arXiv subjects

Li Zhang

Publications and source records attributed to Li Zhang.

At least 253 records · Page 14Linked to original sources

arXiv2025

Do Large Language Models Truly Understand Cross-cultural Differences?

In recent years, large language models (LLMs) have demonstrated strong performance on multilingual tasks. Given its wide range of applications, cross-cultural understanding capability is a crucial competency. However, existing benchmarks for evaluating whether LLMs genuinely possess this capability suffer from three key limitations: a lack of contextual scenarios, insufficient cross-cultural concept mapping, and limited deep cultural reasoning capabilities. To address these gaps, we propose SAGE, a scenario-based benchmark built via cross-cultural core concept alignment and generative task design, to evaluate LLMs' cross-cultural understanding and reasoning. Grounded in cultural theory, we categorize cross-cultural capabilities into nine dimensions. Using this framework, we curated 210 core concepts and constructed 4530 test items across 15 specific real-world scenarios, organized under four broader categories of cross-cultural situations, following established item design principles. The SAGE dataset supports continuous expansion, and experiments confirm its transferability to other languages. It reveals model weaknesses across both dimensions and scenarios, exposing systematic limitations in cross-cultural reasoning. While progress has been made, LLMs are still some distance away from reaching a truly nuanced cross-cultural understanding. In compliance with the anonymity policy, we include data and code in the supplement materials. In future versions, we will make them publicly available online.

cs.CL↗

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

ELSPR: Evaluator LLM Training Data Self-Purification on Non-Transitive Preferences via Tournament Graph Reconstruction

Pairwise evaluation of large language models (LLMs) has become the dominant paradigm for benchmarking open-ended tasks, yet non-transitive preferences, where evaluators prefer A over B, B over C, but C over A, fundamentally undermine ranking reliability. We show that this critical issue stems largely from low-quality data that contains inherently ambiguous preference pairs. To address this challenge, we propose ELSPR, a principled graph-theoretic framework that models pairwise preferences as tournament graphs and systematically identifies problematic training data. ELSPR quantifies non-transitivity through strongly connected components (SCCs) analysis and measures overall preference clarity using a novel normalized directed graph structural entropy metric. Our filtering methodology selectively removes preference data that induce non-transitivity while preserving transitive preferences. Extensive experiments on the AlpacaEval benchmark demonstrate that models fine-tuned on ELSPR-filtered data achieve substantial improvements: a 13.8% reduction in non-transitivity, a 0.088 decrease in structural entropy, and significantly enhanced discriminative power in real-world evaluation systems. Human validation confirms that discarded data exhibit dramatically lower inter-annotator agreement (34.4% vs. 52.6%) and model-human consistency (51.2% vs. 80.6%) compared to cleaned data. These findings establish ELSPR as an effective data self-purification approach for developing more robust, consistent, and human-aligned LLM evaluation systems.

cs.CL↗

arXiv2025

MobileViews: A Million-scale and Diverse Mobile GUI Dataset

Visual language models (VLMs) empower mobile GUI agents to interpret complex mobile screens and respond to user requests. Training such capable agents requires large-scale, high-quality mobile GUI data. However, existing mobile GUI datasets are limited in scale, data comprehensiveness, and fidelity. To overcome this, we utilize two mobile SoC clusters to provide over 200 native, high-fidelity mobile environments, along with a VLM-enhanced automatic application traversal framework for highly parallel, automated dataset collection with minimal human intervention. With this system, we propose MobileViews, a million-scale mobile GUI dataset comprising over 1.2 million unique screenshot-view hierarchy pairs from more than 30K modern Android applications. We assess the effectiveness of MobileViews by training four VLMs using the reinforcement learning-based GUI grounding task and evaluating them on two representative GUI grounding benchmarks. Results show that MobileViews significantly enhances grounding accuracy by up to 6.1%. Further analysis of data scale and quality underscores the critical role of large, high-quality datasets as reliable sources for training mobile GUI agents. The MobileViews dataset is publicly available at https://huggingface.co/datasets/mllmTeam/MobileViews.

cs.HC↗

arXiv2025

CodeIF-Bench: Evaluating Instruction-Following Capabilities of Large Language Models in Interactive Code Generation

Large Language Models (LLMs) have demonstrated exceptional performance in code generation tasks and have become indispensable programming assistants for developers. However, existing code generation benchmarks primarily assess the functional correctness of code generated by LLMs in single-turn interactions. They offer limited insight into LLMs' abilities to generate code that strictly follows users' instructions in multi-turn interaction scenarios. In this paper, we introduce CodeIF-Bench, a benchmark for evaluating the instruction-following capabilities of LLMs in interactive code generation. Specifically, CodeIF-Bench incorporates nine types of verifiable instructions aligned with the real-world software development requirements, which can be independently and objectively validated through specified test cases, facilitating the evaluation of instruction-following capability in multi-turn interactions. In both Static Conversation and Dynamic Conversation settings, we evaluate the performance of 6 state-of-the-art LLMs and summarize the important factors, additional repository context and gradually increasing interaction history influencing the instruction-following ability of LLMs in multi-turn interactions. Furthermore, we identify the potential direction for improvement: context management. The code and data are available at \href{https://github.com/zhu-zhu-ding/CodeIF-Bench}{https://github.com/zhu-zhu-ding/CodeIF-Bench}.

cs.SE↗

arXiv2025

UFO: Unfair-to-Fair Evolving Mitigates Unfairness in LLM-based Recommender Systems via Self-Play Fine-tuning

Large language model-based Recommender Systems (LRSs) have demonstrated superior recommendation performance by integrating pre-training with Supervised Fine-Tuning (SFT). However, this approach introduces item-side unfairness. Existing studies primarily attribute this issue to the absence of fairness constraints during SFT and attempt to mitigate unfairness via re-weighting and re-ranking methods. In this paper, we find that unfairness arises not only from SFT but also from pre-training, where inherent biases are further amplified during SFT. This finding underscores the failure of current methods to address the root causes of unfairness. Moreover, current methods struggle to preserve satisfactory recommendation performance. To tackle these issues, we propose an Unfair-to-Fair evOlving (UFO) framework using a self-play mechanism, formulating unfairness mitigation as a two-player game. UFO alternates between two player roles: the \textit{judger}, which identifies unfairness from both pre-training and SFT, and the \textit{corrector}, which adjusts the LRS to address identified unfairness while preserving recommendation performance. Iterative optimization between these roles enables UFO to completely resolve unfairness. Extensive experiments demonstrate that UFO effectively mitigates unfairness while improving recommendation performance.

cs.IR↗

arXiv2025

GRB 240715A: Revealing Novel Intrinsic Mechanism by Different Individual Pulse

The Space-based multiband astronomical Variable Objects Monitor (SVOM), detected its first short gamma-ray burst, GRB 240715A, in-flight, which was jointly observed by Fermi. Based on observational data of SVOM/GRM and Fermi/GBM, we perform a comprehensive temporal and spectral analysis for individual pulse in the prompt emission of this burst, and novel characteristics are revealed. Firstly, opposite evolutions of spectral lag are found in the first and third pulse of this burst. Second, the large negative lag of the first pulse is an outlier in short GRB sample, especially when the pulse duration is considered. Spectral analysis shows that the negative lag of the first pulse is caused by the evolution of spectrum index, and is irrelevant to Epeak, which is inconsistent with the previous study. The intrinsic mechanism is probably attributed to electron cooling in the decaying magnetic field, which leads to the continuous hardening of the spectrum index and results in negative lag. Furthermore, spectral analysis also shows that the third pulse is more likely to be described by a quasi-thermal spectrum, indicating the existence of photospheric emission. It is difficult to explain how the synchrotron radiation appears before photospheric emission in a single GRB and some assumptions are discussed.

astro-ph.HE↗

arXiv2025

TOFA: Training-Free One-Shot Federated Adaptation for Vision-Language Models

Efficient and lightweight adaptation of pre-trained Vision-Language Models (VLMs) to downstream tasks through collaborative interactions between local clients and a central server is a rapidly emerging research topic in federated learning. Existing adaptation algorithms are typically trained iteratively, which incur significant communication costs and increase the susceptibility to potential attacks. Motivated by the one-shot federated training techniques that reduce client-server exchanges to a single round, developing a lightweight one-shot federated VLM adaptation method to alleviate these issues is particularly attractive. However, current one-shot approaches face certain challenges in adapting VLMs within federated settings: (1) insufficient exploitation of the rich multimodal information inherent in VLMs; (2) lack of specialized adaptation strategies to systematically handle the severe data heterogeneity; and (3) requiring additional training resource of clients or server. To bridge these gaps, we propose a novel Training-free One-shot Federated Adaptation framework for VLMs, named TOFA. To fully leverage the generalizable multimodal features in pre-trained VLMs, TOFA employs both visual and textual pipelines to extract task-relevant representations. In the visual pipeline, a hierarchical Bayesian model learns personalized, class-specific prototype distributions. For the textual pipeline, TOFA evaluates and globally aligns the generated local text prompts for robustness. An adaptive weight calibration mechanism is also introduced to combine predictions from both modalities, balancing personalization and robustness to handle data heterogeneity. Our method is training-free, not relying on additional training resources on either the client or server side. Extensive experiments across 9 datasets in various federated settings demonstrate the effectiveness of the proposed TOFA method.

cs.AI↗

arXiv2025

4D-VLA: Spatiotemporal Vision-Language-Action Pretraining with Cross-Scene Calibration

Leveraging diverse robotic data for pretraining remains a critical challenge. Existing methods typically model the dataset's action distribution using simple observations as inputs. However, these inputs are often incomplete, resulting in a dispersed conditional action distribution-an issue we refer to as coordinate system chaos and state chaos. This inconsistency significantly hampers pretraining efficiency. To address this, we propose 4D-VLA, a novel approach that effectively integrates 4D information into the input to mitigate these sources of chaos. Our model introduces depth and temporal information into visual features with sequential RGB-D inputs, aligning the coordinate systems of the robot and the scene. This alignment endows the model with strong spatiotemporal reasoning capabilities while minimizing training overhead. Additionally, we introduce memory bank sampling, a frame sampling strategy designed to extract informative frames from historical images, further improving effectiveness and efficiency. Experimental results demonstrate that our pretraining method and architectural components substantially enhance model performance. In both simulated and real-world experiments, our model achieves a significant increase in success rate over OpenVLA. To further assess spatial perception and generalization to novel views, we introduce MV-Bench, a multi-view simulation benchmark. Our model consistently outperforms existing methods, demonstrating stronger spatial understanding and adaptability.

cs.CV↗

arXiv2025

Brain3D: Generating 3D Objects from fMRI

Understanding the hidden mechanisms behind human's visual perception is a fundamental question in neuroscience. To that end, investigating into the neural responses of human mind activities, such as functional Magnetic Resonance Imaging (fMRI), has been a significant research vehicle. However, analyzing fMRI signals is challenging, costly, daunting, and demanding for professional training. Despite remarkable progress in fMRI analysis, existing approaches are limited to generating 2D images and far away from being biologically meaningful and practically useful. Under this insight, we propose to generate visually plausible and functionally more comprehensive 3D outputs decoded from brain signals, enabling more sophisticated modeling of fMRI data. Conceptually, we reformulate this task as a {\em fMRI conditioned 3D object generation} problem. We design a novel 3D object representation learning method, Brain3D, that takes as input the fMRI data of a subject who was presented with a 2D image, and yields as output the corresponding 3D object images. The key capabilities of this model include tackling the noises with high-level semantic signals and a two-stage architecture design for progressive high-level information integration. Extensive experiments validate the superior capability of our model over previous state-of-the-art 3D object generation methods. Importantly, we show that our model captures the distinct functionalities of each region of human vision system as well as their intricate interplay relationships, aligning remarkably with the established discoveries in neuroscience. Further, preliminary evaluations indicate that Brain3D can successfully identify the disordered brain regions in simulated scenarios, such as V1, V2, V3, V4, and the medial temporal lobe (MTL) within the human visual system. Our data and code will be available at https://brain-3d.github.io/.

cs.CV↗

arXiv2025

Multi-Scale Target-Aware Representation Learning for Fundus Image Enhancement

High-quality fundus images provide essential anatomical information for clinical screening and ophthalmic disease diagnosis. Yet, due to hardware limitations, operational variability, and patient compliance, fundus images often suffer from low resolution and signal-to-noise ratio. Recent years have witnessed promising progress in fundus image enhancement. However, existing works usually focus on restoring structural details or global characteristics of fundus images, lacking a unified image enhancement framework to recover comprehensive multi-scale information. Moreover, few methods pinpoint the target of image enhancement, e.g., lesions, which is crucial for medical image-based diagnosis. To address these challenges, we propose a multi-scale target-aware representation learning framework (MTRL-FIE) for efficient fundus image enhancement. Specifically, we propose a multi-scale feature encoder (MFE) that employs wavelet decomposition to embed both low-frequency structural information and high-frequency details. Next, we design a structure-preserving hierarchical decoder (SHD) to fuse multi-scale feature embeddings for real fundus image restoration. SHD integrates hierarchical fusion and group attention mechanisms to achieve adaptive feature fusion while retaining local structural smoothness. Meanwhile, a target-aware feature aggregation (TFA) module is used to enhance pathological regions and reduce artifacts. Experimental results on multiple fundus image datasets demonstrate the effectiveness and generalizability of MTRL-FIE for fundus image enhancement. Compared to state-of-the-art methods, MTRL-FIE achieves superior enhancement performance with a more lightweight architecture. Furthermore, our approach generalizes to other ophthalmic image processing tasks without supervised fine-tuning, highlighting its potential for clinical applications.

eess.IV↗

arXiv2025

VistaDepth: Improving far-range Depth Estimation with Spectral Modulation and Adaptive Reweighting

Monocular depth estimation (MDE) aims to infer per-pixel depth from a single RGB image. While diffusion models have advanced MDE with impressive generalization, they often exhibit limitations in accurately reconstructing far-range regions. This difficulty arises from two key challenges. First, the implicit multi-scale processing in standard spatial-domain models can be insufficient for preserving the fine-grained, high-frequency details crucial for distant structures. Second, the intrinsic long-tail distribution of depth data imposes a strong training bias towards more prevalent near-range regions. To address these, we propose VistaDepth, a novel diffusion framework designed for balanced and accurate depth perception. We introduce two key innovations. First, the Latent Frequency Modulation (LFM) module enhances the model's ability to represent high-frequency details. It operates by having a lightweight network predict a dynamic, content-aware spectral filter to refine latent features, thereby improving the reconstruction of distant structures. Second, our BiasMap mechanism introduces an adaptive reweighting of the diffusion loss strategically scaled across diffusion timesteps. It further aligns the supervision with the progressive denoising process, establishing a more consistent learning signal. As a result, it mitigates data bias without sacrificing training stability. Experiments show that VistaDepth achieves state-of-the-art performance for diffusion-based MDE, particularly excelling in reconstructing detailed and accurate depth in far-range regions.

cs.CV↗

arXiv2025

MIDB: Multilingual Instruction Data Booster for Enhancing Cultural Equality in Multilingual Instruction Synthesis

Despite doubts on data quality, instruction synthesis has been widely applied into instruction tuning (IT) of LLMs as an economic and rapid alternative. Recent endeavors focus on improving data quality for synthesized instruction pairs in English and have facilitated IT of English-centric LLMs. However, data quality issues in multilingual synthesized instruction pairs are even more severe, since the common synthesizing practice is to translate English synthesized data into other languages using machine translation (MT). Besides the known content errors in these English synthesized data, multilingual synthesized instruction data are further exposed to defects introduced by MT and face insufficient localization of the target languages, leading to cultural inequality in trained LLMs. In this paper, we propose MIDB, a Multilingual Instruction Data Booster to automatically address the quality issues in multilingual synthesized data. MIDB is trained on around 36.8k revision examples across 16 languages by human linguistic experts, thereby can boost the low-quality data by addressing content errors and MT defects, and improving localization in these synthesized data. Both automatic and human evaluation indicate that not only MIDB steadily improved instruction data quality in 16 languages, but also the instruction-following and cultural-understanding abilities of multilingual LLMs fine-tuned on MIDB-boosted data were significantly enhanced, suggesting an improved linguistic and cultural equality.

cs.CL↗

arXiv2025

From Noise to Latent: Generating Gaussian Latents for INR-Based Image Compression

Recent implicit neural representation (INR)-based image compression methods have shown competitive performance by overfitting image-specific latent codes. However, they remain inferior to end-to-end (E2E) compression approaches due to the absence of expressive latent representations. On the other hand, E2E methods rely on transmitting latent codes and requiring complex entropy models, leading to increased decoding complexity. Inspired by the normalization strategy in E2E codecs where latents are transformed into Gaussian noise to demonstrate the removal of spatial redundancy, we explore the inverse direction: generating latents directly from Gaussian noise. In this paper, we propose a novel image compression paradigm that reconstructs image-specific latents from a multi-scale Gaussian noise tensor, deterministically generated using a shared random seed. A Gaussian Parameter Prediction (GPP) module estimates the distribution parameters, enabling one-shot latent generation via reparameterization trick. The predicted latent is then passed through a synthesis network to reconstruct the image. Our method eliminates the need to transmit latent codes while preserving latent-based benefits, achieving competitive rate-distortion performance on Kodak and CLIC dataset. To the best of our knowledge, this is the first work to explore Gaussian latent generation for learned image compression.

eess.IV↗

arXiv2025

Exploring Category-level Articulated Object Pose Tracking on SE(3) Manifolds

Articulated objects are prevalent in daily life and robotic manipulation tasks. However, compared to rigid objects, pose tracking for articulated objects remains an underexplored problem due to their inherent kinematic constraints. To address these challenges, this work proposes a novel point-pair-based pose tracking framework, termed \textbf{PPF-Tracker}. The proposed framework first performs quasi-canonicalization of point clouds in the SE(3) Lie group space, and then models articulated objects using Point Pair Features (PPF) to predict pose voting parameters by leveraging the invariance properties of SE(3). Finally, semantic information of joint axes is incorporated to impose unified kinematic constraints across all parts of the articulated object. PPF-Tracker is systematically evaluated on both synthetic datasets and real-world scenarios, demonstrating strong generalization across diverse and challenging environments. Experimental results highlight the effectiveness and robustness of PPF-Tracker in multi-frame pose tracking of articulated objects. We believe this work can foster advances in robotics, embodied intelligence, and augmented reality. Codes are available at https://github.com/mengxh20/PPFTracker.

cs.CV↗

arXiv2025

FedFACT: A Provable Framework for Controllable Group-Fairness Calibration in Federated Learning

With the emerging application of Federated Learning (FL) in decision-making scenarios, it is imperative to regulate model fairness to prevent disparities across sensitive groups (e.g., female, male). Current research predominantly focuses on two concepts of group fairness within FL: Global Fairness (overall model disparity across all clients) and Local Fairness (the disparity within each client). However, the non-decomposable, non-differentiable nature of fairness criteria poses two fundamental, unresolved challenges for fair FL: (i) Harmonizing global and local fairness, especially in multi-class setting; (ii) Enabling a controllable, optimal accuracy-fairness trade-off. To tackle these challenges, we propose a novel controllable federated group-fairness calibration framework, named FedFACT. FedFACT identifies the Bayes-optimal classifiers under both global and local fairness constraints, yielding models with minimal performance decline while guaranteeing fairness. Building on the characterization of the optimal fair classifiers, we reformulate fair federated learning as a personalized cost-sensitive learning problem for in-processing and a bi-level optimization for post-processing. Theoretically, we provide convergence and generalization guarantees for FedFACT to approach the near-optimal accuracy under given fairness levels. Extensive experiments on multiple datasets across various data heterogeneity demonstrate that FedFACT consistently outperforms baselines in balancing accuracy and global-local fairness.

cs.LG↗

arXiv2025

Towards Realistic Project-Level Code Generation via Multi-Agent Collaboration and Semantic Architecture Modeling

In recent years, Large Language Models (LLMs) have achieved remarkable progress in automated code generation. In real-world software engineering, the growing demand for rapid iteration and continuous delivery underscores the importance of project-level code generation, where LLMs are expected to generate complete software projects directly from complex user requirements. Although existing studies have made initial explorations, they still face key limitations, including unrealistic datasets and unreliable evaluation metrics that fail to reflect real-world complexity, the semantic gap between human-written requirements and machine-interpretable structures, and difficulties in managing hierarchical dependencies and maintaining quality throughout the generation process. To address these limitations, we first introduce CodeProjectEval, a project-level code generation dataset built from 18 real-world repositories with 12.7 files and 2,388.6 lines of code per task on average, supplemented with documentation and executable test cases for automatic evaluation. We further propose ProjectGen, a multi-agent framework that decomposes projects into architecture design, skeleton generation, and code filling stages with iterative refinement and memory-based context management. Within this framework, we introduce the Semantic Software Architecture Tree (SSAT), a structured and semantically rich representation that effectively bridges user requirements and source code implementation. Experiments show that ProjectGen achieves state-of-the-art performance, passing 52/124 test cases on the small-scale project-level code generation dataset DevBench, a 57% improvement over the baseline approaches, and 310 test cases on CodeProjectEval, representing an improvement of roughly tenfold compared to the baselines.

cs.SE↗

arXiv2025

RepoScope: Leveraging Call Chain-Aware Multi-View Context for Repository-Level Code Generation

Repository-level code generation aims to generate code within the context of a specified repository. Existing approaches typically employ retrieval-augmented generation (RAG) techniques to provide LLMs with relevant contextual information extracted from the repository. However, these approaches often struggle with effectively identifying truly relevant contexts that capture the rich semantics of the repository, and their contextual perspectives remains narrow. Moreover, most approaches fail to account for the structural relationships in the retrieved code during prompt construction, hindering the LLM's ability to accurately interpret the context. To address these issues, we propose RepoScope, which leverages call chain-aware multi-view context for repository-level code generation. RepoScope constructs a Repository Structural Semantic Graph (RSSG) and retrieves a comprehensive four-view context, integrating both structural and similarity-based contexts. We propose a novel call chain prediction method that utilizes the repository's structural semantics to improve the identification of callees in the target function. Additionally, we present a structure-preserving serialization algorithm for prompt construction, ensuring the coherence of the context for the LLM. Notably, RepoScope relies solely on static analysis, eliminating the need for additional training or multiple LLM queries, thus ensuring both efficiency and generalizability. Evaluation on widely-used repository-level code generation benchmarks (CoderEval and DevEval) demonstrates that RepoScope outperforms state-of-the-art methods, achieving up to a 36.35% relative improvement in pass@1 scores. Further experiments emphasize RepoScope's potential to improve code generation across different tasks and its ability to integrate effectively with existing approaches.

cs.SE↗