arXiv subjects

Wen Wang

Publications and source records attributed to Wen Wang.

At least 55 records · Page 3Linked to original sources

arXiv2026

Breaking Degradation Coupling: A Structural Entropy Guided Decoupled Framework and Benchmark for Infrared Enhancement

Thermal infrared image enhancement aims to restore high-quality images from complex compound degradations. Existing all-in-one approaches typically employ a single shared backbone to handle diverse degradations, which causes gradient interference and parameter competition. To address this, we propose a Structural Entropy-Guided Decoupled (SEGD) Framework. Unlike unified modeling paradigms, SEGD decomposes compound degradations into independent sub-processes and models them in a divide-and-conquer manner through Degradation-Specific Residual Modules (DRMs). Each DRM focuses on residual estimation for a specific degradation, enabling task decoupling while remaining jointly trainable, which mitigates parameter contention. A Degradation-Aware Evidential Network further estimates degradation type and intensity, providing priors that adaptively regulate DRM restoration strength. To handle compound cases, DRMs are composed in varying orders to form multiple restoration paths, from which the most informative features are aggregated under a structural-entropy criterion, yielding decoder-ready representations with structural fidelity and degradation awareness. Integrating divide-and-conquer restoration, evidential perception, and entropy-guided adaptation, SEGD achieves fine-grained and interpretable enhancement. We also construct a nighttime TIR benchmark for evaluation under real low-light conditions. Experimental results demonstrate that SEGD surpasses state-of-the-art methods while achieving higher efficiency with fewer parameters.

cs.CV↗

arXiv2026

Generative Learning Enhanced Intelligent Resource Management for Cell-Free Delay Deterministic Communications

Cell-free multiple-input multiple-output (CF-MIMO) architecture significantly enhances wireless network performance, offering a promising solution for delay-sensitive applications. This paper investigates the resource allocation problem in CF-MIMO systems, aiming to maximize energy efficiency (EE) while satisfying delay violation rate constraint. We design a Proximal Policy Optimization (PPO) with a primal-dual method to solve it. To address the low sample efficiency and safety risks caused by cold-start of the designed safe deep reinforcement learning (DRL) method, we propose a novel offline pretraining framework based on virtual constrained Markov decision process (CMDP) modeling. The virtual CMDP consists of reward and cost prediction module, initial-state distribution module and state transition module. Notably, we propose an evidence-aware conditional Gaussian Mixture Model (EA-CGMM) inference approach to mitigate data sparsity and distribution drift issues in state transition modeling. Simulation results demonstrate the effectiveness of CMDP modeling and validate the safety and efficiency of the proposed pretraining framework. Specifically, compared with non-pretrained baseline, the agent pretrained through our proposed framework achieves twice the initial EE and maintains a low delay constraint violation rate of $1\%$, while ultimately converging to an EE that is $4.7\%$ higher with a $50\%$ reduction in exploration steps. Additionally, our proposed pretraining framework implementation exhibits comparable performance to the SOTA diffusion model-based implementation, while achieving a $14$-fold reduction in computational complexity.

cs.IT↗

arXiv2026

Dual-Axis Generative Reward Model Toward Semantic and Turn-taking Robustness in Interactive Spoken Dialogue Models

Achieving seamless, human-like interaction remains a key challenge for full-duplex spoken dialogue models (SDMs). Reinforcement learning (RL) has substantially enhanced text- and vision-language models, while well-designed reward signals are crucial for the performance of RL. We consider RL a promising strategy to address the key challenge for SDMs. However, a fundamental barrier persists: prevailing automated metrics for assessing interaction quality rely on superficial proxies, such as behavioral statistics or timing-prediction accuracy, failing to provide reliable reward signals for RL. On the other hand, human evaluations, despite their richness, remain costly, inconsistent, and difficult to scale. We tackle this critical barrier by proposing a Dual-Axis Generative Reward Model, which is trained to understand complex interaction dynamics using a detailed taxonomy and an annotated dataset, produces a single score and, crucially, provides separate evaluations for semantic quality and interaction timing. Such dual outputs furnish precise diagnostic feedback for SDMs and deliver a dependable, instructive reward signal suitable for online reinforcement learning. Our model achieves state-of-the-art performance on interaction-quality assessment across a wide spectrum of datasets, spanning synthetic dialogues and complex real-world interactions.

cs.AI↗

arXiv2026

WavAlign: Enhancing Intelligence and Expressiveness in Spoken Dialogue Models via Adaptive Hybrid Post-Training

End-to-end spoken dialogue models have garnered significant attention because they offer a higher potential ceiling in expressiveness and perceptual ability than cascaded systems. However, the intelligence and expressiveness of current open-source spoken dialogue models often remain below expectations. Motivated by the success of online reinforcement learning(RL) in other domains, one might attempt to directly apply preference optimization to spoken dialogue models, yet this transfer is non-trivial. We analyze these obstacles from the perspectives of reward modeling and rollout sampling, focusing on how sparse preference supervision interacts with dense speech generation under shared-parameter updates. Based on the analysis, we propose a modality-aware adaptive post-training recipe that makes RL practical for spoken dialogue: it constrains preference updates to the semantic channel and improves acoustic behavior via explicit anchoring, while dynamically regulating their mixture from rollout statistics to avoid unreliable preference gradients. We evaluate the method across multiple spoken dialogue benchmarks and representative architectures, and observe consistent improvements in semantic quality and speech expressiveness.

cs.AI↗

arXiv2026

GenesisFunc: Multi-Agent Data Generation for Accurate and Generalizable Function-Calling

Large Language Models (LLMs) extend their capabilities through function-calling (FC), which relies on training data with high quality, diversity, and broad coverage of scenario. However, obtaining and annotating real function-calling data is challenging, while synthetic data from existing pipelines often suffers from unreliable APIs, limited tool scalability, insufficient diversity, and weak quality control. To address these, we present GenesisFunc, an automated pipeline for generating FC training data. Starting from reliable tools in widely used public benchmarks, our GenesisFunc employs a multi-agent framework to support a dialogue generation system that produces conversations spanning diverse scenarios, while maintaining both diversity and quality throughout the process. The accuracy of the data is further reinforced through a multi-stage evaluation system. We fine-tune an 8B LLM on the synthetic dataset and show through extensive experiments that it outperforms similarly sized open-source models in in-domain FC performance and out-of-domain generalization, while reaching FC capabilities comparable to some of the latest API-based models. In addition, our method demonstrates strong potential to scale effectively across downstream tools, underscoring its real-world applicability.

cs.CL↗

arXiv2026

Preserving Source Video Realism: High-Fidelity Face Swapping for Cinematic Quality

Video face swapping is crucial in film and entertainment production, where achieving high fidelity and temporal consistency over long and complex video sequences remains a significant challenge. Inspired by recent advances in reference-guided image editing, we explore whether rich visual attributes from source videos can be similarly leveraged to enhance both fidelity and temporal coherence in video face swapping. Building on this insight, this work presents LivingSwap, the first video reference guided face swapping model. Our approach employs keyframes as conditioning signals to inject the target identity, enabling flexible and controllable editing. By combining keyframe conditioning with video reference guidance, the model performs temporal stitching to ensure stable identity preservation and high-fidelity reconstruction across long video sequences. To address the scarcity of data for reference-guided training, we construct a paired face-swapping dataset, Face2Face, and further reverse the data pairs to ensure reliable ground-truth supervision. Extensive experiments demonstrate that our method achieves state-of-the-art results, seamlessly integrating the target identity with the source video's expressions, lighting, and motion, while significantly reducing manual effort in production workflows. Project webpage: https://aim-uofa.github.io/LivingSwap

cs.CV↗

arXiv2026

PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation

Video-to-Audio (V2A) generation requires balancing four critical perceptual dimensions: semantic consistency, audio-visual temporal synchrony, aesthetic quality, and spatial accuracy; yet existing methods suffer from objective entanglement that conflates competing goals in single loss functions and lack human preference alignment. We introduce PrismAudio, the first framework to integrate Reinforcement Learning into V2A generation with specialized Chain-of-Thought (CoT) planning. Our approach decomposes monolithic reasoning into four specialized CoT modules (Semantic, Temporal, Aesthetic, and Spatial CoT), each paired with targeted reward functions. This CoT-reward correspondence enables multidimensional RL optimization that guides the model to jointly generate better reasoning across all perspectives, solving the objective entanglement problem while preserving interpretability. To make this optimization computationally practical, we propose Fast-GRPO, which employs hybrid ODE-SDE sampling that dramatically reduces the training overhead compared to existing GRPO implementations. We also introduce AudioCanvas, a rigorous benchmark that is more distributionally balanced and covers more realistically diverse and challenging scenarios than existing datasets, with 300 single-event classes and 501 multi-event samples. Experimental results demonstrate that PrismAudio achieves state-of-the-art performance across all four perceptual dimensions on both the in-domain VGGSound test set and out-of-domain AudioCanvas benchmark. The project page is available at https://PrismAudio.github.io.

cs.SD↗

arXiv2026

Attainable forms of lower spectra

Let $d\in\mathbb{N}$ and $φ\colon(0,1)\to[0,d]$. We prove there exists a set $F\subset\mathbb{R}^d$ whose lower spectrum $\operatorname{dim}^θ_{\mathrm{L}} F$ satisfies $(1-θ)\operatorname{dim}^θ_{\mathrm{L}} F = φ(θ)$ for all $θ\in(0,1)$ if and only if for all $λ,θ\in(0,1)$, \begin{equation*} φ(θ) \leq φ(λθ) - θφ(λ) \leq (1-θ) d. \end{equation*} We also obtain a similar classification result for $\underline{\operatorname{dim}}^θ_{\mathrm{L}} F$. In contrast to the case for Assouad spectra, it is insufficient to consider homogeneous (or uniform) sets. Instead, we follow the approach introduced by Orgoványi--Rutar in arXiv:2510.07013 and proceed via a more general classification result for appropriate two-scale branching functions.

math.CA↗

arXiv2026

MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models

Recent advances in multimodal large language models (MLLMs) have catalyzed transformative progress in affective computing, enabling models to exhibit emergent emotional intelligence. Despite substantial methodological progress, current emotional benchmarks remain limited, as it is still unknown: (a) the generalization abilities of MLLMs across distinct scenarios, and (b) their reasoning capabilities to identify the triggering factors behind emotional states. To bridge these gaps, we present \textbf{MME-Emotion}, a systematic benchmark that assesses both emotional understanding and reasoning capabilities of MLLMs, enjoying \textit{scalable capacity}, \textit{diverse settings}, and \textit{unified protocols}. As the largest emotional intelligence benchmark for MLLMs, MME-Emotion contains over 6,000 curated video clips with task-specific questioning-answering (QA) pairs, spanning broad scenarios to formulate eight emotional tasks. It further incorporates a holistic evaluation suite with hybrid metrics for emotion recognition and reasoning, analyzed through a multi-agent system framework. Through a rigorous evaluation of 20 advanced MLLMs, we uncover both their strengths and limitations, yielding several key insights: \ding{182} Current MLLMs exhibit unsatisfactory emotional intelligence, with the best-performing model achieving only $39.3\%$ recognition score and $56.0\%$ Chain-of-Thought (CoT) score on our benchmark. \ding{183} Generalist models (\emph{e.g.}, Gemini-2.5-Pro) derive emotional intelligence from generalized multimodal understanding capabilities, while specialist models (\emph{e.g.}, R1-Omni) can achieve comparable performance through domain-specific post-training adaptation. By introducing MME-Emotion, we hope that it can serve as a foundation for advancing MLLMs' emotional intelligence in the future.

cs.CV↗

arXiv2026

Generalised lower Assouad-type dimensions and their interpolations

This paper investigates the analytic and structural properties of the $ϕ$-lower Assouad dimension, a generalized notion extending the lower Assouad dimension. We establish the equivalence of $ϕ$-lower Assouad dimensions with respect to the dimension functions, prove analytic properties related to the regularity of the $ϕ$-lower dimension, and analyse the role of rate windows in this context. Furthermore, we explore both positive and negative interpolation properties of the $ϕ$-lower dimension by presenting corresponding theorems that delineate these behaviors.

math.CA↗

arXiv2026

Improving Diffusion Language Model Decoding through Joint Search in Generation Order and Token Space

Diffusion Language Models (DLMs) offer order-agnostic generation that can explore many possible decoding trajectories. However, current decoding methods commit to a single trajectory, limiting exploration in trajectory space. We introduce Order-Token Search to explore this space through jointly searching over generation order and token values. Its core is a likelihood estimator that scores denoising actions, enabling stable pruning and efficient exploration of diverse trajectories. Across mathematical reasoning and coding benchmarks, Order-Token Search consistently outperforms baselines on GSM8K, MATH500, Countdown, and HumanEval (3.1%, 3.8%, 7.9%, and 6.8% absolute over backbone), matching or surpassing diffu-GRPO post-trained d1-LLaDA. Our work establishes joint search as a key component for advancing decoding in DLMs.

cs.CL↗

arXiv2026

Joint Optimization of Latency and Accuracy for Split Federated Learning in User-Centric Cell-Free MIMO Networks

This paper proposes a user-centric split federated learning (UCSFL) framework for user-centric cell-free multiple-input multiple-output (CF-MIMO) networks to support split federated learning (SFL). In the proposed UCSFL framework, users deploy split sub-models locally, while complete models are maintained and updated at access point (AP)-side distributed processing units (DPUs), followed by a two-level aggregation procedure across DPUs and the central processing unit (CPU). Under standard machine learning (ML) assumptions, we provide a theoretical convergence analysis for UCSFL, which reveals that the AP-cluster size is a key factor influencing model training accuracy. Motivated by this result, we introduce a new performance metric, termed the latency-to-accuracy ratio, defined as the ratio of a user's per-iteration training latency to the weighted size of its AP cluster. Based on this metric, we formulate a joint optimization problem to minimize the maximum latency-to-accuracy ratio by jointly optimizing uplink power control, downlink beamforming, model splitting, and AP clustering. The resulting problem is decomposed into two sub-problems operating on different time scales, for which dedicated algorithms are developed to handle the short-term and long-term optimizations, respectively. Simulation results verify the convergence of the proposed algorithms and demonstrate that UCSFL effectively reduces the latency-to-accuracy ratio of the VGG16 model compared with baseline schemes. Moreover, the proposed framework adaptively adjusts splitting and clustering strategies in response to varying communication and computation resources. An MNIST-based handwritten digit classification example further shows that UCSFL significantly accelerates the convergence of the VGG16 model.

eess.SP↗

arXiv2026

FGGM: Fisher-Guided Gradient Masking for Continual Learning

Catastrophic forgetting impairs the continuous learning of large language models. We propose Fisher-Guided Gradient Masking (FGGM), a framework that mitigates this by strategically selecting parameters for updates using diagonal Fisher Information. FGGM dynamically generates binary masks with adaptive thresholds, preserving critical parameters to balance stability and plasticity without requiring historical data. Unlike magnitude-based methods such as MIGU, our approach offers a mathematically principled parameter importance estimation. On the TRACE benchmark, FGGM shows a 9.6% relative improvement in retaining general capabilities over supervised fine-tuning (SFT) and a 4.4% improvement over MIGU on TRACE tasks. Additional analysis on code generation tasks confirms FGGM's superior performance and reduced forgetting, establishing it as an effective solution.

cs.LG↗

arXiv2026

Fun-Audio-Chat Technical Report

Recent advancements in joint speech-text models show great potential for seamless voice interactions. However, existing models face critical challenges: temporal resolution mismatch between speech tokens (25Hz) and text tokens (~3Hz) dilutes semantic information, incurs high computational costs, and causes catastrophic forgetting of text LLM knowledge. We introduce Fun-Audio-Chat, a Large Audio Language Model addressing these limitations via two innovations from our previous work DrVoice. First, Dual-Resolution Speech Representations (DRSR): the Shared LLM processes audio at efficient 5Hz (via token grouping), while the Speech Refined Head generates high-quality tokens at 25Hz, balancing efficiency (~50% GPU reduction) and quality. Second, Core-Cocktail Training, a two-stage fine-tuning with intermediate merging that mitigates catastrophic forgetting. We then apply Multi-Task DPO Training to enhance robustness, audio understanding, instruction-following and voice empathy. This multi-stage post-training enables Fun-Audio-Chat to retain text LLM knowledge while gaining powerful audio understanding, reasoning, and generation. Unlike recent LALMs requiring large-scale audio-text pre-training, Fun-Audio-Chat leverages pre-trained models and extensive post-training. Fun-Audio-Chat 8B and MoE 30B-A3B achieve competitive performance on Speech-to-Text and Speech-to-Speech tasks, ranking top among similar-scale models on Spoken QA benchmarks. They also achieve competitive to superior performance on Audio Understanding, Speech Function Calling, Instruction-Following and Voice Empathy. We develop Fun-Audio-Chat-Duplex, a full-duplex variant with strong performance on Spoken QA and full-duplex interactions. We open-source Fun-Audio-Chat-8B with training and inference code, and provide an interactive demo, at https://github.com/FunAudioLLM/Fun-Audio-Chat .

cs.CL↗

arXiv2026

Beyond Hard Masks: Progressive Token Evolution for Diffusion Language Models

Diffusion Language Models (DLMs) offer a promising alternative for language modeling by enabling parallel decoding through iterative refinement. However, most DLMs rely on hard binary masking and discrete token assignments, which hinder the revision of early decisions and underutilize intermediate probabilistic representations. In this paper, we propose EvoToken-DLM, a novel diffusion-based language modeling approach that replaces hard binary masks with evolving soft token distributions. EvoToken-DLM enables a progressive transition from masked states to discrete outputs, supporting revisable decoding. To effectively support this evolution, we introduce continuous trajectory supervision, which aligns training objectives with iterative probabilistic updates. Extensive experiments across multiple benchmarks show that EvoToken-DLM consistently achieves superior performance, outperforming strong diffusion-based and masked DLM baselines. Project webpage: https://aim-uofa.github.io/EvoTokenDLM.

cs.CL↗

arXiv2026

MATS: An Audio Language Model under Text-only Supervision

Large audio-language models (LALMs), built upon powerful Large Language Models (LLMs), have exhibited remarkable audio comprehension and reasoning capabilities. However, the training of LALMs demands a large corpus of audio-language pairs, which requires substantial costs in both data collection and training resources. In this paper, we propose \textbf{MATS}, an audio-language multimodal LLM designed to handle \textbf{M}ultiple \textbf{A}udio task using solely \textbf{T}ext-only \textbf{S}upervision. By leveraging pre-trained audio-language alignment models such as CLAP, we develop a text-only training strategy that projects the shared audio-language latent space into LLM latent space, endowing the LLM with audio comprehension capabilities without relying on audio data during training. To further bridge the modality gap between audio and language embeddings within CLAP, we propose the \textbf{S}trongly-rel\textbf{a}ted \textbf{n}oisy \textbf{t}ext with \textbf{a}udio (\textbf{Santa}) mechanism. Santa maps audio embeddings into CLAP language embedding space while preserving essential information from the audio input. Extensive experiments demonstrate that MATS, despite being trained exclusively on text data, achieves competitive performance compared to recent LALMs trained on large-scale audio-language pairs. The code is publicly available in \href{https://github.com/wangwen-banban/MATS}{https://github.com/wangwen-banban/MATS}.

cs.SD↗

arXiv2026

SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models

The Speaker Diarization and Recognition (SDR) task aims to predict "who spoke when and what" within an audio clip, which is a crucial task in various real-world multi-speaker scenarios such as meeting transcription and dialogue systems. Existing SDR systems typically adopt a cascaded framework, combining multiple modules such as speaker diarization (SD) and automatic speech recognition (ASR). The cascaded systems suffer from several limitations, such as error propagation, difficulty in handling overlapping speech, and lack of joint optimization for exploring the synergy between SD and ASR tasks. To address these limitations, we introduce SpeakerLM, a unified multimodal large language model for SDR that jointly performs SD and ASR in an end-to-end manner. Moreover, to facilitate diverse real-world scenarios, we incorporate a flexible speaker registration mechanism into SpeakerLM, enabling SDR under different speaker registration settings. SpeakerLM is progressively developed with a multi-stage training strategy on large-scale real data. Extensive experiments show that SpeakerLM demonstrates strong data scaling capability and generalizability, outperforming state-of-the-art cascaded baselines on both in-domain and out-of-domain public SDR benchmarks. Furthermore, experimental results show that the proposed speaker registration mechanism effectively ensures robust SDR performance of SpeakerLM across diverse speaker registration conditions and varying numbers of registered speakers.

cs.SD↗

arXiv2025

DrVoice: Parallel Speech-Text Voice Conversation Model via Dual-Resolution Speech Representations

Recent studies on end-to-end (E2E) speech generation with large language models (LLMs) have attracted significant community attention, with multiple works extending text-based LLMs to generate discrete speech tokens. Existing E2E approaches primarily fall into two categories: (1) Methods that generate discrete speech tokens independently without incorporating them into the LLM's autoregressive process, resulting in text generation being unaware of concurrent speech synthesis. (2) Models that generate interleaved or parallel speech-text tokens through joint autoregressive modeling, enabling mutual modality awareness during generation. This paper presents DrVoice, a parallel speech-text voice conversation model based on joint autoregressive modeling, featuring dual-resolution speech representations. Notably, while current methods utilize mainly 12.5Hz input audio representation, our proposed dual-resolution mechanism reduces the input frequency for the LLM to 5Hz, significantly reducing computational cost and alleviating the frequency discrepancy between speech and text tokens and in turn better exploiting LLMs' capabilities. Experimental results demonstrate that DrVoice-7B establishes new state-of-the-art (SOTA) on prominent speech benchmarks including OpenAudioBench, VoiceBench, UltraEval-Audio and Big Bench Audio, making it a leading open-source speech foundation model in ~7B models.

cs.CL↗