arXiv subjects

Ke Li

Publications and source records attributed to Ke Li.

At least 127 records · Page 7Linked to original sources

arXiv2025

CUARewardBench: A Benchmark for Evaluating Reward Models on Computer-using Agent

Computer-using agents (CUAs) enable task completion through natural interaction with operating systems and software interfaces. While script-based verifiers are widely adopted for evaluation, they suffer from limited scalability and inability to provide step-wise assessment. Reward models offer promising alternatives, but their effectiveness on CUA evaluation remains largely underexplored. To address this gap, we present CUARewardBench, comprising four key contributions: (1) First-ever Comprehensive CUA Reward Benchmark: We introduce the first benchmark for evaluating both outcome reward models (ORM) and process reward models (PRM) on CUA tasks, enabling systematic assessment across trajectory-level and step-level evaluation. (2) Diverse, Practical and Reliable Dataset: CUARewardBench encompasses trajectories from 10 software categories and 7 agent architectures with varying performance levels (25.9%-50.8% success rates). All trajectories are expertly annotated through carefully designed protocols, with rigorous quality control to ensure reliability and practical applicability. (3) Comprehensive Analysis and Insights: Through extensive experiments across 7 vision-language models and 3 prompt templates, we reveal critical limitations of current CUA RMs, including insufficient visual reasoning capabilities, knowledge deficiencies, and the superiority of general VLMs over specialized CUA models for reward evaluation. (4) Unanimous Prompt Ensemble (UPE): Based on the insights from our comprehensive analysis, we propose UPE, a novel ensemble method that significantly enhances reward model reliability through strict unanimous voting and strategic prompt-template configurations. UPE achieves 89.8% precision and 93.3% NPV for ORM, and 81.7% precision and 85.1% NPV for PRM, substantially outperforming single VLMs and traditional ensemble approaches.

cs.SE↗

arXiv2025

Benchmarking Fake Voice Detection in the Fake Voice Generation Arms Race

The rapid advancement of fake voice generation technology has ignited a race with detection systems, creating an urgent need to secure the audio ecosystem. However, existing benchmarks suffer from a critical limitation: they typically aggregate diverse fake voice samples into a single dataset for evaluation. This practice masks method-specific artifacts and obscures the varying performance of detectors against different generation paradigms, preventing a nuanced understanding of their true vulnerabilities. To address this gap, we introduce the first ecosystem-level benchmark that systematically evaluates the interplay between 17 state-of-the-art fake voice generators and 8 leading detectors through a novel one-to-one evaluation protocol. This fine-grained analysis exposes previously hidden vulnerabilities and sensitivities that are missed by traditional aggregated testing. We also propose unified scoring systems to quantify both the evasiveness of generators and the robustness of detectors, enabling fair and direct comparisons. Our extensive cross-domain evaluation reveals that modern generators, particularly those based on neural audio codecs and flow matching, consistently evade top-tier detectors. We found that no single detector is universally robust; their effectiveness varies dramatically depending on the generator's architecture, highlighting a significant generalization gap in current defenses. This work provides a more realistic assessment of the threat landscape and offers actionable insights for building the next generation of detection systems.

cs.SD↗

arXiv2025

Contrastive Local Manifold Learning for No-Reference Image Quality Assessment

Image Quality Assessment (IQA) methods typically overlook local manifold structures, leading to compromised discriminative capabilities in perceptual quality evaluation. To address this limitation, we present LML-IQA, an innovative no-reference IQA (NR-IQA) approach that leverages a combination of local manifold learning and contrastive learning. Our approach first extracts multiple patches from each image and identifies the most visually salient region. This salient patch serves as a positive sample for contrastive learning, while other patches from the same image are treated as intra-class negatives to preserve local distinctiveness. Patches from different images also act as inter-class negatives to enhance feature separation. Additionally, we introduce a mutual learning strategy to improve the model's ability to recognize and prioritize visually important regions. Comprehensive experiments across eight benchmark datasets demonstrate significant performance gains over state-of-the-art methods, achieving a PLCC of 0.942 on TID2013 (compared to 0.908) and 0.977 on CSIQ (compared to 0.965).

cs.CV↗

arXiv2025

Adaptive Collaborative Correlation Learning-based Semi-Supervised Multi-Label Feature Selection

Semi-supervised multi-label feature selection has recently been developed to solve the curse of dimensionality problem in high-dimensional multi-label data with certain samples missing labels. Although many efforts have been made, most existing methods use a predefined graph approach to capture the sample similarity or the label correlation. In this manner, the presence of noise and outliers within the original feature space can undermine the reliability of the resulting sample similarity graph. It also fails to precisely depict the label correlation due to the existence of unknown labels. Besides, these methods only consider the discriminative power of selected features, while neglecting their redundancy. In this paper, we propose an Adaptive Collaborative Correlation lEarning-based Semi-Supervised Multi-label Feature Selection (Access-MFS) method to address these issues. Specifically, a generalized regression model equipped with an extended uncorrelated constraint is introduced to select discriminative yet irrelevant features and maintain consistency between predicted and ground-truth labels in labeled data, simultaneously. Then, the instance correlation and label correlation are integrated into the proposed regression model to adaptively learn both the sample similarity graph and the label similarity graph, which mutually enhance feature selection performance. Extensive experimental results demonstrate the superiority of the proposed Access-MFS over other state-of-the-art methods.

cs.LG↗

arXiv2025

Training-Free Group Relative Policy Optimization

Recent advances in Large Language Model (LLM) agents have demonstrated their promising general capabilities. However, their performance in specialized real-world domains often degrades due to challenges in effectively integrating external tools and specific prompting strategies. While methods like agentic reinforcement learning have been proposed to address this, they typically rely on costly parameter updates, for example, through a process that uses Supervised Fine-Tuning (SFT) followed by a Reinforcement Learning (RL) phase with Group Relative Policy Optimization (GRPO) to alter the output distribution. However, we argue that LLMs can achieve a similar effect on the output distribution by learning experiential knowledge as a token prior, which is a far more lightweight approach that not only addresses practical data scarcity but also avoids the common issue of overfitting. To this end, we propose Training-Free Group Relative Policy Optimization (Training-Free GRPO), a cost-effective solution that enhances LLM agent performance without any parameter updates. Our method leverages the group relative semantic advantage instead of numerical ones within each group of rollouts, iteratively distilling high-quality experiential knowledge during multi-epoch learning on a minimal ground-truth data. Such knowledge serves as the learned token prior, which is seamlessly integrated during LLM API calls to guide model behavior. Experiments on mathematical reasoning and web searching tasks demonstrate that Training-Free GRPO, when applied to DeepSeek-V3.1-Terminus, significantly improves out-of-domain performance. With just a few dozen training samples, Training-Free GRPO outperforms fine-tuned small LLMs with marginal training data and cost.

cs.CL↗

arXiv2025

Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models

Existing large language models (LLMs) face challenges of following complex instructions, especially when multiple constraints are present and organized in paralleling, chaining, and branching structures. One intuitive solution, namely chain-of-thought (CoT), is expected to universally improve capabilities of LLMs. However, we find that the vanilla CoT exerts a negative impact on performance due to its superficial reasoning pattern of simply paraphrasing the instructions. It fails to peel back the compositions of constraints for identifying their relationship across hierarchies of types and dimensions. To this end, we propose RAIF, a systematic method to boost LLMs in dealing with complex instructions via incentivizing reasoning for test-time compute scaling. First, we stem from the decomposition of complex instructions under existing taxonomies and propose a reproducible data acquisition method. Second, we exploit reinforcement learning (RL) with verifiable rule-centric reward signals to cultivate reasoning specifically for instruction following. We address the shallow, non-essential nature of reasoning under complex instructions via sample-wise contrast for superior CoT enforcement. We also exploit behavior cloning of experts to facilitate steady distribution shift from fast-thinking LLMs to skillful reasoners. Extensive evaluations on seven comprehensive benchmarks confirm the validity of the proposed method, where a 1.5B LLM achieves 11.74% gains with performance comparable to a 8B LLM. Evaluation on OOD constraints also confirms the generalizability of our RAIF. Codes and data are available at https://github.com/yuleiqin/RAIF. Keywords: reinforcement learning with verifiable rewards (RLVR), instruction following, complex instructions

cs.CV↗

arXiv2025

RoRecomp: Enhancing Reasoning Efficiency via Rollout Response Recomposition in Reinforcement Learning

Reinforcement learning with verifiable rewards (RLVR) has proven effective in eliciting complex reasoning in large language models (LLMs). However, standard RLVR training often leads to excessively verbose processes (in reasoning tasks) and inefficient exploration trajectories (in agentic settings), as outcome-only rewards provide no incentive for efficiency and the high variance in response length within relatively small rollout groups results in noisy optimization signals. To address this, we propose Rollout Response Recomposition (RoRecomp), a plug-and-play method that guides models toward concise reasoning by strategically recomposing the training data. RoRecomp separates responses into two distinct batch types: 1) priority batches, which combine short-correct and long-incorrect responses selected from online batches to provide a clear gradient signal for brevity, and 2) compensation batches, which utilize remaining responses from a replay buffer to maintain stability and prevent model collapse. To comprehensively evaluate effectiveness, we test RoRecomp across three settings where results demonstrate substantial efficiency gains: reducing reasoning length by 27.7% in zero RL training, reducing unnecessary tool calls by 46.8% while improving accuracy in agentic RL, and achieving up to 52.5% length reduction in thinking compression, all with minimal performance impact.

cs.AI↗

arXiv2025

Enhancing Cross-View Geo-Localization Generalization via Global-Local Consistency and Geometric Equivariance

Cross-view geo-localization (CVGL) aims to match images of the same location captured from drastically different viewpoints. Despite recent progress, existing methods still face two key challenges: (1) achieving robustness under severe appearance variations induced by diverse UAV orientations and fields of view, which hinders cross-domain generalization, and (2) establishing reliable correspondences that capture both global scene-level semantics and fine-grained local details. In this paper, we propose EGS, a novel CVGL framework designed to enhance cross-domain generalization. Specifically, we introduce an E(2)-Steerable CNN encoder to extract stable and reliable features under rotation and viewpoint shifts. Furthermore, we construct a graph with a virtual super-node that connects to all local nodes, enabling global semantics to be aggregated and redistributed to local regions, thereby enforcing global-local consistency. Extensive experiments on the University-1652 and SUES-200 benchmarks demonstrate that EGS consistently achieves substantial performance gains and establishes a new state of the art in cross-domain CVGL.

cs.CV↗

arXiv2025

EDBench: Large-Scale Electron Density Data for Molecular Modeling

Existing molecular machine learning force fields (MLFFs) generally focus on the learning of atoms, molecules, and simple quantum chemical properties (such as energy and force), but ignore the importance of electron density (ED) $ρ(r)$ in accurately understanding molecular force fields (MFFs). ED describes the probability of finding electrons at specific locations around atoms or molecules, which uniquely determines all ground state properties (such as energy, molecular structure, etc.) of interactive multi-particle systems according to the Hohenberg-Kohn theorem. However, the calculation of ED relies on the time-consuming first-principles density functional theory (DFT) which leads to the lack of large-scale ED data and limits its application in MLFFs. In this paper, we introduce EDBench, a large-scale, high-quality dataset of ED designed to advance learning-based research at the electronic scale. Built upon the PCQM4Mv2, EDBench provides accurate ED data, covering 3.3 million molecules. To comprehensively evaluate the ability of models to understand and utilize electronic information, we design a suite of ED-centric benchmark tasks spanning prediction, retrieval, and generation. Our evaluation on several state-of-the-art methods demonstrates that learning from EDBench is not only feasible but also achieves high accuracy. Moreover, we show that learning-based method can efficiently calculate ED with comparable precision while significantly reducing the computational cost relative to traditional DFT calculations. All data and benchmarks from EDBench will be freely available, laying a robust foundation for ED-driven drug discovery and materials science.

physics.chem-ph↗

arXiv2025

Few-Shot Image Quality Assessment via Adaptation of Vision-Language Models

Image Quality Assessment (IQA) remains an unresolved challenge in computer vision due to complex distortions, diverse image content, and limited data availability. Existing Blind IQA (BIQA) methods largely rely on extensive human annotations, which are labor-intensive and costly due to the demanding nature of creating IQA datasets. To reduce this dependency, we propose the Gradient-Regulated Meta-Prompt IQA Framework (GRMP-IQA), designed to efficiently adapt the visual-language pre-trained model, CLIP, to IQA tasks, achieving high accuracy even with limited data. GRMP-IQA consists of two core modules: (i) Meta-Prompt Pre-training Module and (ii) Quality-Aware Gradient Regularization. The Meta Prompt Pre-training Module leverages a meta-learning paradigm to pre-train soft prompts with shared meta-knowledge across different distortions, enabling rapid adaptation to various IQA tasks. On the other hand, the Quality-Aware Gradient Regularization is designed to adjust the update gradients during fine-tuning, focusing the model's attention on quality-relevant features and preventing overfitting to semantic information. Extensive experiments on standard BIQA datasets demonstrate the superior performance to the state-of-the-art BIQA methods under limited data setting. Notably, utilizing just 20% of the training data, GRMP-IQA is competitive with most existing fully supervised BIQA approaches.

cs.CV↗

arXiv2025

Multi-label Scene Classification for Autonomous Vehicles: Acquiring and Accumulating Knowledge from Diverse Datasets

Driving scenes are inherently heterogeneous and dynamic. Multi-attribute scene identification, as a high-level visual perception capability, provides autonomous vehicles (AVs) with essential contextual awareness to understand, reason through, and interact with complex driving environments. Although scene identification is best modeled as a multi-label classification problem via multitask learning, it faces two major challenges: the difficulty of acquiring balanced, comprehensively annotated datasets and the need to re-annotate all training data when new attributes emerge. To address these challenges, this paper introduces a novel deep learning method that integrates Knowledge Acquisition and Accumulation (KAA) with Consistency-based Active Learning (CAL). KAA leverages monotask learning on heterogeneous single-label datasets to build a knowledge foundation, while CAL bridges the gap between single- and multi-label data, adapting the foundation model for multi-label scene classification. An ablation study on the newly developed Driving Scene Identification (DSI) dataset demonstrates a 56.1% improvement over an ImageNet-pretrained baseline. Moreover, KAA-CAL outperforms state-of-the-art multi-label classification methods on the BDD100K and HSD datasets, achieving this with 85% less data and even recognizing attributes unseen during foundation model training. The DSI dataset and KAA-CAL implementation code are publicly available at https://github.com/KELISBU/KAA-CAL .

cs.CV↗

arXiv2025

OptiProxy-NAS: Optimization Proxy based End-to-End Neural Architecture Search

Neural architecture search (NAS) is a hard computationally expensive optimization problem with a discrete, vast, and spiky search space. One of the key research efforts dedicated to this space focuses on accelerating NAS via certain proxy evaluations of neural architectures. Different from the prevalent predictor-based methods using surrogate models and differentiable architecture search via supernetworks, we propose an optimization proxy to streamline the NAS as an end-to-end optimization framework, named OptiProxy-NAS. In particular, using a proxy representation, the NAS space is reformulated to be continuous, differentiable, and smooth. Thereby, any differentiable optimization method can be applied to the gradient-based search of the relaxed architecture parameters. Our comprehensive experiments on $12$ NAS tasks of $4$ search spaces across three different domains including computer vision, natural language processing, and resource-constrained NAS fully demonstrate the superior search results and efficiency. Further experiments on low-fidelity scenarios verify the flexibility.

cs.LG↗

arXiv2025

Observation of Universal Expansion Anisotropy from Cold Atoms to Hot Quark-Gluon Plasma

Azimuthal anisotropy has been ubiquitously observed in high-energy proton-proton, proton-nucleus, and nucleus-nucleus (heavy-ion) collisions, shaking the early belief that those anisotropies require an intense phase of multiple interactions between the created particles. This work reports a study of anisotropic expansion of cold $^{6}$Li Fermi gases, initially trapped in an anisotropic potential, as a function of the interaction strength that can be readily tuned by an external magnetic field. It is found that the expansion anisotropy builds up quickly at small interaction strength, without the need of a large amount of interactions. An unexpected and quantitative universal scaling of the expansion anisotropy is observed for the first time between cold atom and heavy-ion systems as a function of the number of collisions per particle or opacity ($n_{\rm coll}$), despite their vast differences in scale and physics. The expansion isotropy in both the cold atom gases and heavy-ion collisions increases smoothly and shows no sign of saturation in the observed opacity range, with an approximate power-law dependence of $\sqrt{n_{\rm coll}}$, characteristic of random walks. This universality potentially unifies a variety of vastly different physical systems, from weakly interacting dilute gases to the strongly interacting quark-gluon plasma of the early universe.

cond-mat.quant-gas↗

arXiv2025

UTA-Sign: Unsupervised Thermal Video Augmentation via Event-Assisted Traffic Signage Sketching

The thermal camera excels at perceiving outdoor environments under low-light conditions, making it ideal for applications such as nighttime autonomous driving and unmanned navigation. However, thermal cameras encounter challenges when capturing signage from objects made of similar materials, which can pose safety risks for accurately understanding semantics in autonomous driving systems. In contrast, the neuromorphic vision camera, also known as an event camera, detects changes in light intensity asynchronously and has proven effective in high-speed, low-light traffic environments. Recognizing the complementary characteristics of these two modalities, this paper proposes UTA-Sign, an unsupervised thermal-event video augmentation for traffic signage in low-illumination environments, targeting elements such as license plates and roadblock indicators. To address the signage blind spots of thermal imaging and the non-uniform sampling of event cameras, we developed a dual-boosting mechanism that fuses thermal frames and event signals for consistent signage representation over time. The proposed method utilizes thermal frames to provide accurate motion cues as temporal references for aligning the uneven event signals. At the same time, event signals contribute subtle signage content to the raw thermal frames, enhancing the overall understanding of the environment. The proposed method is validated on datasets collected from real-world scenarios, demonstrating superior quality in traffic signage sketching and improved detection accuracy at the perceptual level.

cs.CV↗

arXiv2025

Amadeus: Autoregressive Model with Bidirectional Attribute Modelling for Symbolic Music

Existing state-of-the-art symbolic music generation models predominantly adopt autoregressive or hierarchical autoregressive architectures, modelling symbolic music as a sequence of attribute tokens with unidirectional temporal dependencies, under the assumption of a fixed, strict dependency structure among these attributes. However, we observe that using different attributes as the initial token in these models leads to comparable performance. This suggests that the attributes of a musical note are, in essence, a concurrent and unordered set, rather than a temporally dependent sequence. Based on this insight, we introduce Amadeus, a novel symbolic music generation framework. Amadeus adopts a two-level architecture: an autoregressive model for note sequences and a bidirectional discrete diffusion model for attributes. To enhance performance, we propose Music Latent Space Discriminability Enhancement Strategy(MLSDES), incorporating contrastive learning constraints that amplify discriminability of intermediate music representations. The Conditional Information Enhancement Module (CIEM) simultaneously strengthens note latent vector representation via attention mechanisms, enabling more precise note decoding. We conduct extensive experiments on unconditional and text-conditioned generation tasks. Amadeus significantly outperforms SOTA models across multiple metrics while achieving at least 4$\times$ speed-up. Furthermore, we demonstrate training-free, fine-grained note attribute control feasibility using our model. To explore the upper performance bound of the Amadeus architecture, we compile the largest open-source symbolic music dataset to date, AMD (Amadeus MIDI Dataset), supporting both pre-training and fine-tuning.

cs.SD↗

arXiv2025

Global Motion Corresponder for 3D Point-Based Scene Interpolation under Large Motion

Existing dynamic scene interpolation methods typically assume that the motion between consecutive timesteps is small enough so that displacements can be locally approximated by linear models. In practice, even slight deviations from this small-motion assumption can cause conventional techniques to fail. In this paper, we introduce Global Motion Corresponder (GMC), a novel approach that robustly handles large motion and achieves smooth transitions. GMC learns unary potential fields that predict SE(3) mappings into a shared canonical space, balancing correspondence, spatial and semantic smoothness, and local rigidity. We demonstrate that our method significantly outperforms existing baselines on 3D scene interpolation when the two states undergo large global motions. Furthermore, our method enables extrapolation capabilities where other baseline methods cannot.

eess.IV↗

arXiv2025

Reality Fusion: Robust Real-time Immersive Mobile Robot Teleoperation with Volumetric Visual Data Fusion

We introduce Reality Fusion, a novel robot teleoperation system that localizes, streams, projects, and merges a typical onboard depth sensor with a photorealistic, high resolution, high framerate, and wide field of view (FoV) rendering of the complex remote environment represented as 3D Gaussian splats (3DGS). Our framework enables robust egocentric and exocentric robot teleoperation in immersive VR, with the 3DGS effectively extending spatial information of a depth sensor with limited FoV and balancing the trade-off between data streaming costs and data visual quality. We evaluated our framework through a user study with 24 participants, which revealed that Reality Fusion leads to significantly better user performance, situation awareness, and user preferences. To support further research and development, we provide an open-source implementation with an easy-to-replicate custom-made telepresence robot, a high-performance virtual reality 3DGS renderer, and an immersive robot control package. (Source code: https://github.com/uhhhci/RealityFusion)

cs.RO↗

arXiv2025

Radiance Fields in XR: A Survey on How Radiance Fields are Envisioned and Addressed for XR Research

The development of radiance fields (RF), such as 3D Gaussian Splatting (3DGS) and Neural Radiance Fields (NeRF), has revolutionized interactive photorealistic view synthesis and presents enormous opportunities for XR research and applications. However, despite the exponential growth of RF research, RF-related contributions to the XR community remain sparse. To better understand this research gap, we performed a systematic survey of current RF literature to analyze (i) how RF is envisioned for XR applications, (ii) how they have already been implemented, and (iii) the remaining research gaps. We collected 365 RF contributions related to XR from computer vision, computer graphics, robotics, multimedia, human-computer interaction, and XR communities, seeking to answer the above research questions. Among the 365 papers, we performed an analysis of 66 papers that already addressed a detailed aspect of RF research for XR. With this survey, we extended and positioned XR-specific RF research topics in the broader RF research field and provide a helpful resource for the XR community to navigate within the rapid development of RF research.

cs.GR↗