 concentration. We believe our results can shed light on the structural design and preparation of many carbon allotropes and further uncover the underlying transition mechanism.

cond-mat.mtrl-sci↗

arXiv2025

Grammar-Based Code Representation: Is It a Worthy Pursuit for LLMs?

Grammar serves as a cornerstone in programming languages and software engineering, providing frameworks to define the syntactic space and program structure. Existing research demonstrates the effectiveness of grammar-based code representations in small-scale models, showing their ability to reduce syntax errors and enhance performance. However, as language models scale to the billion level or beyond, syntax-level errors become rare, making it unclear whether grammar information still provides performance benefits. To explore this, we develop a series of billion-scale GrammarCoder models, incorporating grammar rules in the code generation process. Experiments on HumanEval (+) and MBPP (+) demonstrate a notable improvement in code generation accuracy. Further analysis shows that grammar-based representations enhance LLMs' ability to discern subtle code differences, reducing semantic errors caused by minor variations. These findings suggest that grammar-based code representations remain valuable even in billion-scale models, not only by maintaining syntax correctness but also by improving semantic differentiation.

cs.PL↗

arXiv2025

UARE: A Unified Vision-Language Model for Image Quality Assessment, Restoration, and Enhancement

Image quality assessment (IQA) and image restoration are fundamental problems in low-level vision. Although IQA and restoration are closely connected conceptually, most existing work treats them in isolation. Recent advances in unified multimodal understanding-generation models demonstrate promising results and indicate that stronger understanding can improve generative performance. This motivates a single model that unifies IQA and restoration and explicitly studies how IQA can guide restoration, a setting that remains largely underexplored yet highly valuable. In this paper, we propose UARE, to our knowledge the first Unified vision-language model for image quality Assessment, Restoration, and Enhancement. Built on pretrained unified understanding and generation models, we introduce a two-stage training framework. First, a progressive, easy-to-hard schedule expands from single-type distortions to higher-order mixed degradations, enabling UARE to handle multiple degradations. Second, we perform unified fine-tuning of quality understanding and restoration with interleaved text-image data, aligning IQA signals with restoration objectives. Through multi-task co-training, UARE leverages IQA to boost restoration and enhancement performance. Extensive experiments across IQA, restoration, and enhancement tasks demonstrate the effectiveness of UARE. The code and models will be available at https://github.com/lwq20020127/UARE.

cs.CV↗

arXiv2025

Less Is More, but Where? Dynamic Token Compression via LLM-Guided Keyframe Prior

Recent advances in Video Large Language Models (VLLMs) have achieved remarkable video understanding capabilities, yet face critical efficiency bottlenecks due to quadratic computational growth with lengthy visual token sequences of long videos. While existing keyframe sampling methods can improve temporal modeling efficiency, additional computational cost is introduced before feature encoding, and the binary frame selection paradigm is found suboptimal. Therefore, in this work, we propose Dynamic Token compression via LLM-guided Keyframe prior (DyToK), a training-free paradigm that enables dynamic token compression by harnessing VLLMs' inherent attention mechanisms. Our analysis reveals that VLLM attention layers naturally encoding query-conditioned keyframe priors, by which DyToK dynamically adjusts per-frame token retention ratios, prioritizing semantically rich frames while suppressing redundancies. Extensive experiments demonstrate that DyToK achieves state-of-the-art efficiency-accuracy tradeoffs. DyToK shows plug-and-play compatibility with existing compression methods, such as VisionZip and FastV, attaining 4.3x faster inference while preserving accuracy across multiple VLLMs, such as LLaVA-OneVision and Qwen2.5-VL. Code is available at https://github.com/yu-lin-li/DyToK .

cs.CV↗

arXiv2025

A study of the spectrum resource leasing method based on ERC4907 extension

The ERC4907 standard enables rentable Non-Fungible Tokens (NFTs) but is limited to single-user, single-time-slot authorization, which severely limits its applicability and efficiency in decentralized multi-slot scheduling scenarios. To address this limitation, this paper proposes Multi-slot ERC4907 (M-ERC4907) extension method. The M-ERC4907 method introduces novel functionalities to support the batch configuration of multiple time slots and simultaneous authorization of multiple users, thereby effectively eliminating the rigid sequential authorization constraint of ERC4907. The experiment was conducted on the Remix development platform. Experimental results show that the M-ERC4907 method significantly reduces on-chain transactions and overall Gas consumption, leading to enhanced scalability and resource allocation efficiency.

cs.DC↗

arXiv2025

Paths with two blocks in oriented graphs of large minimum semi-degree

Stein (2020) conjectured that for any positive integer $k$, every oriented graph of minimum semi-degree greater than $k/2$ contains every oriented path of length $k$. This conjecture is true for directed paths by a result from Jackson (JGT, 1981). In this paper, we establish the validity of Stein's conjecture specifically for any oriented path with two blocks, where, a block of an oriented path $P$ refers to a maximal directed subpath within $P$.

math.CO↗

arXiv2025

Rank Matters: Understanding and Defending Model Inversion Attacks via Low-Rank Feature Filtering

Model Inversion Attacks (MIAs) pose a significant threat to data privacy by reconstructing sensitive training samples from the knowledge embedded in trained machine learning models. Despite recent progress in enhancing the effectiveness of MIAs across diverse settings, defense strategies have lagged behind, struggling to balance model utility with robustness against increasingly sophisticated attacks. In this work, we propose the ideal inversion error to measure the privacy leakage, and our theoretical and empirical investigations reveals that higher-rank features are inherently more prone to privacy leakage. Motivated by this insight, we propose a lightweight and effective defense strategy based on low-rank feature filtering, which explicitly reduces the attack surface by constraining the dimension of intermediate representations. Extensive experiments across various model architectures and datasets demonstrate that our method consistently outperforms existing defenses, achieving state-of-the-art performance against a wide range of MIAs. Notably, our approach remains effective even in challenging regimes involving high-resolution data and high-capacity models, where prior defenses fail to provide adequate protection. The code is available at https://github.com/Chrisqcwx/LoFt .

cs.CR↗

arXiv2025

Erkang-Diagnosis-1.1 Technical Report

This report provides a detailed introduction to Erkang-Diagnosis-1.1 model, our AI healthcare consulting assistant developed using Alibaba Qwen-3 model. The Erkang model integrates approximately 500GB of high-quality structured medical knowledge, employing a hybrid approach combining enhanced pre-training and retrieval-enhanced generation to create a secure, reliable, and professional AI health advisor. Through 3-5 efficient interaction rounds, Erkang Diagnosis can accurately understand user symptoms, conduct preliminary analysis, and provide valuable diagnostic suggestions and health guidance. Designed to become users intelligent health companions, it empowers primary healthcare and health management. To validate, Erkang-Diagnosis-1.1 leads GPT-4 in terms of comprehensive medical exams.

cs.AI↗

arXiv2025

ICAS: Detecting Training Data from Autoregressive Image Generative Models

Autoregressive image generation has witnessed rapid advancements, with prominent models such as scale-wise visual auto-regression pushing the boundaries of visual synthesis. However, these developments also raise significant concerns regarding data privacy and copyright. In response, training data detection has emerged as a critical task for identifying unauthorized data usage in model training. To better understand the vulnerability of autoregressive image generative models to such detection, we conduct the first study applying membership inference to this domain. Our approach comprises two key components: implicit classification and an adaptive score aggregation strategy. First, we compute the implicit token-wise classification score within the query image. Then we propose an adaptive score aggregation strategy to acquire a final score, which places greater emphasis on the tokens with lower scores. A higher final score indicates that the sample is more likely to be involved in the training set. To validate the effectiveness of our method, we adapt existing detection algorithms originally designed for LLMs to visual autoregressive models. Extensive experiments demonstrate the superiority of our method in both class-conditional and text-to-image scenarios. Moreover, our approach exhibits strong robustness and generalization under various data transformations. Furthermore, sufficient experiments suggest two novel key findings: (1) A linear scaling law on membership inference, exposing the vulnerability of large foundation models. (2) Training data from scale-wise visual autoregressive models is easier to detect than other autoregressive paradigms. Our code is available at https://github.com/Chrisqcwx/ImageAR-MIA.

cs.CV↗

arXiv2025

Character of the highest weight module of BMS algebra realized on codimensional-two boundary

In this paper, we investigate the highest weight representation (HWR) of the three and four-dimensional Bondi-Metzner-Sachs (BMS) algebra realized on the codimension-two boundary of asymptotic flat spacetime (AFS). In such a realization, the action of supertranslation shifts the conformal weight of the highest-weight states. As a result, there is no extra quantum number relating to the supertranslation. We construct the highest-weight BMS modules and compute their characters. We show that the BMS$_3$ highest-weight vacuum character with special value of central charges coincides with the 1-loop partition function of three-dimensional asymptotic flat gravity, up to an overall phase factor ``$i$''. We expect the vacuum character of BMS$_4$ may shed light on the flat holography in four dimensions.

hep-th↗

arXiv2025

Parameter-Free Neural Lens Blur Rendering for High-Fidelity Composites

Consistent and natural camera lens blur is important for seamlessly blending 3D virtual objects into photographed real-scenes. Since lens blur typically varies with scene depth, the placement of virtual objects and their corresponding blur levels significantly affect the visual fidelity of mixed reality compositions. Existing pipelines often rely on camera parameters (e.g., focal length, focus distance, aperture size) and scene depth to compute the circle of confusion (CoC) for realistic lens blur rendering. However, such information is often unavailable to ordinary users, limiting the accessibility and generalizability of these methods. In this work, we propose a novel compositing approach that directly estimates the CoC map from RGB images, bypassing the need for scene depth or camera metadata. The CoC values for virtual objects are inferred through a linear relationship between its signed CoC map and depth, and realistic lens blur is rendered using a neural reblurring network. Our method provides flexible and practical solution for real-world applications. Experimental results demonstrate that our method achieves high-fidelity compositing with realistic defocus effects, outperforming state-of-the-art techniques in both qualitative and quantitative evaluations.

cs.CV↗