arXiv subjects

Jun Chen

Publications and source records attributed to Jun Chen.

At least 91 records · Page 5Linked to original sources

arXiv2026

Constructive Approaches to Perception-Aware Lossy Source Coding: Information-Theoretic Guidelines

Perception-aware lossy source coding has attracted significant recent interest. It augments the classical distortion criterion with an explicit perception constraint, thereby enabling more refined control over fidelity and perceptual quality. Despite rapid progress, the diversity of rate-distortion-perception formulations and their underlying assumptions remains poorly understood by many practitioners. In particular, there is often a tendency to rely heavily on the expressive power of deep neural networks and generative models without clear theoretical guidance, using fundamental limits merely as performance benchmarks rather than as sources of design insight. This tutorial paper aims to bridge this gap by surveying information-theoretic principles that can be leveraged to develop constructive approaches to perception-aware lossy source coding. We distill practical guidelines implied by rate-distortion-perception theory and demonstrate how they inform the design of implementable coding schemes. A simple unit-circle example is used as a pedagogical tool to illustrate key ideas, architectural principles, and tradeoffs in an intuitive and unified manner. Both one-shot and asymptotic settings are examined to highlight conceptual similarities and operational differences. We also clarify the role of common randomness and the notion of universal representation, and elucidate the connections between perception-aware and conventional lossy source coding. Overall, this tutorial provides a principled foundation for developing perception-aware compression systems that go beyond black-box model design.

cs.IT↗

arXiv2026

UniBlendNet: Unified Global, Multi-Scale, and Region-Adaptive Modeling for Ambient Lighting Normalization

Ambient Lighting Normalization (ALN) aims to restore images degraded by complex, spatially varying illumination conditions. Existing methods, such as IFBlend, leverage frequency-domain priors to model illumination variations, but still suffer from limited global context modeling and insufficient spatial adaptivity, leading to suboptimal restoration in challenging regions. In this paper, we propose UniBlendNet, a unified framework for ambient lighting normalization that jointly models global illumination, multi-scale structures, and region-adaptive refinement. Specifically, we enhance global illumination understanding by integrating a UniConvNet-based module to capture long-range dependencies. To better handle complex lighting variations, we introduce a Scale-Aware Aggregation Module (SAAM) that performs pyramid-based multi-scale feature aggregation with dynamic reweighting. Furthermore, we design a mask-guided residual refinement mechanism to enable region-adaptive correction, allowing the model to selectively enhance degraded regions while preserving well-exposed areas. This design effectively improves illumination consistency and structural fidelity under complex lighting conditions. Extensive experiments on the NTIRE Ambient Lighting Normalization benchmark demonstrate that UniBlendNet consistently outperforms the baseline IFBlend and achieves improved restoration quality, while producing visually more natural and stable restoration results.

cs.CV↗

arXiv2026

Bilevel Late Acceptance Hill Climbing for the Electric Capacitated Vehicle Routing Problem

This paper tackles the Electric Capacitated Vehicle Routing Problem (E-CVRP) through a bilevel optimization framework that handles routing and charging decisions separately or jointly depending on the search stage. By analyzing their interaction, we introduce a surrogate objective at the upper level to guide the search and accelerate convergence. A bilevel Late Acceptance Hill Climbing algorithm (b-LAHC) is introduced that operates through three phases: greedy descent, neighborhood exploration, and final solution refinement. b-LAHC operates with fixed parameters, eliminating the need for complex adaptation while remaining lightweight and effective. Extensive experiments on the IEEE WCCI-2020 benchmark show that b-LAHC achieves superior or competitive performance against eight state-of-the-art algorithms. Under a fixed evaluation budget, it attains near-optimal solutions on small-scale instances and sets 9/10 new best-known results on large-scale benchmarks, improving existing records by an average of 1.07%. Moreover, the strong correlation (though not universal) observed between the surrogate objective and the complete cost justifies the use of the surrogate objective while still necessitating a joint solution of both levels, thereby validating the effectiveness of the proposed bilevel framework and highlighting its potential for efficiently solving large-scale routing problems with a hierarchical structure.

cs.AI↗

arXiv2026

dTRPO: Trajectory Reduction in Policy Optimization of Diffusion Large Language Models

Diffusion Large Language Models (dLLMs) introduce a new paradigm for language generation, which in turn presents new challenges for aligning them with human preferences. In this work, we aim to improve the policy optimization for dLLMs by reducing the cost of the trajectory probability calculation, thereby enabling scaled-up offline policy training. We prove that: (i) under reference policy regularization, the probability ratio of the newly unmasked tokens is an unbiased estimate of that of intermediate diffusion states, and (ii) the probability of the full trajectory can be effectively estimated with a single forward pass of a re-masked final state. By integrating these two trajectory reduction strategies into a policy optimization objective, we propose Trajectory Reduction Policy Optimization (dTRPO). We evaluate dTRPO on 7B dLLMs across instruction-following and reasoning benchmarks. Results show that it substantially improves the core performance of state-of-the-art dLLMs, achieving gains of up to 9.6% on STEM tasks, up to 4.3% on coding tasks, and up to 3.0% on instruction-following tasks. Moreover, dTRPO exhibits strong training efficiency due to its offline, single-forward nature, and achieves improved generation efficiency through high-quality outputs.

cs.AI↗

arXiv2026

Antitopological magnetic textures in an antiferromagnetically coupled bilayer with frustration

The bilayer skyrmion composed of upper and lower tightly coupled skyrmions on two layers with completely compensated topological charges (called as anti-topology here), has become one feasible improvement of conventional skyrmion to realize straight motion without skyrmion Hall effect, which has aroused great interest in practical applications. The present work investigates a general model (without external magnetic field) for the frustration-induced anti-topological bilayer magnetic textures with rich morphologies, and discusses the modulations of key parameters on the energy barrier and the current-driven dynamics. It is revealed that the interlayer coupling plays a key role in preventing distortion, and thus helps to reach a faster velocity. This model can be realized in various frustrated magnetic materials with antiferromagnetically coupled bilayer, providing a helpful guidance for the material design and application of topological magnetic textures.

cond-mat.mes-hall↗

arXiv2026

CODA: A Continuous Online Evolve Framework for Deploying HAR Sensing Systems

In always-on HAR deployments, model accuracy erodes silently as domain shift accumulates over time. Addressing this challenge requires moving beyond one-off updates toward instance-driven adaptation from streaming data. However, continuous adaptation exposes a fundamental tension: systems must selectively learn from informative instances while actively forgetting obsolete ones under long-term, non-stationary drift. To address them, we propose CODA, a continuous online adaptation framework for mobile sensing. CODA introduces two synergistic components: (i) Cache-based Selective Assimilation, which prioritizes informative instances likely to enhance system performance under sparse supervision, and (ii) an Adaptive Temporal Retention Strategy, which enables the system to gradually forget obsolete instances as sensing conditions evolve. By treating adaptation as a principled cache evolution rather than parameter-heavy retraining, CODA maintains high accuracy without model reconfiguration. We conduct extensive evaluations on four heterogeneous datasets spanning phone, watch, and multi-sensor configurations. Results demonstrate that CODA consistently outperforms one-off adaptation under non-stationary drift, remains robust against imperfect feedback, and incurs negligible on-device latency.

cs.LG↗

arXiv2026

FinTruthQA: A Benchmark for AI-Driven Financial Disclosure Quality Assessment in Investor -- Firm Interactions

Accurate and transparent financial information disclosure is essential for market efficiency, investor decision-making, and corporate governance. Chinese stock exchanges' investor interactive platforms provide a widely used channel through which listed firms respond to investor concerns, yet these responses are often limited or non-substantive, making disclosure quality difficult to assess at scale. To address this challenge, we introduce FinTruthQA, to our knowledge the first benchmark for AI-driven assessment of financial disclosure quality in investor-firm interactions. FinTruthQA comprises 6,000 real-world financial Q&A entries, each manually annotated based on four key evaluation criteria: question identification, question relevance, answer readability, and answer relevance. We benchmark statistical machine learning models, pre-trained language models and their fine-tuned variants, as well as large language models (LLMs), on FinTruthQA. Experiments show that existing models achieve strong performance on question identification and question relevance (F1 > 95%), but remain substantially weaker on answer readability (Micro F1 approximately 88%) and especially answer relevance (Micro F1 approximately 80%), highlighting the nontrivial difficulty of fine-grained disclosure quality assessment. Domain- and task-adapted pre-trained language models consistently outperform general-purpose models and LLM-based prompting on the most challenging settings. These findings position FinTruthQA as a practical foundation for AI-driven disclosure monitoring in capital markets, with value for regulatory oversight, investor protection, and disclosure governance in real-world financial settings.

cs.CL↗

arXiv2026

RetinexDualV2: Physically-Grounded Dual Retinex for Generalized UHD Image Restoration

We propose RetinexDualV2, a unified, physically grounded dual-branch framework for diverse Ultra-High-Definition (UHD) image restoration. Unlike generic models, our method employs a Task-Specific Physical Grounding Module (TS-PGM) to extract degradation-aware priors (e.g., rain masks and dark channels). These explicitly guide a Retinex decomposition network via a novel Physical-Conditioned Multi-head Self-Attention (PC-MSA) mechanism, enabling robust reflection and illumination correction. This physical conditioning allows a single architecture to handle various complex degradations seamlessly, without task-specific structural modifications. RetinexDualV2 demonstrates exceptional generalizability, securing 4th place in the NTIRE 2026 Day and Night Raindrop Removal Challenge and 5th place in the Joint Noise Low-light Enhancement (JNLLIE) Challenge. Extensive experiments confirm the state-of-the-art performance and efficiency of our physically motivated approach. Code is available at https://github.com/ErrorLogic1211/RetinexDual/tree/master/RetinexDualV2

cs.CV↗

arXiv2026

Reinforcement-Guided Synthetic Data Generation for Privacy-Sensitive Identity Recognition

High-fidelity generative models are increasingly needed in privacy-sensitive scenarios, where access to data is severely restricted due to regulatory and copyright constraints. This scarcity hampers model development--ironically, in settings where generative models are most needed to compensate for the lack of data. This creates a self-reinforcing challenge: limited data leads to poor generative models, which in turn fail to mitigate data scarcity. To break this cycle, we propose a reinforcement-guided synthetic data generation framework that adapts general-domain generative priors to privacy-sensitive identity recognition tasks. We first perform a cold-start adaptation to align a pretrained generator with the target domain, establishing semantic relevance and initial fidelity. Building on this foundation, we introduce a multi-objective reward that jointly optimizes semantic consistency, coverage diversity, and expression richness, guiding the generator to produce both realistic and task-effective samples. During downstream training, a dynamic sample selection mechanism further prioritizes high-utility synthetic samples, enabling adaptive data scaling and improved domain alignment. Extensive experiments on benchmark datasets demonstrate that our framework significantly improves both generation fidelity and classification accuracy, while also exhibiting strong generalization to novel categories in small-data regimes.

cs.CV↗

arXiv2026

Small Vision-Language Models are Smart Compressors for Long Video Understanding

Adapting Multimodal Large Language Models (MLLMs) for hour-long videos is bottlenecked by context limits. Dense visual streams saturate token budgets and exacerbate the lost-in-the-middle phenomenon. Existing heuristics, like sparse sampling or uniform pooling, blindly sacrifice fidelity by discarding decisive moments and wasting bandwidth on irrelevant backgrounds. We propose Tempo, an efficient query-aware framework compressing long videos for downstream understanding. Tempo leverages a Small Vision-Language Model (SVLM) as a local temporal compressor, casting token reduction as an early cross-modal distillation process to generate compact, intent-aligned representations in a single forward pass. To enforce strict budgets without breaking causality, we introduce Adaptive Token Allocation (ATA). Exploiting the SVLM's zero-shot relevance prior and semantic front-loading, ATA acts as a training-free $O(1)$ dynamic router. It allocates dense bandwidth to query-critical segments while compressing redundancies into minimal temporal anchors to maintain the global storyline. Extensive experiments show our 6B architecture achieves state-of-the-art performance with aggressive dynamic compression (0.5-16 tokens/frame). On the extreme-long LVBench (4101s), Tempo scores 52.3 under a strict 8K visual budget, outperforming GPT-4o and Gemini 1.5 Pro. Scaling to 2048 frames reaches 53.7. Crucially, Tempo compresses hour-long videos substantially below theoretical limits, proving true long-form video understanding relies on intent-driven efficiency rather than greedily padded context windows.

cs.CV↗

arXiv2026

LLM2Manim: Pedagogy-Aware AI Generation of STEM Animations

High-quality STEM animations can be useful for learning, but they are still not common in daily teaching, mostly because they take time and special skills to make. In this paper, we present a semi-automated, human-in-the-loop (HITL) pipeline that uses a large language model (LLM) to help convert math and physics concepts into narrated animations with the Python library Manim. The pipeline also tries to follow multimedia learning ideas like segmentation, signaling, and dual coding, so the narration and the visuals are more aligned. To keep the outputs stable, we use constrained prompt templates, a symbol ledger to keep symbols consistent, and we regenerate only the parts that have errors. We also include expert review before the final rendering, because sometimes the generated code or explanation is not fully correct. We tested the approach with 100 undergraduate students in a within-subject A-B study. Each student learned two similar STEM topics, one with the LLM-generated animations and one with PowerPoint slides. In general, the animation-based instruction gives slightly better post-test scores (83% vs.78%, p < .001), and students show higher learning gains (d=0.67). They also report higher engagement (d=0.94) and lower cognitive load (d=0.41). Students finished the tasks faster, and many of them said they prefer the animated format. Overall, these results suggest LLM-assisted animation can make STEM content creation easier, and it may be a practical option for more classrooms.

cs.MM↗

arXiv2026

HistoFusionNet: Histogram-Guided Fusion and Frequency-Adaptive Refinement for Nighttime Image Dehazing

Nighttime image dehazing remains a challenging low-level vision problem due to the joint presence of haze, glow, non-uniform illumination, color distortion, and sensor noise, which often invalidate assumptions commonly used in daytime dehazing. To address these challenges, we propose HistoFusionNet, a transformer-enhanced architecture tailored for nighttime image dehazing by combining histogram-guided representation learning with frequency-adaptive feature refinement. Built upon a multi-scale encoder-decoder backbone, our method introduces histogram transformer blocks that model long-range dependencies by grouping features according to their dynamic-range characteristics, enabling more effective aggregation of similarly degraded regions under complex nighttime lighting. To further improve restoration fidelity, we incorporate a frequency-aware refinement branch that adaptively exploits complementary low- and high-frequency cues, helping recover scene structures, suppress artifacts, and enhance local details. This design yields a unified framework that is particularly well suited to the heterogeneous degradations encountered in real nighttime hazy scenes. Extensive experiments and highly competitive performance of our method on the NTIRE 2026 Nighttime Image Dehazing Challenge benchmark demonstrate the effectiveness of the proposed method. Our team ranked 1st among 22 participating teams, highlighting the robustness and competitive performance of HistoFusionNet. The code is available at: https://github.com/heydarimo/Night-Time-Dehazing

cs.CV↗

arXiv2026

Magnetic doping-induced second-order and first-order topological phase transition inthe photonic alloy

The bulk-edge correspondence principle, a cornerstone of topological physics, ensures that first-order topological systems host robust chiral edge states in two dimension. This was later extended to higher-order phases, where second-order topological insulators exhibit localized, topologically protected corner states. While the transition between these distinct phases has been demonstrated in periodic systems, its existence in disordered platforms remains an open question. Here, we demonstrate a controllable topological phase transition between a second-order topological phase and a first-order topological phase in a two-dimensional photonic alloy. By tuning the magnetic doping concentration - implemented by attaching permanent magnets randomly to nonmagnetized yttrium iron garnet rods in an alternately magnetized honeycomb lattice with C3 rotational symmetry - we flexibly control the system's topology. At zero doping, we observe higher-order corner states, confirmed by a trivial Chern number and non-zero bulk polarizations of 1/3. As doping concentration increases, these corner states progressively merge with the bulk states, culminating in the closure of the bulk transmission gap. After the bulk transmission gap reopens with further increased doping, the system transitions to a first-order topological phase, characterized by a nontrivial Chern number of -1 and the emergence of a chiral edge state. This transition is reversible, providing a highly tunable and experimentally simple platform for flexibly switching between localized corner states and delocalized chiral edge states within a single photonic system.

cond-mat.dis-nn↗

arXiv2026

A Sc2C2@C88 cluster based ultra-compact multi-level probabilistic bit for matrix multiplication

Information units are progressively approaching the fundamental physical limits of the integration density, including in terms of extremely small sizes, multistates and probabilistic traversal. However, simultaneously encompassing all of these characteristics in a unit remains elusive. Here, via real-time in situ electrical monitoring, we clearly observed stochastic alterations of multiple conductance states in Sc2C2@C88. The true random bit sequence generated exhibited an autocorrelation function whose confidence interval fell within \pm 0.02, demonstrating high-quality randomness. The alterations of multiple conductance states are controllable, that is, whose probability distributions could traverse from 0 to 1, enabling us to factorize 551 into its prime factors. Furthermore, we proposed a matrix-chain multiplication scheme and experimentally verified the multiplication of two 4 \times 4 state-transition matrices with a small maximum error < 0.05. Combined with theoretical calculations, the stochastic but controllable multistates are probably attributed to the rich energy landscape, which could be stepwise changed by the electric field. Our findings reveal extremely small multi-level probabilistic bit for matrix multiplication, which pave the way for ultracompact intelligent electronic devices.

cond-mat.mtrl-sci↗

arXiv2026

TrajLoom: Dense Future Trajectory Generation from Video

Predicting future motion is crucial in video understanding and controllable video generation. Dense point trajectories are a compact, expressive motion representation, but modeling their future evolution from observed video remains challenging. We propose a framework that predicts future trajectories and visibility from past trajectories and video context. Our method has three components: (1) Grid-Anchor Offset Encoding, which reduces location-dependent bias by representing each point as an offset from its pixel-center anchor; (2) TrajLoom-VAE, which learns a compact spatiotemporal latent space for dense trajectories with masked reconstruction and a spatiotemporal consistency regularizer; and (3) TrajLoom-Flow, which generates future trajectories in latent space via flow matching, with boundary cues and on-policy K-step fine-tuning for stable sampling. We also introduce TrajLoomBench, a unified benchmark spanning real and synthetic videos with a standardized setup aligned with video-generation benchmarks. Compared with state-of-the-art methods, our approach extends the prediction horizon from 24 to 81 frames while improving motion realism and stability across datasets. The predicted trajectories directly support downstream video generation and editing. Code, model checkpoints, and datasets are available at https://trajloom.github.io/.

cs.CV↗

arXiv2026

VideoAuto-R1: Video Auto Reasoning via Thinking Once, Answering Twice

Chain-of-thought (CoT) reasoning has emerged as a powerful tool for multimodal large language models on video understanding tasks. However, its necessity and advantages over direct answering remain underexplored. In this paper, we first demonstrate that for RL-trained video models, direct answering often matches or even surpasses CoT performance, despite CoT producing step-by-step analyses at a higher computational cost. Motivated by this, we propose VideoAuto-R1, a video understanding framework that adopts a reason-when-necessary strategy. During training, our approach follows a Thinking Once, Answering Twice paradigm: the model first generates an initial answer, then performs reasoning, and finally outputs a reviewed answer. Both answers are supervised via verifiable rewards. During inference, the model uses the confidence score of the initial answer to determine whether to proceed with reasoning. Across video QA and grounding benchmarks, VideoAuto-R1 achieves state-of-the-art accuracy with significantly improved efficiency, reducing the average response length by ~3.3x, e.g., from 149 to just 44 tokens. Moreover, we observe a low rate of thinking-mode activation on perception-oriented tasks, but a higher rate on reasoning-intensive tasks. This suggests that explicit language-based reasoning is generally beneficial but not always necessary.

cs.CV↗

arXiv2026

Rethinking Gradient-based Adversarial Attacks on Point Cloud Classification

Gradient-based adversarial attacks are widely used to evaluate the robustness of 3D point cloud classifiers, yet they often rely on uniform update rules that neglect point-wise heterogeneity, leading to perceptible perturbations. We propose two complementary strategies to improve both the effectiveness and imperceptibility of the attack. \textbf{WAAttack} employs weighted gradients to dynamically adjust per-point perturbation magnitudes and uses an adaptive step size strategy to regulate the global perturbation scale. \textbf{SubAttack} partitions the point cloud into subsets and, at each iteration, perturbs only those combinations with high adversarial efficacy and low perceptual saliency. Together, these methods offer a principled refinement of gradient-based attacks for 3D point clouds. Extensive experiments show that our approach consistently outperforms state-of-the-art methods in generating highly imperceptible adversarial examples. The code is available at https://github.com/chenjun0326/WA_SubAttack.

cs.CV↗

arXiv2026

Multi-Agent SAC Enabled Beamforming Design for Joint Secret Key Generation and Data Transmission

Physical layer key generation (PLKG) has emerged as a promising solution for achieving highly secured and low-latency key distribution, offering information-theoretic security that is inherently resilient to quantum attacks. However, simultaneously ensuring a high data transmission rate and a high secret key generation rate under eavesdropping attacks remains a major challenge. In time-division duplex (TDD) systems with multiple antennas, we derive closed-form expressions for both rates by modeling the legitimate channel as a time-correlated autoregressive (AR) process. This formulation leads to a highly nonconvex and time-coupled optimization problem, rendering traditional optimization methods ineffective. To address this issue, we propose a multi-agent soft actor-critic (SAC) framework equipped with a long short-term memory (LSTM) adversary prediction module to cope with the partial observability of the eavesdropper's mode. Simulation results demonstrate that the proposed approach achieves superior performance compared with other benchmark algorithms, while effectively balancing the trade-off between secret key generation rate and data transmission rate. The results also confirm the robustness of the proposed framework against intelligent eavesdropping and partial observation uncertainty.

cs.IT↗