arXiv subjects

Shuai Li

Publications and source records attributed to Shuai Li.

At least 127 records · Page 7Linked to original sources

arXiv2025

Transferring Vision-Language-Action Models to Industry Applications: Architectures, Performance, and Challenges

The application of artificial intelligence (AI) in industry is accelerating the shift from traditional automation to intelligent systems with perception and cognition. Vision language-action (VLA) models have been a key paradigm in AI to unify perception, reasoning, and control. Has the performance of the VLA models met the industrial requirements? In this paper, from the perspective of industrial deployment, we compare the performance of existing state-of-the-art VLA models in industrial scenarios and analyze the limitations of VLA models for real-world industrial deployment from the perspectives of data collection and model architecture. The results show that the VLA models retain their ability to perform simple grasping tasks even in industrial settings after fine-tuning. However, there is much room for performance improvement in complex industrial environments, diverse object categories, and high precision placing tasks. Our findings provide practical insight into the adaptability of VLA models for industrial use and highlight the need for task-specific enhancements to improve their robustness, generalization, and precision.

cs.AI↗

arXiv2025

Reinforcement Learning on Pre-Training Data

The growing disparity between the exponential scaling of computational resources and the finite growth of high-quality text data now constrains conventional scaling approaches for large language models (LLMs). To address this challenge, we introduce Reinforcement Learning on Pre-Training data (RLPT), a new training-time scaling paradigm for optimizing LLMs. In contrast to prior approaches that scale training primarily through supervised learning, RLPT enables the policy to autonomously explore meaningful trajectories to learn from pre-training data and improve its capability through reinforcement learning (RL). While existing RL strategies such as reinforcement learning from human feedback (RLHF) and reinforcement learning with verifiable rewards (RLVR) rely on human annotation for reward construction, RLPT eliminates this dependency by deriving reward signals directly from pre-training data. Specifically, it adopts a next-segment reasoning objective, rewarding the policy for accurately predicting subsequent text segments conditioned on the preceding context. This formulation allows RL to be scaled on pre-training data, encouraging the exploration of richer trajectories across broader contexts and thereby fostering more generalizable reasoning skills. Extensive experiments on both general-domain and mathematical reasoning benchmarks across multiple models validate the effectiveness of RLPT. For example, when applied to Qwen3-4B-Base, RLPT yields absolute improvements of $3.0$, $5.1$, $8.1$, $6.0$, $6.6$, and $5.3$ on MMLU, MMLU-Pro, GPQA-Diamond, KOR-Bench, AIME24, and AIME25, respectively. The results further demonstrate favorable scaling behavior, suggesting strong potential for continued gains with more compute. In addition, RLPT provides a solid foundation, extending the reasoning boundaries of LLMs and enhancing RLVR performance.

cs.CL↗

arXiv2025

Multimodal Prompt Decoupling Attack on the Safety Filters in Text-to-Image Models

Text-to-image (T2I) models have been widely applied in generating high-fidelity images across various domains. However, these models may also be abused to produce Not-Safe-for-Work (NSFW) content via jailbreak attacks. Existing jailbreak methods primarily manipulate the textual prompt, leaving potential vulnerabilities in image-based inputs largely unexplored. Moreover, text-based methods face challenges in bypassing the model's safety filters. In response to these limitations, we propose the Multimodal Prompt Decoupling Attack (MPDA), which utilizes image modality to separate the harmful semantic components of the original unsafe prompt. MPDA follows three core steps: firstly, a large language model (LLM) decouples unsafe prompts into pseudo-safe prompts and harmful prompts. The former are seemingly harmless sub-prompts that can bypass filters, while the latter are sub-prompts with unsafe semantics that trigger filters. Subsequently, the LLM rewrites the harmful prompts into natural adversarial prompts to bypass safety filters, which guide the T2I model to modify the base image into an NSFW output. Finally, to ensure semantic consistency between the generated NSFW images and the original unsafe prompts, the visual language model generates image captions, providing a new pathway to guide the LLM in iterative rewriting and refining the generated content.

cs.CV↗

arXiv2025

Learning a Neural Association Network for Self-supervised Multi-Object Tracking

This paper introduces a novel framework to learn data association for multi-object tracking in a self-supervised manner. Fully-supervised learning methods are known to achieve excellent tracking performances, but acquiring identity-level annotations is tedious and time-consuming. Motivated by the fact that in real-world scenarios object motion can be usually represented by a Markov process, we present a novel expectation maximization (EM) algorithm that trains a neural network to associate detections for tracking, without requiring prior knowledge of their temporal correspondences. At the core of our method lies a neural Kalman filter, with an observation model conditioned on associations of detections parameterized by a neural network. Given a batch of frames as input, data associations between detections from adjacent frames are predicted by a neural network followed by a Sinkhorn normalization that determines the assignment probabilities of detections to states. Kalman smoothing is then used to obtain the marginal probability of observations given the inferred states, producing a training objective to maximize this marginal probability using gradient descent. The proposed framework is fully differentiable, allowing the underlying neural model to be trained end-to-end. We evaluate our approach on the challenging MOT17, MOT20, and BDD100K datasets and achieve state-of-the-art results in comparison to self-supervised trackers using public detections.

cs.CV↗

arXiv2025

ALow-Cost Real-Time Framework for Industrial Action Recognition Using Foundation Models

Action recognition (AR) in industrial environments -- particularly for identifying actions and operational gestures -- faces persistent challenges due to high deployment costs, poor cross-scenario generalization, and limited real-time performance. To address these issues, we propose a low-cost real-time framework for industrial action recognition using foundation models, denoted as LRIAR, to enhance recognition accuracy and transferability while minimizing human annotation and computational overhead. The proposed framework constructs an automatically labeled dataset by coupling Grounding DINO with the pretrained BLIP-2 image encoder, enabling efficient and scalable action labeling. Leveraging the constructed dataset, we train YOLOv5 for real-time action detection, and a Vision Transformer (ViT) classifier is deceloped via LoRA-based fine-tuning for action classification. Extensive experiments conducted in real-world industrial settings validate the effectiveness of LRIAR, demonstrating consistent improvements over state-of-the-art methods in recognition accuracy, scenario generalization, and deployment efficiency.

cs.CV↗

arXiv2025

Phonon-scattering-induced quantum linear magnetoresistance up to room temperature

The realization of quantum transport effects at elevated temperatures has long intrigued researchers due to the implications for unveiling novel physics and developing quantum devices. In this work, we report remarkable quantum linear magnetoresistance (LMR) in the Weyl semiconductor tellurium at high temperatures of 40-300 K under strong magnetic fields up to 60 T. At high fields, the Weyl band features a large energy gap between the lowest and first Landau levels, which suppresses thermal excitation and preserves Landau quantization at high temperatures. The LMR is observed as long as majority carriers remain in the lowest Landau level without requiring monochromaticity, allowing it to persist up to room temperature. The inverse relationship between the LMR slope and temperature provides clear evidence that quantum LMR originates from high-temperature phonon scattering in the quantum limit, firstly demonstrating a theoretical prediction made nearly fifty years ago. This study highlights the key role of electron-phonon interaction and reveals an innovative quantum mechanism for achieving high-temperature LMR, fundamentally distinct from previous findings. Our results bridge a gap in the understanding of phonon-mediated quantum-limit physics and establish strong magnetic fields at high temperatures as a promising platform for exploring novel quantum phenomena.

cond-mat.mes-hall↗

arXiv2025

Heavy-tailed Linear Bandits: Adversarial Robustness, Best-of-both-worlds, and Beyond

Heavy-tailed bandits have been extensively studied since the seminal work of \citet{Bubeck2012BanditsWH}. In particular, heavy-tailed linear bandits, enabling efficient learning with both a large number of arms and heavy-tailed noises, have recently attracted significant attention \citep{ShaoYKL18,XueWWZ20,ZhongHYW21,Wang2025heavy,tajdini2025improved}. However, prior studies focus almost exclusively on stochastic regimes, with few exceptions limited to the special case of heavy-tailed multi-armed bandits (MABs) \citep{Huang0H22,ChengZ024,Chen2024uniINF}. In this work, we propose a general framework for adversarial heavy-tailed bandit problems, which performs follow-the-regularized-leader (FTRL) over the loss estimates shifted by a bonus function. Via a delicate setup of the bonus function, we devise the first FTRL-type best-of-both-worlds (BOBW) algorithm for heavy-tailed MABs, which does not require the truncated non-negativity assumption and achieves an $\widetilde{O}(T^{\frac{1}{\varepsilon}})$ worst-case regret in the adversarial regime as well as an $\widetilde{O}(\log T)$ gap-dependent regret in the stochastic regime. We then extend our framework to the linear case, proposing the first algorithm for adversarial heavy-tailed linear bandits with finite arm sets. This algorithm achieves an $\widetilde{O}(d^{\frac{1}{2}}T^{\frac{1}{\varepsilon}})$ regret, matching the best-known worst-case regret bound in stochastic regimes. Moreover, we propose a general data-dependent learning rate, termed \textit{heavy-tailed noise aware stability-penalty matching} (HT-SPM). We prove that HT-SPM guarantees BOBW regret bounds for general heavy-tailed bandit problems once certain conditions are satisfied. By using HT-SPM and, in particular, a variance-reduced linear loss estimator, we obtain the first BOBW result for heavy-tailed linear bandits.

cs.LG↗

arXiv2025

Elucidating Rectified Flow with Deterministic Sampler: Polynomial Discretization Complexity for Multi and One-step Models

Recently, rectified flow (RF)-based models have achieved state-of-the-art performance in many areas for both the multi-step and one-step generation. However, only a few theoretical works analyze the discretization complexity of RF-based models. Existing works either focus on flow-based models with stochastic samplers or establish complexity results that exhibit exponential dependence on problem parameters. In this work, under the realistic bounded support assumption, we prove the first polynomial discretization complexity for multi-step and one-step RF-based models with a deterministic sampler simultaneously. For the multi-step setting, inspired by the predictor-corrector framework of diffusion models, we introduce a Langevin process as a corrector and show that RF-based models can achieve better polynomial discretization complexity than diffusion models. To achieve this result, we conduct a detailed analysis of the RF-based model and explain why it is better than previous popular models, such as variance preserving (VP) and variance exploding (VE)-based models. Based on the observation of multi-step RF-based models, we further provide the first polynomial discretization complexity result for one-step RF-based models, improving upon prior results for one-step diffusion-based models. These findings mark the first step toward theoretically understanding the impressive empirical performance of RF-based models in both multi-step and one-step generation.

cs.LG↗

arXiv2025

Offline-to-Online Reinforcement Learning with Classifier-Free Diffusion Generation

Offline-to-online Reinforcement Learning (O2O RL) aims to perform online fine-tuning on an offline pre-trained policy to minimize costly online interactions. Existing work used offline datasets to generate data that conform to the online data distribution for data augmentation. However, generated data still exhibits a gap with the online data, limiting overall performance. To address this, we propose a new data augmentation approach, Classifier-Free Diffusion Generation (CFDG). Without introducing additional classifier training overhead, CFDG leverages classifier-free guidance diffusion to significantly enhance the generation quality of offline and online data with different distributions. Additionally, it employs a reweighting method to enable more generated data to align with the online data, enhancing performance while maintaining the agent's stability. Experimental results show that CFDG outperforms replaying the two data types or using a standard diffusion model to generate new data. Our method is versatile and can be integrated with existing offline-to-online RL algorithms. By implementing CFDG to popular methods IQL, PEX and APL, we achieve a notable 15% average improvement in empirical performance on the D4RL benchmark such as MuJoCo and AntMaze.

cs.LG↗

arXiv2025

Multiple quantum spin Hall states and topological current divider in Twisted Bilayer WSe$_2$

It has been demonstrated that topological quantum spin Hall (QSH) state exist in twisted bilayers of transition metal dichalcogenides. However, a comprehensive theoretical characterization of the topological edge states remains a topic of interest and an unresolved issue. Here, the topological transport properties of the twisted WSe$_2$ bilayers are investigated. Beyond the conventional single QSH, we identify emergent double and quartuple quantum spin Hall states, hosting two and four pairs of counter-propagating helical edge channels respectively. Furthermore, the charge carriers in these edge states are not localized at edge but rather the high potential point of the moire superlattice boundary, undergoing interlayer transitions and propagating forward continuously. We term these edge states as moire edge states. These edge states can survive in non-magnetic disorder, with the robustness of double QSH states surpassing that of single QSH states. At a twisting angle of 2.45$^\circ$, the transition between the single and double QSH states can be achieved by adjusting the gate on the surface. Based on this, we propose a five-terminal device to as a topological current devider. Our findings provide support for the development of dissipationless spintronics.

cond-mat.mes-hall↗

arXiv2025

Learning to Incentivize: LLM-Empowered Contract for AIGC Offloading in Teleoperation

With the rapid growth in demand for AI-generated content (AIGC), edge AIGC service providers (ASPs) have become indispensable. However, designing incentive mechanisms that motivate ASPs to deliver high-quality AIGC services remains a challenge, especially in the presence of information asymmetry. In this paper, we address bonus design between a teleoperator and an edge ASP when the teleoperator cannot observe the ASP's private settings and chosen actions (diffusion steps). We formulate this as an online learning contract design problem and decompose it into two subproblems: ASP's settings inference and contract derivation. To tackle the NP-hard setting-inference subproblem with unknown variable sizes, we introduce a large language model (LLM)-empowered framework that iteratively refines a naive seed solver using the LLM's domain expertise. Upon obtaining the solution from the LLM-evolved solver, we directly address the contract derivation problem using convex optimization techniques and obtain a near-optimal contract. Simulation results on our Unity-based teleoperation platform show that our method boosts the teleoperator's utility by $5 \sim 40\%$ compared to benchmarks, while preserving positive incentives for the ASP. The code is available at https://github.com/Zijun0819/llm4contract.

cs.CE↗

arXiv2025

The Evolution of Video Anomaly Detection: A Unified Framework from DNN to MLLM

Video anomaly detection (VAD) aims to identify and ground anomalous behaviors or events in videos, serving as a core technology in the fields of intelligent surveillance and public safety. With the advancement of deep learning, the continuous evolution of deep model architectures has driven innovation in VAD methodologies, significantly enhancing feature representation and scene adaptability, thereby improving algorithm generalization and expanding application boundaries. More importantly, the rapid development of multi-modal large language (MLLMs) and large language models (LLMs) has introduced new opportunities and challenges to the VAD field. Under the support of MLLMs and LLMs, VAD has undergone significant transformations in terms of data annotation, input modalities, model architectures, and task objectives. The surge in publications and the evolution of tasks have created an urgent need for systematic reviews of recent advancements. This paper presents the first comprehensive survey analyzing VAD methods based on MLLMs and LLMs, providing an in-depth discussion of the changes occurring in the VAD field in the era of large models and their underlying causes. Additionally, this paper proposes a unified framework that encompasses both deep neural network (DNN)-based and LLM-based VAD methods, offering a thorough analysis of the new VAD paradigms empowered by LLMs, constructing a classification system, and comparing their strengths and weaknesses. Building on this foundation, this paper focuses on current VAD methods based on MLLMs/LLMs. Finally, based on the trajectory of technological advancements and existing bottlenecks, this paper distills key challenges and outlines future research directions, offering guidance for the VAD community.

cs.CV↗

arXiv2025

Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training

Impressive results on real-world image super-resolution (Real-ISR) have been achieved by employing pre-trained stable diffusion (SD) models. However, one critical issue of such methods lies in their poor reconstruction of image fine structures, such as small characters and textures, due to the aggressive resolution reduction of the VAE (eg., 8$\times$ downsampling) in the SD model. One solution is to employ a VAE with a lower downsampling rate for diffusion; however, adapting its latent features with the pre-trained UNet while mitigating the increased computational cost poses new challenges. To address these issues, we propose a Transfer VAE Training (TVT) strategy to transfer the 8$\times$ downsampled VAE into a 4$\times$ one while adapting to the pre-trained UNet. Specifically, we first train a 4$\times$ decoder based on the output features of the original VAE encoder, then train a 4$\times$ encoder while keeping the newly trained decoder fixed. Such a TVT strategy aligns the new encoder-decoder pair with the original VAE latent space while enhancing image fine details. Additionally, we introduce a compact VAE and compute-efficient UNet by optimizing their network architectures, reducing the computational cost while capturing high-resolution fine-scale features. Experimental results demonstrate that our TVT method significantly improves fine-structure preservation, which is often compromised by other SD-based methods, while requiring fewer FLOPs than state-of-the-art one-step diffusion models. The official code can be found at https://github.com/Joyies/TVT.

cs.CV↗

arXiv2025

Large-Scale Mixed-Traffic and Intersection Control using Multi-agent Reinforcement Learning

Traffic congestion remains a significant challenge in modern urban networks. Autonomous driving technologies have emerged as a potential solution. Among traffic control methods, reinforcement learning has shown superior performance over traffic signals in various scenarios. However, prior research has largely focused on small-scale networks or isolated intersections, leaving large-scale mixed traffic control largely unexplored. This study presents the first attempt to use decentralized multi-agent reinforcement learning for large-scale mixed traffic control in which some intersections are managed by traffic signals and others by robot vehicles. Evaluating a real-world network in Colorado Springs, CO, USA with 14 intersections, we measure traffic efficiency via average waiting time of vehicles at intersections and the number of vehicles reaching their destinations within a time window (i.e., throughput). At 80% RV penetration rate, our method reduces waiting time from 6.17s to 5.09s and increases throughput from 454 vehicles per 500 seconds to 493 vehicles per 500 seconds, outperforming the baseline of fully signalized intersections. These findings suggest that integrating reinforcement learning-based control large-scale traffic can improve overall efficiency and may inform future urban planning strategies.

cs.LG↗

arXiv2025

Heterogeneous Mixed Traffic Control and Coordination

Urban intersections with diverse vehicle types, from small cars to large semi-trailers, pose significant challenges for traffic control. This study explores how robot vehicles (RVs) can enhance heterogeneous traffic flow, particularly at unsignalized intersections where traditional methods fail during power outages. Using reinforcement learning (RL) and real-world data, we simulate mixed traffic at complex intersections with RV penetration rates ranging from 10% to 90%. Results show that average waiting times drop by up to 86% and 91% compared to signalized and unsignalized intersections, respectively. We observe a "rarity advantage," where less frequent vehicles benefit the most (up to 87%). Although CO2 emissions and fuel consumption increase with RV penetration, they remain well below those of traditional signalized traffic. Decreased space headways also indicate more efficient road usage. These findings highlight RVs' potential to improve traffic efficiency and reduce environmental impact in complex, heterogeneous settings.

cs.MA↗

arXiv2025

EEPNet-V2: Patch-to-Pixel Solution for Efficient Cross-Modal Registration between LiDAR Point Cloud and Camera Image

The primary requirement for cross-modal data fusion is the precise alignment of data from different sensors. However, the calibration between LiDAR point clouds and camera images is typically time-consuming and needs external calibration board or specific environmental features. Cross-modal registration effectively solves this problem by aligning the data directly without requiring external calibration. However, due to the domain gap between the point cloud and the image, existing methods rarely achieve satisfactory registration accuracy while maintaining real-time performance. To address this issue, we propose a framework that projects point clouds into several 2D representations for matching with camera images, which not only leverages the geometric characteristic of LiDAR point clouds effectively but also bridge the domain gap between the point cloud and image. Moreover, to tackle the challenges of cross modal differences and the limited overlap between LiDAR point clouds and images in the image matching task, we introduce a multi-scale feature extraction network to effectively extract features from both camera images and the projection maps of LiDAR point cloud. Additionally, we propose a patch-to-pixel matching network to provide more effective supervision and achieve high accuracy. We validate the performance of our model through experiments on the KITTI and nuScenes datasets. Experimental results demonstrate the the proposed method achieves real-time performance and extremely high registration accuracy. Specifically, on the KITTI dataset, our model achieves a registration accuracy rate of over 99\%. Our code is released at: https://github.com/ESRSchao/EEPNet-V2.

cs.CV↗

arXiv2025

Origin-Destination Pattern Effects on Large-Scale Mixed Traffic Control via Multi-Agent Reinforcement Learning

Traffic congestion remains a major challenge for modern urban transportation, diminishing both efficiency and quality of life. While autonomous driving technologies and reinforcement learning (RL) have shown promise for improving traffic control, most prior work has focused on small-scale networks or isolated intersections. Large-scale mixed traffic control, involving both human-driven and robotic vehicles, remains underexplored. In this study, we propose a decentralized multi-agent reinforcement learning framework for managing large-scale mixed traffic networks, where intersections are controlled either by traditional traffic signals or by robotic vehicles. We evaluate our approach on a real-world network of 14 intersections in Colorado Springs, Colorado, USA, using average vehicle waiting time as the primary measure of traffic efficiency. We are exploring a problem that has not been sufficiently addressed: Is large-scale Multi-Agent Traffic Control (MTC) still feasible when facing time-varying Origin-Destination (OD) patterns?

cs.MA↗

arXiv2025

Semi-Supervised Defect Detection via Conditional Diffusion and CLIP-Guided Noise Filtering

In the realm of industrial quality inspection, defect detection stands as a critical component, particularly in high-precision, safety-critical sectors such as automotive components aerospace, and medical devices. Traditional methods, reliant on manual inspection or early image processing algorithms, suffer from inefficiencies, high costs, and limited robustness. This paper introduces a semi-supervised defect detection framework based on conditional diffusion (DSYM), leveraging a two-stage collaborative training mechanism and a staged joint optimization strategy. The framework utilizes labeled data for initial training and subsequently incorporates unlabeled data through the generation of pseudo-labels. A conditional diffusion model synthesizes multi-scale pseudo-defect samples, while a CLIP cross-modal feature-based noise filtering mechanism mitigates label contamination. Experimental results on the NEU-DET dataset demonstrate a 78.4% mAP@0.5 with the same amount of labeled data as traditional supervised methods, and 75.1% mAP@0.5 with only 40% of the labeled data required by the original supervised model, showcasing significant advantages in data efficiency. This research provides a high-precision, low-labeling-dependent solution for defect detection in industrial quality inspection scenarios. The work of this article has been open-sourced at https://github.com/cLin-c/Semisupervised-DSYM.

cs.CV↗