Searcharxiv⌕ Search

arXiv subjects

Qian Chen

Publications and source records attributed to Qian Chen.

At least 91 records · Page 5Linked to original sources
arXiv2026

Toward Personalized LLM-Powered Agents: Foundations, Evaluation, and Future Directions

Large language models have enabled agentic systems that reason, plan, and interact with tools and environments to accomplish complex tasks. As these agents operate over extended interaction horizons, their effectiveness increasingly depends on adapting behavior to individual users and maintaining continuity across interactions, giving rise to personalized LLM-powered agents (PLAs). In such long-term, user-dependent settings, personalization permeates the entire decision pipeline rather than remaining confined to surface-level response generation. This survey provides a capability-oriented review of personalized LLM-powered agents. Existing work is organized around four interdependent capabilities: profile modeling, memory, planning, and action execution. Using this taxonomy, representative methods are synthesized and analyzed to illustrate how user signals are represented, propagated, and utilized across the agent pipeline, highlighting cross-component interactions and recurring design challenges. Evaluation metrics and benchmarking paradigms tailored to personalized agents are further examined, along with application scenarios ranging from conversational assistants to domain-specific expert systems. By clarifying the design space of personalization in agent systems, this survey provides a structured foundation for developing more user-aligned, adaptive, and deployable LLM-powered agents.

cs.AI↗
arXiv2026

Structure-Dependent Regret and Constraint Violation Bounds for Online Convex Optimization with Time-Varying Constraints

Online convex optimization (OCO) with time-varying constraints is a critical framework for sequential decision-making in dynamic networked systems, where learners must minimize cumulative loss while satisfying regions of feasibility that shift across rounds. Existing theoretical analyses typically treat constraint variation as a monolithic adversarial process, resulting in joint regret and violation bounds that are overly conservative for real-world network dynamics. In this paper, we introduce a structured characterization of constraint variation - smooth drift, periodic cycles, and sparse switching - mapping these classes to common network phenomena such as slow channel fading, diurnal traffic patterns, and discrete maintenance windows. We derive structure-dependent joint bounds that strictly improve upon adversarial rates when the constraint process exhibits regularity. To realize these gains, we propose the Structure-Adaptive Primal-Dual (SA-PD) algorithm, which utilizes observable constraint signals to detect environmental structure online and adapt dual update strategies accordingly. Extensive experiments on synthetic benchmarks and real-world datasets - including online electricity scheduling and transformer load management - demonstrate that SA-PD reduces cumulative constraint violation by up to 53% relative to structure-agnostic baselines while maintaining competitive utility. This work serves as a comprehensive guide for exploiting temporal regularity in constrained online learning for robust network engineering.

cs.LG↗
arXiv2026

More Bang for the Buck: Process Reward Modeling with Entropy-Driven Uncertainty

We introduce the Entropy-Driven Uncertainty Process Reward Model (EDU-PRM), a novel entropy-driven training framework for process reward modeling that enables dynamic, uncertainty-aligned segmentation of complex reasoning steps, eliminating the need for costly manual step annotations. Unlike previous Process Reward Models (PRMs) that rely on static partitioning and human labeling, EDU-PRM automatically anchors step boundaries at tokens with high predictive entropy, effectively capturing intrinsic logical transitions and facilitating efficient exploration of diverse reasoning paths. On the ProcessBench benchmark, EDU-PRM outperforms strong public PRM baselines, such as Math-Shepherd PRM and Omega PRM, and EDU-PRM achieves comparable results with SOTA models while only using 1.5% training data. Furthermore, by leveraging our proposed EDU sampling strategy, we observe accuracy boosts from 64.7% to 67.3% for generative reasoning tasks, accompanied by a reduction of 32% in token usage. These findings underscore the potential of EDU-PRM as a scalable and annotation-efficient paradigm for process supervision in mathematical reasoning, paving the way for more efficient and robust approaches to complex mathematical problem solving.

cs.LG↗
arXiv2026

DianJin-OCR-R1: Enhancing OCR Capabilities via a Reasoning-and-Tool Interleaved Vision-Language Model

Recent advances in vision-language models (VLMs) have enabled end-to-end document parsing and understanding, achieving strong performance on diverse optical character recognition (OCR) tasks. However, VLMs are prone to generate words that do not exist in the input image due to over-reliance on language priors. By contrast, traditional OCR models, whose architectures are tailored for specific recognition tasks, often achieve stronger fine-grained visual perception with fewer hallucinations, but they typically lack the contextual semantic understanding and reasoning capabilities needed in more challenging cases. To bridge this gap, we propose DianJin-OCR-R1, a reasoning-enhanced framework for recognition that trains VLMs in a reasoning-and-tool interleaved paradigm. Our DianJin-OCR-R1 model first recognizes the content in the input image through its own OCR capabilities, and then calls other expert models for extra results as references. After that, it is guided to "look again" at the image and compare its own recognized content with other results to find errors or omissions. Finally, it integrates all available evidence to generate a more accurate output. This design empowers the model to learn how to implicitly re-focus on the visual input and effectively leverage the results of other expert models for better performance. We evaluate our DianJin-OCR-R1 model on ReST and OmniDocBench, where it consistently outperforms both its non-reasoning counterparts and expert models, demonstrating the effectiveness of our method.

cs.CV↗
arXiv2026

SemFuzz: A Semantics-Aware Fuzzing Framework for Network Protocol Implementations

Network protocols are the foundation of modern communication, yet their implementations often contain semantic vulnerabilities stemming from inadequate understanding of specification semantics. Existing gray-box and black-box testing approaches lack semantic modeling of protocols, making it difficult to precisely express testing intent and cover boundary conditions. Moreover, they typically rely on coarse-grained oracles such as crashes, which are inadequate for identifying deep semantic vulnerabilities. To address these limitations, we present a semantics-aware fuzzing framework, SemFuzz. The framework leverages large language models to extract structured semantic rules from RFC documents and generates test cases that intentionally violate these rules to encode specific testing intents. It then detects deep semantic vulnerabilities by comparing the observed responses with the expected ones. Evaluation on seven widely deployed protocol implementations shows that SemFuzz identified sixteen potential vulnerabilities, ten of which have been confirmed. Among the confirmed vulnerabilities, five were previously unknown and four have been assigned CVEs. These results demonstrate the effectiveness of SemFuzz in detecting semantic vulnerabilities.

cs.CR↗
arXiv2026

Simultaneous super-resolution and optical sectioning with four-beam interference structured illumination microscopy (4I-SIM)

Structured illumination microscopy (SIM) has emerged as a widely adopted super-resolution fluorescence imaging modality, offering high speed, low phototoxicity, large field-of-view, and compatibility with conventional probes. However, when applied to thick or scattering specimens, conventional two-dimensional SIM (2D-SIM) suffers from the missing cone problem in its optical transfer function, resulting in prominent out-of-focus background and severe reconstruction artifacts that compromise image fidelity. Here, we present four-beam interference structured illumination microscopy (4I-SIM), which introduces additional interference orders to expand lateral frequency support and compensate the axial missing cone simultaneously. This strategy achieves artifact-free super-resolution with intrinsic optical sectioning, effectively overcoming the fundamental limitation of 2D-SIM without additional acquisition overhead. Experimental validation across diverse thick fixed and live specimens demonstrates that 4I-SIM delivers nearly twofold lateral resolution enhancement and substantially improved sectioning compared with its 2D counterpart, achieving lateral and axial resolutions of 103 nm and 336 nm, respectively. In particular, 4I-SIM reveals mitochondrial remodeling and apoptosis under high-glucose stress with millisecond temporal resolution -- features that remain obscured with conventional SIM. With minimal hardware modification, low phototoxicity, and open-source reconstruction tools, 4I-SIM establishes a practical and reproducible platform for simultaneous super-resolution and optical sectioning imaging in complex biological environments.

eess.IV↗
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

Accelerating Single-Pass SGD for Generalized Linear Prediction

We study generalized linear prediction under a streaming setting, where each iteration uses only one fresh data point for a gradient-level update. While momentum is well-established in deterministic optimization, a fundamental open question is whether it can accelerate such single-pass non-quadratic stochastic optimization. We propose the first algorithm that successfully incorporates momentum via a novel data-dependent proximal method, achieving dual-momentum acceleration. Our derived excess risk bound decomposes into three components: an improved optimization error, a minimax optimal statistical error, and a higher-order model-misspecification error. The proof handles mis-specification via a fine-grained stationary analysis of inner updates, while localizing statistical error through a two-phase outer-loop analysis. As a result, we resolve the open problem posed by Jain et al. [2018a] and demonstrate that momentum acceleration is more effective than variance reduction for generalized linear prediction in the streaming setting.

cs.LG↗
arXiv2026

SlimCaching: Edge Caching of Mixture-of-Experts for Distributed Inference

Mixture-of-Experts (MoE) models improve the scalability of large language models (LLMs) by activating only a small subset of relevant experts per input. However, the sheer number of expert networks in an MoE model introduces a significant storage/memory burden for an edge device. To address this challenge, we consider a scenario where experts are dispersed across an edge network for distributed inference. Based on the popular Top-$K$ expert selection strategy, we formulate a latency minimization problem by optimizing expert caching on edge servers under storage constraints. When $K=1$, the problem reduces to a monotone submodular maximization problem with knapsack constraints, for which we design a greedy-based algorithm with a $(1 - 1/e)$-approximation guarantee. For the general case where $K\geq1$, expert co-activation within the same MoE layer introduces non-submodularity, which renders greedy methods ineffective. To tackle this issue, we propose a successive greedy decomposition method to decompose the original problem into a series of subproblems, with each being solved by a dynamic programming approach. Furthermore, we design an accelerated algorithm based on the max-convolution technique to obtain the approximate solution with a provable guarantee in polynomial time. Simulation results on various MoE models demonstrate that our method significantly reduces inference latency compared to existing baselines.

cs.LG↗
arXiv2026

RRPO: Robust Reward Policy Optimization for LLM-based Emotional TTS

Differentiable reinforcement learning (RL) frameworks like DiffRO offer a powerful approach for controllable text-to-speech (TTS), but are vulnerable to reward hacking, particularly for nuanced tasks like emotion control. The policy model can exploit a vanilla Reward Model (RM) by generating acoustic artifacts to achieve spurious rewards, but at the cost of degrading perceptual quality. To address this, we propose Robust Reward Policy Optimization (RRPO), a novel framework that employs a hybrid regularization scheme. This scheme develops a robust RM whose reward signal is more reliably aligned with human perception, compelling the policy to abandon detrimental shortcuts and instead learn the complex features of genuine emotions. Our ablation study confirms the enhanced robustness of our RM, as evidenced by its strong cross-lingual generalization. The subjective evaluation demonstrates that this robust RM effectively mitigates reward hacking, leading to significant improvements in both emotional expressiveness and naturalness over all baselines. Demo page: https://lrwinr.github.io/RRPO-CosyVoice.

cs.SD↗
arXiv2026

Eliminating stability hallucinations in llm-based tts models via attention guidance

This paper focuses on resolving stability hallucinations (e.g., repetitive or omitted speech) in LLM-based Text-to-Speech (TTS) models by improving and leveraging the attention mechanism. First, we analyzed the alignment mechanism between text tokens and speech tokens in LLMs. We then proposed a metric termed the Optimal Alignment Score (OAS), which employs the Viterbi algorithm to evaluate text-speech alignment quality. Subsequently, OAS was integrated into the training of CosyVoice2 to assist LLMs in learning continuous, stable alignment. Additionally, the pre-trained attention value is employed to guide the training of the student CosyVoice2 via chain-of-thought (CoT), which further reduces stability hallucinations in synthesized speech. Experiments on the Seed-TTS-Eval and CV3-Eval test sets demonstrate that the proposed methods can effectively reduce the stability hallucinations of CosyVoice2 without introducing additional negative effects. The appendix is available at https://wsmzzz.github.io/llm_attn.

cs.SD↗
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

Network function computation with vector linear target function and security function

In this paper, we study the problem of securely computing a function over a network, where both the target function and the security function are vector linear. The network is modeled as a directed acyclic graph. A sink node wishes to compute a function of messages generated by multiple distributed sources, while an eavesdropper can access exactly one wiretap set from a given collection. The eavesdropper must be prevented from obtaining any information about a specified security function of the source messages. The secure computing capacity is the maximum average number of times that the target function can be securely computed with zero error at the sink node with the given collection of wiretap sets and security function for one use of the network. We establish two upper bounds on this capacity, which hold for arbitrary network topologies and for any vector linear target and security functions. These bounds generalize existing results and also lead to a new upper bound when the target function is the sum over a finite field. For the lower bound, when the target function is the sum, we extend an existing method, which transforms a non-secure network code into a secure one, to the case where the security function is vector linear. Furthermore, for a particular class of networks and a vector linear target function, we characterize the required properties of the global encoding matrix to construct a secure vector linear network code.

cs.IT↗
arXiv2026

SADER: Structure-Aware Diffusion Framework with DEterministic Resampling for Multi-Temporal Remote Sensing Cloud Removal

Cloud contamination severely degrades the usability of remote sensing imagery and poses a fundamental challenge for downstream Earth observation tasks. Recently, diffusion-based models have emerged as a dominant paradigm for remote sensing cloud removal due to their strong generative capability and stable optimization. However, existing diffusion-based approaches often suffer from limited sampling efficiency and insufficient exploitation of structural and temporal priors in multi-temporal remote sensing scenarios. In this work, we propose SADER, a structure-aware diffusion framework for multi-temporal remote sensing cloud removal. SADER first develops a scalable Multi-Temporal Conditional Diffusion Network (MTCDN) to fully capture multi-temporal and multimodal correlations via temporal fusion and hybrid attention. Then, a cloud-aware attention loss is introduced to emphasize cloud-dominated regions by accounting for cloud thickness and brightness discrepancies. In addition, a deterministic resampling strategy is designed for continuous diffusion models to iteratively refine samples under fixed sampling steps by replacing outliers through guided correction. Extensive experiments on multiple multi-temporal datasets demonstrate that SADER consistently outperforms state-of-the-art cloud removal methods across all evaluation metrics. The code of SADER is publicly available at https://github.com/zyfzs0/SADER.

cs.CV↗
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

The development of a high granular crystal calorimeter prototype of VLAST

Very Large Area gamma-ray Space Telescope (VLAST) is the next-generation flagship space observatory for high-energy gamma-ray detection proposed by China. The observation energy range covers from MeV to TeV and beyond, with acceptance of 10 m^2sr. The calorimeter serves as a crucial subdetector of VLAST, responsible for high-precision energy measurement and electron/proton discrimination. This discrimination capability is essential for accurately identifying gamma-ray events among the background of charged particles. To accommodate such an extensive energy range, a high dynamic range readout scheme employing dual avalanche photodiodes (APDs) has been developed, achieving a remarkable dynamic range of 10^6. Furthermore, a high granular prototype based on bismuth germanate (BGO) cubic scintillation crystals has been developed. This high granularity enables detailed imaging of the particle showers, improving both energy resolution and particle identification. The prototype's performance is evaluated through cosmic ray testing, providing valuable data for optimizing the final calorimeter design for VLAST.

physics.ins-det↗
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

SlingBAG Pro: Accelerating point cloud-based iterative reconstruction for 3D photoacoustic imaging with arbitrary array geometries

High-quality three-dimensional (3D) photoacoustic imaging (PAI) is gaining increasing attention in clinical applications. To address the challenges of limited space and high costs, irregular geometric transducer arrays that conform to specific imaging regions are promising for achieving high-quality 3D PAI with fewer transducers. However, traditional iterative reconstruction algorithms struggle with irregular array configurations, suffering from high computational complexity, substantial memory requirements, and lengthy reconstruction times. In this work, we introduce SlingBAG Pro, an advanced reconstruction algorithm based on the point cloud iteration concept of the Sliding ball adaptive growth (SlingBAG) method, while extending its compatibility to arbitrary array geometries. SlingBAG Pro maintains high reconstruction quality, reduces the number of required transducers, and employs a hierarchical optimization strategy that combines zero-gradient filtering with progressively increased temporal sampling rates during iteration. This strategy rapidly removes redundant spatial point clouds, accelerates convergence, and significantly shortens overall reconstruction time. Compared to the original SlingBAG algorithm, SlingBAG Pro achieves up to a 2.2-fold speed improvement in point cloud-based 3D PA reconstruction under irregular array geometries. The proposed method is validated through both simulation and in vivo mouse experiments, and the source code is publicly available at https://github.com/JaegerCQ/SlingBAG_Pro.

cs.CV↗