arXiv subjects

Wen Wen

Publications and source records attributed to Wen Wen.

At least 19 recordsLinked to original sources

arXiv2026

SPATEX: Array-Flexible Multichannel-to-Multichannel Target Speech Extraction using Direction Clue

Multichannel-to-multichannel target speech extraction (MIMO TSE) aims to recover the target speech signal at each microphone while preserving interchannel spatial information. However, existing MIMO TSE systems generally assume a fixed microphone configuration, limiting their applicability to recording devices with varying microphone configurations. In this work, we propose SPATEX, the first array-flexible MIMO TSE framework that reconstructs microphone-wise target speech signals across microphone counts and array geometries. Given microphone coordinates and a target direction-of-arrival (DOA), SPATEX combines geometry-aware channel exchange and shared temporal attention to jointly reconstruct microphone-wise target signals while maintaining permutation equivariance. Experiments show that SPATEX outperforms array-flexible single-output baselines under most test conditions and consistently improves extraction quality and spatial fidelity over fixed-array MIMO baselines. Ablation studies further validate the benefits of temporal coordination and spatial supervision, while additional evaluations demonstrate robustness to target DOA errors. Our code and dataset are available at https://github.com/Wenanzhi/SPATEX.

eess.AS↗

arXiv2026

SURE-Tagger: Structured Speech Representations for Compositional Evaluation and Targeted Data Selection

Speech conveys linguistic content, speaker characteristics, temporal interactions, paralinguistic cues, and acoustic environments. While recent speech captioning models describe these dimensions in natural language, inconsistent attribute coverage and ambiguous omissions hinder systematic analysis across recordings. We introduce SURE-Tagger, a framework that constructs semi-structured speech representations with explicit attribute values, supplementary descriptions, and abstention under insufficient evidence. By integrating specialist observations through language-model reasoning, SURE-Tagger enables speech conditions to be consistently identified and jointly queried across datasets. We further introduce Tag-Bench, combining real recordings with controlled, agentically synthesized speech scenes and verified attribute annotations. On Tag-Bench, SURE-Tagger achieves the highest scores on 25 of 29 evaluated dimensions for real speech and 24 of 29 for synthetic speech, outperforming caption-based baselines across structural and descriptive attributes. Beyond annotation, we use these representations to construct cross-dataset evaluation subsets and reveal condition-specific ASR errors. Using a separate candidate pool, SURE-Tagger-guided selection reduces the overall ASR error rate of Qwen3-ASR-1.7B by 14.3% relative to the unadapted model under a one-hour fine-tuning budget, while caption-guided and random selection increase error in the same setting. These results demonstrate how structured speech representations can connect rich annotation, compositional evaluation, and targeted model improvement.

eess.AS↗

arXiv2026

PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying real-world dynamics remains unclear. Existing benchmark paradigms often suffer from fragmented evaluation, focusing on isolated cognitive stages while overlooking the inherent synergy between perception, reasoning, and physical judgment. The lack of a holistic perspective limits the ability to diagnose whether VLMs can reliably serve as evaluators of physical plausibility in generative content. To address these issues, we introduce PhysVista, a benchmark designed to evaluate physical intelligence in VLMs through a closed cognitive loop framework inspired by the human seeing-reasoning-assessment process. PhysVista restores this loop by jointly evaluating physical state perception, physical dynamics reasoning, and physical plausibility assessment. It further distinguishes event-level reasoning and scale-level reasoning to enable fine-grained analysis of physical understanding. In addition, PhysVista incorporates both real-world and AI-generated videos, allowing evaluation across diverse domains and emerging generative scenarios. Extensive experiments across a diverse set of VLMs reveal substantial limitations in physical reasoning and plausibility assessment, highlighting a persistent gap between visual recognition and genuine physical understanding, and pointing toward more principled designs for physically grounded multimodal intelligence.

cs.CV↗

arXiv2026

SURE-EVAL: A Systematic and Unified Agentic Framework for Reproducible Evaluation

Audio and speech models are released rapidly, but reported scores often conflate model capability with deployment and evaluation choices. The same checkpoint can produce different predictions under different runtimes, hardware, decoding settings, or fallback policies. Even fixed predictions can receive different scores under different normalization and metric implementations. Existing speech benchmarks standardize selected datasets or scoring procedures, but rarely connect heterogeneous model onboarding, controlled inference, and versioned scoring in one executable workflow. We introduce SURE-EVAL, a Systematic and Unified Agentic framework for Reproducible Evaluation of audio and speech systems. A Tool Agent Workflow converts model releases into isolated, verified callable tools. A Main Agent Workflow commits task-specific inference and scoring protocols, then delegates all score-bearing operations to versioned deterministic programs. Each result retains its runtime, protocol, pipeline nodes, predictions, and audit artifacts. Across 18 public releases covering automatic speech recognition, text-to-speech, voice conversion, speaker diarization, speaker-attributed recognition, and multi-task audio understanding, a Codex-only baseline completes 12 models in one shot, while the same agent with the SURE-EVAL Tool Agent Workflow completes all 18. We also conduct unified evaluations over seven ASR test conditions and two TTS subsets. A protocol analysis of three TTS systems finds absolute differences of 0.02-0.52 points between paper-reported and unified results, with the direction varying by model and language. These results show that reproducible evaluation requires controlling both model execution and output scoring.

eess.AS↗

arXiv2026

DAMSEP: Distance-Aware Monaural Source Separation using Multi-RIR Estimation

Although room impulse responses (RIRs) encode source-distance cues, conventional monaural source separation focuses on recovering audio content without estimating source-specific RIRs, losing the associated spatial information. To address this limitation, we propose Distance-Aware Monaural Source Separation using Multi-RIR Estimation (DAMSEP), the first end-to-end framework that is jointly trained for source separation and multi-source RIR estimation from a single-microphone mixture. DAMSEP integrates a separation backbone with shared dereverberation and RIR estimation modules to jointly recover clean sources and source-specific complex convolutive transfer functions under source estimation and reverberant reconstruction objectives, enabling relative near/far ordering through the direct-to-reverberant ratios of the corresponding RIRs. For comprehensive evaluation, we introduce HETMIXR, which spans heterogeneous source content and diverse simulated room conditions with source-specific RIRs and geometric distance annotations. Experiments on HETMIXR demonstrate superior performance in source separation, RIR estimation, and distance ordering. Ablation studies reveal the complementary benefits of source supervision and reverberant reconstruction, while additional evaluations show generalization to single-speaker inputs and mixtures generated using measured RIRs from an unseen room. Our code and dataset are available at https://github.com/Wenanzhi/DAMSEP.

eess.AS↗

arXiv2026

The Impact of Generative AI on Collaborative Open-Source Software Development: Evidence from GitHub Copilot

Generative artificial intelligence (AI) facilitates content production and enhances ideation, with potentially important implications for developer productivity and participation in software development. To explore its impact on collaborative open-source software (OSS) development, we investigate the role of GitHub Copilot, a generative AI pair programmer, in OSS development where multiple distributed developers voluntarily collaborate. Using GitHub's proprietary Copilot usage data, combined with public OSS project data obtained from GitHub, we find that Copilot use increases project-level code contributions by 5.9%. This gain is accompanied by a 3.4% increase in developer coding participation and a 2.1% increase in individual code contributions. However, Copilot use is also associated with an 8% increase in coordination time and more code discussions. This reveals an important tradeoff: While AI expands who can contribute and how much they contribute, it slows coordination in collective development efforts. Despite this tension, the overall effect remains positive, resulting in a net increase in the timely merge of code contributions at the project level. Interestingly, we also find heterogeneous effects across developer roles. Peripheral developers exhibit relatively smaller increases in project-level code contributions and larger increases in coordination time than core developers. Together, our findings highlight the dual effects of AI pair programmers on code contributions and coordination in OSS development and provide implications for how generative AI may reshape the structure of OSS communities over time.

cs.SE↗

arXiv2026

Information-Theoretic Decoupled Prompt Tuning for Continual Learning

Continual learning (CL) aims to incrementally acquire knowledge from sequential data while avoiding catastrophic forgetting. Recently, prompt tuning has attracted increasing attention as an efficient approach for adapting pre-trained models to CL tasks. However, existing prompt design paradigms commonly suffer from retrieval dependence and classifier bias, which make model adaptation sensitive to prompt selection and bias predictions toward newly arrived classes. To address these challenges, we propose Decoupled Prompt Tuning for Continual Learning (DPT4CL), which decouples the CLIP textual prompt into a task-shared prompt distribution and class-specific prompts. The task-shared prompt distribution is derived by optimizing an Information Bottleneck objective to facilitate cross-task knowledge transfer and alleviate classifier bias, while class-specific prompts enhance inter-class separability without relying on explicit prompt retrieval. Furthermore, we establish a unified excess risk bound from an information-theoretic perspective, providing theoretical support for the robust generalization and forgetting mitigation of the proposed framework. Extensive experiments on standard CL benchmarks demonstrate that DPT4CL achieves state-of-the-art performance. The source code is available at https://github.com/Cloudfly-Z/DPT4CL

cs.LG↗

arXiv2026

Drift and Dependence: Layer-wise Information-Theoretic Bounds for Replay-Based Continual Learning

Continual learning must absorb new tasks without erasing old ones, and replay---mixing a small buffer of past examples into current training---is among the most effective remedies for catastrophic forgetting. Yet its generalization behavior is shaped by two coupled effects that existing analyses fold into a single hypothesis-level quantity: finite memory replaces each past distribution with an empirical proxy, and repeated reuse couples the buffer, the current data, and the final hypothesis through a shared optimization trajectory. We develop a layer-wise information-theoretic framework that separates these effects at every depth. Our main result decomposes the expected generalization gap into a replay-induced representation drift and an optimization-dependence term, the latter further resolved into stability, plasticity, interaction, and residual-coupling components. Two refinements make the framework operational. A Wasserstein relaxation of the drift term, valid under support mismatch, yields a depth-dependent drift--sensitivity trade-off whose minimizer identifies which interior layer to stabilize. An SGLD instantiation of the optimization term reduces it to a trajectory-level log-determinant budget, exposing a curvature-aware gradient-alignment statistic that serves as an online diagnostic of task-wise forgetting. Controlled and benchmark experiments confirm the predicted memory scaling, the interior funnel, and the alignment signal's link to forgetting.

cs.LG↗

arXiv2026

LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment: Methods and Results

This paper reviews the LoViF 2026 Challenge on Human-oriented Semantic Image Quality Assessment. This challenge aims to raise a new direction, i.e., how to evaluate the loss of semantic information from the human perspective, intending to promote the development of some new directions, like semantic coding, processing, and semantic-oriented optimization, etc. Unlike existing datasets of quality assessment, we form a dataset of human-oriented semantic quality assessment, termed the SeIQA dataset. This dataset is divided into three parts for this competition: (i) training data: 510 pairs of degraded images and their corresponding ground truth references; (ii) validation data: 80 pairs of degraded images and their corresponding ground-truth references; (iii) testing data: 160 pairs of degraded images and their corresponding ground-truth references. The primary objective of this challenge is to establish a new and powerful benchmark for human-oriented semantic image quality assessment. There are a total of 58 teams registered in this competition, and 6 teams submitted valid solutions and fact sheets for the final testing phase. These submissions achieved state-of-the-art (SOTA) performance on the SeIQA dataset.

cs.CV↗

arXiv2026

Rebuilding Startups: An Empirical Study on Remote Work and Skill Complementarity

Remote work is a common practice of workplace flexibility enabled by digital infrastructure, yet its implications for firms' talent composition and organizational structure remain underexplored. This question is especially important for startups, which often operate with constraints in accessing talent through local labor markets. We focus on skill complementarity, a dimension of talent composition that is critical to startups' early-stage development. By integrating LinkedIn job postings, worker skills, and worker mobility data, we study the impact of remote work on skill complementarity in startups. We find that higher remote work intensity increases firm-level skill complementarity, primarily by helping startups recruit new workers whose skills better match the firms' hiring needs and diversify from the skill sets of existing employees. We further show that this shift in workforce composition carries organizational consequences: remote work is associated with greater organizational hierarchy through increased skill complementarity. These findings suggest that, for startups, remote work is not merely a flexibility policy but a hiring mechanism that helps young firms assemble complementary talent despite resource constraints. At the same time, this may push startups toward more hierarchical structures, which serve as formalized coordination mechanisms to effectively achieve the value of a more complementary workforce.

econ.GN↗

arXiv2026

ME-IQA: Memory-Enhanced Image Quality Assessment via Re-Ranking

Reasoning-induced vision-language models (VLMs) advance image quality assessment (IQA) with textual reasoning, yet their scalar scores often lack sensitivity and collapse to a few values, so-called discrete collapse. We introduce ME-IQA, a plug-and-play, test-time memory-enhanced re-ranking framework. It (i) builds a memory bank and retrieves semantically and perceptually aligned neighbors using reasoning summaries, (ii) reframes the VLM as a probabilistic comparator to obtain pairwise preference probabilities and fuse this ordinal evidence with the initial score under Thurstone's Case V model, and (iii) performs gated reflection and consolidates memory to improve future decisions. This yields denser, distortion-sensitive predictions and mitigates discrete collapse. Experiments across multiple IQA benchmarks show consistent gains over strong reasoning-induced VLM baselines, existing non-reasoning IQA methods, and test-time scaling alternatives.

cs.CV↗

arXiv2026

Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking

Improving vision-language models (VLMs) in the post-training stage typically relies on supervised fine-tuning or reinforcement learning, methods that necessitate costly, human-annotated data. While self-supervised techniques have proven effective for enhancing reasoning capabilities, their application to perceptual domains such as image quality assessment (IQA) remains largely unexplored. In this work, we introduce EvoQuality, a novel framework that enables a VLM to autonomously refine its quality perception capabilities without any ground-truth labels. EvoQuality adapts the principle of self-consistency to the ranking-based nature of IQA. It generates pseudo-labels by performing pairwise majority voting on the VLM's own outputs to establish a consensus on relative quality. These pseudo-rankings are then formulated into a fidelity reward that guides the model's iterative evolution through group relative policy optimization (GRPO). By iteratively leveraging its own predictions, EvoQuality progressively refines the VLM's perceptual capability. Extensive experiments show that EvoQuality boosts the base VLM's zero-shot performance by 31.8% on PLCC across diverse IQA benchmarks. Remarkably, despite being entirely self-supervised, EvoQuality achieves performance that is competitive with, or even surpasses, state-of-the-art supervised VLM-based IQA models, outperforming these models on 5 out of 7 IQA benchmarks. Furthermore, the framework demonstrates significant flexibility, allowing it to be stacked with pre-trained IQA models to bolster generalization on unseen datasets. Codes and checkpoints will be available at https://github.com/bytedance/EvoQuality.

cs.CV↗

arXiv2026

A Unified and Reproducible Experimentation Framework for Speech Understanding

Speech foundation models and Speech LLMs have advanced speech understanding, yet deployment-oriented model selection is hindered by non-comparable evaluations caused by mismatched post-processing, and by training results that are hard to reproduce across data scales and pipelines. We present SURE, a unified experimentation framework that standardizes prediction formats, normalization, and scoring. SURE evaluates strong systems across paradigms, from conventional pipelines to Speech LLMs, on representative tasks under realistic acoustic and linguistic stressors. Beyond evaluation, SURE introduces an agent-assisted training conversion flow that maps paper and code into versioned, runnable training pipelines under a unified protocol on matched open-data subsets. Overall, SURE improves comparability and reproducibility for deployment-oriented evaluation.

eess.AS↗

arXiv2026

DevBench: A Realistic, Developer-Informed Benchmark for Code Generation Models

DevBench is a telemetry-driven benchmark designed to evaluate Large Language Models (LLMs) on realistic code completion tasks. It includes 1,800 evaluation instances across six programming languages and six task categories derived from real developer telemetry and synthesized using generator models from multiple provider families to mitigate single-source bias. Unlike prior benchmarks, it emphasizes ecological validity, avoids training data contamination, and enables detailed diagnostics. The evaluation combines functional correctness, similarity-based metrics, and LLM-judge assessments focused on usefulness and contextual relevance. 9 state-of-the-art models were assessed, with the strongest achieving only 43.5% Pass@1, confirming the benchmark remains challenging and revealing differences in syntactic precision, semantic reasoning, and practical utility. Our benchmark provides actionable insights to guide model selection and improvement, detail that is often missing from other benchmarks but is essential for both practical deployment and targeted model development.

cs.LG↗

arXiv2026

Context and Pixel Aware Large Language Model for Video Quality Assessment

Video quality assessment (VQA) is a challenging research topic with broad applications. Traditional hand-crafted and discriminative learning-based VQA models mainly focus on pixel-level distortions and lack contextual understanding, while recent multimodal large language models (MLLMs) struggle with sensitivity to small distortions or handle quality scoring and description as separate tasks. To address these shortcomings, we introduce CP-LLM: a Context- and Pixel-aware Large Language Model. CP-LLM is a novel multimodal LLM architecture featuring dual vision encoders designed to independently analyze perceptual quality at both high-level (video context) and low-level (pixel distortion) granularity, along with a language decoder that subsequently reasons about the interplay between these aspects. This design enables CP-LLM to simultaneously produce robust quality scores and interpretable quality descriptions, with enhanced sensitivity to pixel distortions (e.g., compression artifacts). Experiment results demonstrate that CP-LLM achieves state-of-the-art cross-dataset performance on VQA benchmarks and superior robustness to pixel distortions.

cs.CV↗

arXiv2026

Prompt-Anchored Vision-Text Distillation for Lifelong Person Re-identification

Lifelong person re-identification (LReID) aims to train a generalizable model with sequentially collected data. However, such models often suffer from semantic drift, limited adaptability, and catastrophic forgetting as new domains emerge. Existing exemplar-free approaches largely rely on visual-only distillation or parameter regularization, while overlooking the potential of auxiliary modalities, such as text, to preserve semantic stability and enable incremental plasticity. We observe that the frozen text encoder in pretrained vision-language models can serve as a stable semantic anchor across domains. To decouple the roles of vision and text, we propose Prompt-Anchored vision-text Distillation (PAD), an asymmetric vision-text framework for semantic alignment and cross-domain generalization. On the textual side, we distill prompts to preserve vision-text alignment under a fixed semantic space, acting as a global semantic reference rather than a dominant learning signal. On the visual side, an EMA-based teacher with an adaptive prompt pool enables domain-wise adaptation by allocating new slots while freezing past ones. Extensive experiments show that PAD substantially outperforms state-of-the-art methods across seen and unseen domains, achieving a strong balance between stability and plasticity. Project page is available at https://github.com/zu-zi/PAD.

cs.CV↗

arXiv2026

Beyond Sharpness: A Flatness Decomposition Framework for Efficient Continual Learning

Continual Learning (CL) aims to enable models to sequentially learn multiple tasks without forgetting previous knowledge. Recent studies have shown that optimizing towards flatter loss minima can improve model generalization. However, existing sharpness-aware methods for CL suffer from two key limitations: (1) they treat sharpness regularization as a unified signal without distinguishing the contributions of its components. and (2) they introduce substantial computational overhead that impedes practical deployment. To address these challenges, we propose FLAD, a novel optimization framework that decomposes sharpness-aware perturbations into gradient-aligned and stochastic-noise components, and show that retaining only the noise component promotes generalization. We further introduce a lightweight scheduling scheme that enables FLAD to maintain significant performance gains even under constrained training time. FLAD can be seamlessly integrated into various CL paradigms and consistently outperforms standard and sharpness-aware optimizers in diverse experimental settings, demonstrating its effectiveness and practicality in CL.

cs.LG↗

arXiv2026

Information-Theoretic Generalization Bounds of Replay-based Continual Learning

Continual learning (CL) has emerged as a dominant paradigm for acquiring knowledge from sequential tasks while avoiding catastrophic forgetting. Although many CL methods have been proposed to show impressive empirical performance, the theoretical understanding of their generalization behavior remains limited, particularly for replay-based approaches. This paper establishes a unified theoretical framework for replay-based CL, deriving a series of information-theoretic generalization bounds that explicitly elucidate the impact of the memory buffer alongside the current task on generalization performance. Specifically, our hypothesis-based bounds capture the trade-off between the number of selected exemplars and the information dependency between the hypothesis and the memory buffer. Our prediction-based bounds yield tighter and computationally tractable upper bounds on the generalization error by leveraging low-dimensional variables. Theoretical analysis is general and broadly applicable to a wide range of learning algorithms, exemplified by stochastic gradient Langevin dynamics (SGLD) as a representative method. Comprehensive experimental evaluations demonstrate the effectiveness of our derived bounds in capturing the generalization dynamics in replay-based CL settings.

cs.LG↗