arXiv subjects

Qian Zhang

Publications and source records attributed to Qian Zhang.

At least 145 records · Page 8Linked to original sources

arXiv2025

VIL2C: Value-of-Information Aware Low-Latency Communication for Multi-Agent Reinforcement Learning

Inter-agent communication serves as an effective mechanism for enhancing performance in collaborative multi-agent reinforcement learning(MARL) systems. However, the inherent communication latency in practical systems induces both action decision delays and outdated information sharing, impeding MARL performance gains, particularly in time-critical applications like autonomous driving. In this work, we propose a Value-of-Information aware Low-latency Communication(VIL2C) scheme that proactively adjusts the latency distribution to mitigate its effects in MARL systems. Specifically, we define a Value of Information (VOI) metric to quantify the importance of delayed message transmission based on each delayed message's importance. Moreover, we propose a progressive message reception mechanism to adaptively adjust the reception duration based on received messages. We derive the optimized VoI aware resource allocation and theoretically prove the performance advantage of the proposed VIL2C scheme. Extensive experiments demonstrate that VIL2C outperforms existing approaches under various communication conditions. These gains are attributed to the low-latency transmission of high-VoI messages via resource allocation and the elimination of unnecessary waiting periods via adaptive reception duration.

cs.MA↗

arXiv2025

ResAD: Normalized Residual Trajectory Modeling for End-to-End Autonomous Driving

End-to-end autonomous driving (E2EAD) systems, which learn to predict future trajectories directly from sensor data, are fundamentally challenged by the inherent spatio-temporal imbalance of trajectory data. This imbalance creates a significant optimization burden, causing models to learn spurious correlations instead of robust driving logic, while also prioritizing uncertain, distant predictions, thereby compromising immediate safety. To address these issues, we propose ResAD, a novel Normalized Residual Trajectory Modeling framework. Instead of predicting the future trajectory directly, our approach reframes and simplifies the learning task by predicting the residual deviation from a deterministic inertial reference. This inertial reference serves as a strong physical prior, compelling the model to move beyond simple pattern-matching and instead focus its capacity on learning the necessary, context-driven deviations (e.g., traffic rules, obstacles) from this default, inertially-guided path. To mitigate the optimization imbalance caused by uncertain, long-term horizons, ResAD further incorporates Point-wise Normalization of the predicted residual. This technique re-weights the optimization objective, preventing large-magnitude errors associated with distant, uncertain waypoints from dominating the learning signal. On the NAVSIM v1 and v2 benchmarks, ResAD achieves state-of-the-art results of 88.8 PDMS and 85.5 EPDMS with only two denoising steps, demonstrating that ResAD significantly simplifies the learning task and improves planning performance. The code will be released to facilitate further research.

cs.CV↗

arXiv2025

Hybrid renormalization for distribution amplitude of a light baryon in large momentum effective theory

Lightcone distribution amplitudes for a light baryon can be extracted through the simulation of the quasi-distribution amplitudes (quasi-DAs) on the lattice. We implement the hybrid renormalization for the quasi DAs of light baryons. Lattice simulations are performed using $N_f = 2+1$ stout-smeared clover fermions and a tree-level Symanzik-improved gauge action, with three lattice spacings of ${0.105, 0.077, 0.052}$ fm. By analyzing zero-momentum matrix elements for different lattice spacings, we extract the linear divergence associated with the Wilson-line self-energy. Matching to perturbative matrix elements in the $\overline{\text{MS}}$ scheme yields the residual self-renormalization factors. Using these factors, we renormalize the quasi-DAs within the hybrid scheme, which combines self-renormalization at large separations and the ratio scheme at short distances. The renormalized results demonstrate effective cancellation of linear divergences and yield smooth, continuum-like coordinate-space distributions suitable for subsequent Fourier transformation and perturbative matching. These results establish the viability of both self and hybrid renormalization frameworks for light baryon quasi-DAs, providing a robust foundation for LaMET-based determinations of light-cone distribution amplitudes.

hep-lat↗

arXiv2025

UniUltra: Interactive Parameter-Efficient SAM2 for Universal Ultrasound Segmentation

The Segment Anything Model 2 (SAM2) demonstrates remarkable universal segmentation capabilities on natural images. However, its performance on ultrasound images is significantly degraded due to domain disparities. This limitation raises two critical challenges: how to efficiently adapt SAM2 to ultrasound imaging while maintaining parameter efficiency, and how to deploy the adapted model effectively in resource-constrained clinical environments. To address these issues, we propose UniUltra for universal ultrasound segmentation. Specifically, we first introduce a novel context-edge hybrid adapter (CH-Adapter) that enhances fine-grained perception across diverse ultrasound imaging modalities while achieving parameter-efficient fine-tuning. To further improve clinical applicability, we develop a deep-supervised knowledge distillation (DSKD) technique that transfers knowledge from the large image encoder of the fine-tuned SAM2 to a super lightweight encoder, substantially reducing computational requirements without compromising performance. Extensive experiments demonstrate that UniUltra outperforms state-of-the-arts with superior generalization capabilities. Notably, our framework achieves competitive performance using only 8.91% of SAM2's parameters during fine-tuning, and the final compressed model reduces the parameter count by 94.08% compared to the original SAM2, making it highly suitable for practical clinical deployment. The source code is available at https://github.com/xq141839/UniUltra.

eess.IV↗

arXiv2025

Sample Complexity of Agnostic Multiclass Classification: Natarajan Dimension Strikes Back

The fundamental theorem of statistical learning states that binary PAC learning is governed by a single parameter -- the Vapnik-Chervonenkis (VC) dimension -- which determines both learnability and sample complexity. Extending this to multiclass classification has long been challenging, since Natarajan's work in the late 80s proposing the Natarajan dimension (Nat) as a natural analogue of VC. Daniely and Shalev-Shwartz (2014) introduced the DS dimension, later shown by Brukhim et al. (2022) to characterize multiclass learnability. Brukhim et al. also showed that Nat and DS can diverge arbitrarily, suggesting that multiclass learning is governed by DS rather than Nat. We show that agnostic multiclass PAC sample complexity is in fact governed by two distinct dimensions. Specifically, we prove nearly tight agnostic sample complexity bounds that, up to log factors, take the form $\frac{DS^{1.5}}ε + \frac{Nat}{ε^2}$ where $ε$ is the excess risk. This bound is tight up to a $\sqrt{DS}$ factor in the first term, nearly matching known $Nat/ε^2$ and $DS/ε$ lower bounds. The first term reflects the DS-controlled regime, while the second shows that the Natarajan dimension still dictates asymptotic behavior for small $ε$. Thus, unlike binary or online classification -- where a single dimension (VC or Littlestone) controls both phenomena -- multiclass learning inherently involves two structural parameters. Our technical approach departs from traditional agnostic learning methods based on uniform convergence or reductions to realizable cases. A key ingredient is a novel online procedure based on a self-adaptive multiplicative-weights algorithm performing a label-space reduction, which may be of independent interest.

cs.LG↗

arXiv2025

Key Decision-Makers in Multi-Agent Debates: Who Holds the Power?

Recent studies on LLM agent scaling have highlighted the potential of Multi-Agent Debate (MAD) to enhance reasoning abilities. However, the critical aspect of role allocation strategies remains underexplored. In this study, we demonstrate that allocating roles with differing viewpoints to specific positions significantly impacts MAD's performance in reasoning tasks. Specifically, we find a novel role allocation strategy, "Truth Last", which can improve MAD performance by up to 22% in reasoning tasks. To address the issue of unknown truth in practical applications, we propose the Multi-Agent Debate Consistency (MADC) strategy, which systematically simulates and optimizes its core mechanisms. MADC incorporates path consistency to assess agreement among independent roles, simulating the role with the highest consistency score as the truth. We validated MADC across a range of LLMs (9 models), including the DeepSeek-R1 Distilled Models, on challenging reasoning tasks. MADC consistently demonstrated advanced performance, effectively overcoming MAD's performance bottlenecks and providing a crucial pathway for further improvements in LLM agent scaling.

cs.AI↗

arXiv2025

A pressure-robust and parameter-free enriched Galerkin method for the Navier-Stokes equations of rotational form

In this paper, we develop a novel enriched Galerkin (EG) method for the steady incompressible Navier-Stokes equations in rotational form, which is both pressure-robust and parameter-free. The EG space employed here, originally proposed in [1], differs from traditional EG methods: it enriches the first-order continuous Galerkin (CG) space with piecewise constants along edges in two dimensions or on faces in three dimensions, rather than with elementwise polynomials. Within this framework, the gradient and divergence are modified to incorporate the edge/face enrichment, while the curl remains applied only to the CG component, an inherent feature that makes the space particularly suitable for the rotational form. The proposed EG method achieves pressure robustness through a velocity reconstruction operator. We establish existence, uniqueness under a small-data assumption, and convergence of the method, and confirm its effectiveness by numerical experiments.

math.NA↗

arXiv2025

ComDrive: Comfort-Oriented End-to-End Autonomous Driving

We propose ComDrive: the first comfort-oriented end-to-end autonomous driving system to generate temporally consistent and comfortable trajectories. Recent studies have demonstrated that imitation learning-based planners and learning-based trajectory scorers can effectively generate and select safety trajectories that closely mimic expert demonstrations. However, such trajectory planners and scorers face the challenge of generating temporally inconsistent and uncomfortable trajectories. To address these issues, ComDrive first extracts 3D spatial representations through sparse perception, which then serves as conditional inputs. These inputs are used by a Conditional Denoising Diffusion Probabilistic Model (DDPM)-based motion planner to generate temporally consistent multi-modal trajectories. A dual-stream adaptive trajectory scorer subsequently selects the most comfortable trajectory from these candidates to control the vehicle. Experiments demonstrate that ComDrive achieves state-of-the-art performance in both comfort and safety, outperforming UniAD by 17% in driving comfort and reducing collision rates by 25% compared to SparseDrive. More results are available on our project page: https://jmwang0117.github.io/ComDrive/.

cs.CV↗

arXiv2025

RAD: Training an End-to-End Driving Policy via Large-Scale 3DGS-based Reinforcement Learning

Existing end-to-end autonomous driving (AD) algorithms typically follow the Imitation Learning (IL) paradigm, which faces challenges such as causal confusion and an open-loop gap. In this work, we propose RAD, a 3DGS-based closed-loop Reinforcement Learning (RL) framework for end-to-end Autonomous Driving. By leveraging 3DGS techniques, we construct a photorealistic digital replica of the real physical world, enabling the AD policy to extensively explore the state space and learn to handle out-of-distribution scenarios through large-scale trial and error. To enhance safety, we design specialized rewards to guide the policy in effectively responding to safety-critical events and understanding real-world causal relationships. To better align with human driving behavior, we incorporate IL into RL training as a regularization term. We introduce a closed-loop evaluation benchmark consisting of diverse, previously unseen 3DGS environments. Compared to IL-based methods, RAD achieves stronger performance in most closed-loop metrics, particularly exhibiting a 3x lower collision rate. Abundant closed-loop results are presented in the supplementary material. Code is available at https://github.com/hustvl/RAD for facilitating future research.

cs.CV↗

arXiv2025

Hummingbird: A Smaller and Faster Large Language Model Accelerator on Embedded FPGA

Deploying large language models (LLMs) on embedded devices remains a significant research challenge due to the high computational and memory demands of LLMs and the limited hardware resources available in such environments. While embedded FPGAs have demonstrated performance and energy efficiency in traditional deep neural networks, their potential for LLM inference remains largely unexplored. Recent efforts to deploy LLMs on FPGAs have primarily relied on large, expensive cloud-grade hardware and have only shown promising results on relatively small LLMs, limiting their real-world applicability. In this work, we present Hummingbird, a novel FPGA accelerator designed specifically for LLM inference on embedded FPGAs. Hummingbird is smaller, targeting embedded FPGAs such as the KV260 and ZCU104 with 67% LUT, 39% DSP, and 42% power savings over existing research. Hummingbird is stronger, targeting LLaMA3-8B and supporting longer contexts, overcoming the typical 4GB memory constraint of embedded FPGAs through offloading strategies. Finally, Hummingbird is faste, achieving 4.8 tokens/s and 8.6 tokens/s for LLaMA3-8B on the KV260 and ZCU104 respectively, with 93-94% model bandwidth utilization, outperforming the prior 4.9 token/s for LLaMA2-7B with 84% bandwidth utilization baseline. We further demonstrate the viability of industrial applications by deploying Hummingbird on a cost-optimized Spartan UltraScale FPGA, paving the way for affordable LLM solutions at the edge.

cs.AR↗

arXiv2025

UniUIR: Considering Underwater Image Restoration as An All-in-One Learner

Existing underwater image restoration (UIR) methods generally only handle color distortion or jointly address color and haze issues, but they often overlook the more complex degradations that can occur in underwater scenes. To address this limitation, we propose a Universal Underwater Image Restoration method, termed as UniUIR, considering the complex scenario of real-world underwater mixed distortions as an all-in-one manner. To decouple degradation-specific issues and explore the inter-correlations among various degradations in UIR task, we designed the Mamba Mixture-of-Experts module. This module enables each expert to identify distinct types of degradation and collaboratively extract task-specific priors while maintaining global feature representation based on linear complexity. Building upon this foundation, to enhance degradation representation and address the task conflicts that arise when handling multiple types of degradation, we introduce the spatial-frequency prior generator. This module extracts degradation prior information in both spatial and frequency domains, and adaptively selects the most appropriate task-specific prompts based on image content, thereby improving the accuracy of image restoration. Finally, to more effectively address complex, region-dependent distortions in UIR task, we incorporate depth information derived from a large-scale pre-trained depth prediction model, thereby enabling the network to perceive and leverage depth variations across different image regions to handle localized degradation. Extensive experiments demonstrate that UniUIR can produce more attractive results across qualitative and quantitative comparisons, and shows strong generalization than state-of-the-art methods.

cs.CV↗

arXiv2025

LadderMoE: Ladder-Side Mixture of Experts Adapters for Bronze Inscription Recognition

Bronze inscriptions (BI), engraved on ritual vessels, constitute a crucial stage of early Chinese writing and provide indispensable evidence for archaeological and historical studies. However, automatic BI recognition remains difficult due to severe visual degradation, multi-domain variability across photographs, rubbings, and tracings, and an extremely long-tailed character distribution. To address these challenges, we curate a large-scale BI dataset comprising 22454 full-page images and 198598 annotated characters spanning 6658 unique categories, enabling robust cross-domain evaluation. Building on this resource, we develop a two-stage detection-recognition pipeline that first localizes inscriptions and then transcribes individual characters. To handle heterogeneous domains and rare classes, we equip the pipeline with LadderMoE, which augments a pretrained CLIP encoder with ladder-style MoE adapters, enabling dynamic expert specialization and stronger robustness. Comprehensive experiments on single-character and full-page recognition tasks demonstrate that our method substantially outperforms state-of-the-art scene text recognition baselines, achieving superior accuracy across head, mid, and tail categories as well as all acquisition modalities. These results establish a strong foundation for bronze inscription recognition and downstream archaeological analysis.

cs.CV↗

arXiv2025

GoalFlow: Goal-Driven Flow Matching for Multimodal Trajectories Generation in End-to-End Autonomous Driving

We propose GoalFlow, an end-to-end autonomous driving method for generating high-quality multimodal trajectories. In autonomous driving scenarios, there is rarely a single suitable trajectory. Recent methods have increasingly focused on modeling multimodal trajectory distributions. However, they suffer from trajectory selection complexity and reduced trajectory quality due to high trajectory divergence and inconsistencies between guidance and scene information. To address these issues, we introduce GoalFlow, a novel method that effectively constrains the generative process to produce high-quality, multimodal trajectories. To resolve the trajectory divergence problem inherent in diffusion-based methods, GoalFlow constrains the generated trajectories by introducing a goal point. GoalFlow establishes a novel scoring mechanism that selects the most appropriate goal point from the candidate points based on scene information. Furthermore, GoalFlow employs an efficient generative method, Flow Matching, to generate multimodal trajectories, and incorporates a refined scoring mechanism to select the optimal trajectory from the candidates. Our experimental results, validated on the Navsim\cite{Dauner2024_navsim}, demonstrate that GoalFlow achieves state-of-the-art performance, delivering robust multimodal trajectories for autonomous driving. GoalFlow achieved PDMS of 90.3, significantly surpassing other methods. Compared with other diffusion-policy-based methods, our approach requires only a single denoising step to obtain excellent performance. The code is available at https://github.com/YvanYin/GoalFlow.

cs.CV↗

arXiv2025

SafeMind: Benchmarking and Mitigating Safety Risks in Embodied LLM Agents

Embodied agents powered by large language models (LLMs) inherit advanced planning capabilities; however, their direct interaction with the physical world exposes them to safety vulnerabilities. In this work, we identify four key reasoning stages where hazards may arise: Task Understanding, Environment Perception, High-Level Plan Generation, and Low-Level Action Generation. We further formalize three orthogonal safety constraint types (Factual, Causal, and Temporal) to systematically characterize potential safety violations. Building on this risk model, we present SafeMindBench, a multimodal benchmark with 5,558 samples spanning four task categories (Instr-Risk, Env-Risk, Order-Fix, Req-Align) across high-risk scenarios such as sabotage, harm, privacy, and illegal behavior. Extensive experiments on SafeMindBench reveal that leading LLMs (e.g., GPT-4o) and widely used embodied agents remain susceptible to safety-critical failures. To address this challenge, we introduce SafeMindAgent, a modular Planner-Executor architecture integrated with three cascaded safety modules, which incorporate safety constraints into the reasoning process. Results show that SafeMindAgent significantly improves safety rate over strong baselines while maintaining comparable task completion. Together, SafeMindBench and SafeMindAgent provide both a rigorous evaluation suite and a practical solution that advance the systematic study and mitigation of safety risks in embodied LLM agents.

cs.AI↗

arXiv2025

High pressure lattice dynamics study of few layer-$α$-In$_2$Se$_3$

Few-layer $α$-In$_2$Se$_3$ has been studied under pressure using Raman spectroscopy in a diamond anvil cell up to 60 GPa (at room temperature). A combination of AFM and Raman was used to estimate the thickness of the specimens. While few-layer $α$-In$_2$Se$_3$ shows identical structural evolution with the one of the bulk powder-like form of $α$-In$_2$Se$_3$ ( $α$ $\rightarrow$ $β^{'}$ $\rightarrow$ IV ), an abrupt $β^{'}$ $\rightarrow$ IV phase transition (at 45 GPa) was observed, in contrast with the case of the bulk specimen where the two phases coexist over a wide pressure range. This is attributed to the difference in specimens morphology, $i.e.$ single crystal and powder in the case of few-layer and bulk $α$-In$_2$Se$_3$, respectively. This study documents the significance of specimens morphology on the observed pressure-induced phase transitions. The methodology developed in this study for performing high-pressure Raman measurements can be applied to other nanodimensional layered materials.

cond-mat.mtrl-sci↗

arXiv2025

Informative Text-Image Alignment for Visual Affordance Learning with Foundation Models

Visual affordance learning is crucial for robots to understand and interact effectively with the physical world. Recent advances in this field attempt to leverage pre-trained knowledge of vision-language foundation models to learn affordance properties with limited training data, providing a novel paradigm for visual affordance learning. However, these methods overlook the significance of maintaining feature alignment between visual images and language descriptions for identifying affordance areas with textual guidance, and thus may lead to suboptimal results. In this paper, we present an informative framework for text-guided affordance learning, which involves information-based constraints to achieve text-image alignment at feature level. Specifically, we design an affordance mutual information constraint that helps learn appropriate textual prompts and task-oriented visual features simultaneously by maximizing the mutual information between the features of the affordance areas in the input images and the corresponding textual prompts. In addition, we propose an object-level information constraint that maximizes the mutual information between the visual features of a given object and the text features of the category it belongs to. This enables the model to capture high-quality representations for the object, providing more reliable semantic priors for identifying affordance regions. Experimental results on the AGD20K dataset show that the proposed method outperforms existing approaches and achieves the new state-of-the-art in one-shot affordance learning.

cs.CV↗

arXiv2025

Robust Vision-Language Models via Tensor Decomposition: A Defense Against Adversarial Attacks

Vision language models (VLMs) excel in multimodal understanding but are prone to adversarial attacks. Existing defenses often demand costly retraining or significant architecture changes. We introduce a lightweight defense using tensor decomposition suitable for any pre-trained VLM, requiring no retraining. By decomposing and reconstructing vision encoder representations, it filters adversarial noise while preserving meaning. Experiments with CLIP on COCO and Flickr30K show improved robustness. On Flickr30K, it restores 12.3\% performance lost to attacks, raising Recall@1 accuracy from 7.5\% to 19.8\%. On COCO, it recovers 8.1\% performance, improving accuracy from 3.8\% to 11.9\%. Analysis shows Tensor Train decomposition with low rank (8-32) and low residual strength ($α=0.1-0.2$) is optimal. This method is a practical, plug-and-play solution with minimal overhead for existing VLMs.

cs.CV↗

arXiv2025

Boost 3D Reconstruction using Diffusion-based Monocular Camera Calibration

In this paper, we present DM-Calib, a diffusion-based approach for estimating pinhole camera intrinsic parameters from a single input image. Monocular camera calibration is essential for many 3D vision tasks. However, most existing methods depend on handcrafted assumptions or are constrained by limited training data, resulting in poor generalization across diverse real-world images. Recent advancements in stable diffusion models, trained on massive data, have shown the ability to generate high-quality images with varied characteristics. Emerging evidence indicates that these models implicitly capture the relationship between camera focal length and image content. Building on this insight, we explore how to leverage the powerful priors of diffusion models for monocular pinhole camera calibration. Specifically, we introduce a new image-based representation, termed Camera Image, which losslessly encodes the numerical camera intrinsics and integrates seamlessly with the diffusion framework. Using this representation, we reformulate the problem of estimating camera intrinsics as the generation of a dense Camera Image conditioned on an input image. By fine-tuning a stable diffusion model to generate a Camera Image from a single RGB input, we can extract camera intrinsics via a RANSAC operation. We further demonstrate that our monocular calibration method enhances performance across various 3D tasks, including zero-shot metric depth estimation, 3D metrology, pose estimation and sparse-view reconstruction. Extensive experiments on multiple public datasets show that our approach significantly outperforms baselines and provides broad benefits to 3D vision tasks.

cs.CV↗