Searcharxiv⌕ Search

arXiv subjects

Chen Li

Publications and source records attributed to Chen Li.

At least 55 records · Page 3Linked to original sources
arXiv2026

PaDoc: Layout-Grounded Parallel Decoding for Document Parsing

End-to-end document parsers provide a unified interface, but serialize page layouts and regional contents into one autoregressive sequence. This formulation forces independent regions onto a decoding path whose length grows with the total content, whereas crop-based two-stage parsers expose region-level parallelism at the cost of repeated visual prefills and fragmented page context. To retain full-page context while removing dependencies, we propose PaDoc, a layout-grounded parser that treats the predicted layout as a branching structure over a shared page representation. Under a region-sufficiency assumption, we derive a prefix-conditioned factorization in which the layout stream and regional content branches advance concurrently, reducing the decoding depth to the longest layout-content path. We realize this factorization within a single MLLM: packed variable-length ancestor attention preserves the visibility under standard next-token training, while masked parallel decoding creates branches that the evaluated vLLM backend serves as concurrent requests with cache-resident shared-prefix reuse. On OmniDocBench Full, PaDoc attains an Overall layout F1 of 91.1 and, among end-to-end parsers, a top-tier Overall score of 94.24 together with the best Text Edit (0.038) and Formula CDM (95.59). On a 384-page subset and one A800 GPU, it is the fastest end-to-end parser at five concurrency levels, improving valid-page throughput by 67.4-118% and reducing P95 latency by 39.2-54.9% relative to a same-backbone Sequential SFT baseline. Code is available at https://github.com/Longin-Yu/Padoc

cs.AI↗
arXiv2026

From Understanding to Erasing: Towards Complete and Stable Video Object Removal

Video object removal aims to erase target objects while reconstructing visually plausible and temporally coherent content. However, target objects often induce shadows, reflections, illumination changes and other effects that extend beyond the provided mask, making conventional mask-conditioned completion prone to visible residuals. We therefore formulate side-effect-aware object removal as an understanding-guided process that integrates object--effect relations, affected-region localization, and context-aware reconstruction. Specifically, we introduce Object-Induced Relation Distillation to transfer token-level object--effect relations from a pretrained vision foundation model to the video diffusion model. We then design Object-aware Framewise Context Cross-Attention to combine target-object semantics with per-frame background context for removal and reconstruction, and propose Attention-guided Region Localization to derive a soft spatial prior over the target object and its affected regions. Extensive experiments across multiple benchmarks demonstrate that our method achieves more complete object-and-effect removal and outperforms existing approaches in removal quality, side-effect suppression, and temporal consistency.

cs.CV↗
arXiv2026

Dissecting the Nuclear Structure of NGC 5548 with XRISM. I. Physical Properties of the Highly Ionized Outflows

We present a detailed spectral analysis of an X-Ray Imaging and Spectroscopy Mission (XRISM) observation of the prototypical Seyfert 1 galaxy NGC 5548. XRISM's Resolve microcalorimeter reveals, for the first time, highly ionized outflows in this active galactic nucleus (AGN) through the detection of Fe XXV and Fe XXVI absorption lines in the Fe K band. Modeling the XRISM/Resolve spectrum alongside XMM-Newton Reflection Grating Spectrometer (RGS) data allows us to probe the ionization and kinematic structure of the outflows in this AGN. We identify four distinct ionization components, with ionization parameters log $ξ$ ranging from 0.9 to 3.4. Three of these components are further resolved into two velocity sub-components, demonstrating the multiphase structure of the outflows. The measured outflow velocities span 240 to 2730 km/s. We find a trend of increasing column density with ionization parameter ($ξ$), along with a general pattern of increasing outflow velocity with $ξ$. The XRISM/Resolve spectrum provides a far more detailed absorption measure distribution (AMD) than was previously possible, revealing two distinct slopes above and below $\logξ\sim 2.6$. A comparison of the Fe XXV absorption line profile with UV absorption lines (C IV and Ly$α$) observed with the Hubble Space Telescope reveals both overlaps and deviations. The XRISM/Resolve results suggest a multiphase, clumpy outflow in NGC 5548, consistent with a "hybrid wind" scenario in which the observed parameter trends arise from multiple origins and driving mechanisms.

astro-ph.HE↗
arXiv2026

From Patches to Evidence Balls: Class-Conditioned Evidence Retrieval for Few-Shot Whole Slide Image Classification

Whole slide image (WSI) classification is an evidence-driven task, where diagnostic cues are often sparse, spatially organized, and class-dependent. Existing MIL and vision-language methods aggregate a large pool of patch features into a single global slide representation. Under few-shot supervision, limited slide-level labels make it difficult to learn a reliable aggregation mechanism that organizes sparse local cues into compact and coherent diagnostic evidence. Moreover, a shared slide representation compresses evidence supporting a candidate class and its alternatives into the same feature, limiting class-specific reasoning and interpretability. To address these issues, we propose EviBall, a class-conditioned evidence retrieval framework for few-shot WSI classification. EviBall organizes local patches into Evidence Balls through semantic-spatial assignment and center refinement, yielding compact and spatially coherent evidence units under weak supervision. It then uses task-specific class queries, including language-guided queries for morphology-oriented tasks and molecular-guided queries for molecular endpoint prediction, to retrieve supporting evidence balls and produce class-conditioned evidence representations for direct class-wise prediction. By introducing structured evidence units and task-relevant semantic guidance, EviBall reduces the reliance on learning an unconstrained global aggregation mechanism from scarce slide-level labels. It therefore reformulates few-shot WSI classification as structured evidence retrieval and competition among candidate classes. Extensive experiments across four morphology-oriented and molecular endpoint WSI tasks demonstrate that EviBall consistently outperforms conventional and vision-language MIL baselines under diverse few-shot settings, while providing spatially localized and class-specific evidence for each prediction.

cs.CV↗
arXiv2026

BLADE: Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning

Large language models often improve task performance by generating long reasoning traces, but the resulting computation is frequently wasted on redundant verification and revision. Existing probe-based early-exit approaches mainly inspect explicit self-doubt expressions, leaving many earlier termination opportunities undetected. Expanding inspection to ordinary reasoning boundaries improves coverage, but also exposes highly diverse intermediate states whose predictive information may reside in different hidden layers. We present Boundary-Expanded and Layer-Adaptive Dynamic Exit for Efficient LLM Reasoning (BLADE), a lightweight framework that dynamically terminates reasoning by estimating whether the generated prefix is sufficient for correct answering. BLADE constructs multi-granular checkpoints from sentence, self-doubt, and paragraph boundaries, and derives robust training labels through repeated answer completions. It further learns a compact subset of informative probe layers instead of relying on fixed choices or expensive representations from all layers. At inference time, calibrated predictions are combined with checkpoint-specific confirmation rules to balance responsiveness and premature-exit risk. Experiments on five benchmarks and two Qwen3 reasoning models show that BLADE preserves near-baseline accuracy while reducing generated tokens by 24.8% on Qwen3-8B and 15.8% on Qwen3-4B. Ablation studies further confirm the benefits of diverse checkpoints and automatic layer selection, demonstrating an effective approach to more efficient LLM reasoning.

cs.CL↗
arXiv2026

On the Blueprint of Active Galaxies Producing Neutrinos

Based on the observation of the active galaxies NGC 1068 and TXS 0506+056, and on additional evidence for the sources NGC 4151, CGCG 420-015, NGC 7469, and the Circinus Galaxy emerging from IceCube data, we make the case for the production of high-energy neutrinos within a few gravitational radii of supermassive black holes surrounded by a dense plasma radiating X-rays. X-rays represents the target for the production of neutrinos by protons accelerated near the black hole; they also absorb the gamma rays from the decay of neutral pions produced in the same interactions. Neutrinos with energies of tens of TeV and above originate in photoproduction interactions with X-rays of $0.1 \sim 1$\,keV energy on the $Δ$ resonance, $p + γ\rightarrow Δ\rightarrow n + π^+$. Our analysis of the multimessenger data points to gamma-ray-obscured sources with a characteristic neutrino flux linearly proportional to the X-ray flux originating within $\sim 10$ gravitational radii of the black holes, with lower values preferred. We speculate on such sources producing the diffuse flux of neutrinos and cosmic rays of extragalactic origin.

astro-ph.HE↗
arXiv2026

LLM-Based Scientific Equation Discovery via Physics-Informed Token-Regularized Policy Optimization

Symbolic regression aims to distill mathematical equations from observational data. Recent approaches have successfully leveraged Large Language Models (LLMs) to generate equation hypotheses, capitalizing on their vast pre-trained scientific priors. However, existing frameworks predominantly treat the LLM as a static generator, relying on prompt-level guidance to steer exploration. This paradigm fails to update the model's internal representations based on search feedback, often yielding physically inconsistent or mathematically redundant expressions. In this work, we propose PiT-PO (Physics-informed Token-regularized Policy Optimization), a unified framework that evolves the LLM into an adaptive generator via reinforcement learning. Central to PiT-PO is a dual-constraint mechanism that rigorously enforces hierarchical physical validity while simultaneously applying fine-grained, token-level penalties to suppress redundant structures. Consequently, PiT-PO aligns LLM to produce equations that are both scientifically consistent and structurally parsimonious. Empirically, PiT-PO achieves state-of-the-art performance on standard benchmarks and successfully discovers novel turbulence models for challenging fluid dynamics problems. We also demonstrate that PiT-PO empowers small-scale models to outperform closed-source giants, democratizing access to high-performance scientific discovery.

cs.LG↗
arXiv2026

FilmWorld: Agentic Novel-to-Film Generation through Dynamic Cinematic World Modeling

Translating novels into films poses a grand challenge for generative artificial intelligence, requiring conversion of abstract literary prose into long-form, multi-scene visual narratives. While current video generation models excel at short, single-scene clips within narrow temporal and spatial contexts, novel-to-film generation operates in a more complex regime, demanding long-duration content across diverse scenes with dynamically evolving entity states. To address this, we formalize novel-to-film generation as dynamic cinematic world modeling, decomposed into two phases: construction, which grounds abstract, underspecified literary narratives into concrete, stateful, and persistent world entities; and evolution, which governs how these entities dynamically update under plot progression to maintain causal consistency across scenes. We propose FilmWorld, an end-to-end agentic system where two groups of specialized agents collaborate to instantiate these phases. Construction-side agents perform narrative structured translation, world entity state modeling with visual anchoring, and state-driven shot planning, progressively projecting literary language into a cinematic blueprint. Evolution-side agents perform state-anchored visual generation, cross-shot dynamic state propagation, and closed-loop state verification to maintain causal consistency and visual coherence. To address the evaluation gap in long-form generation, we introduce FilmEval, a systematic evaluation framework that couples a difficulty-graded benchmark of 15 representative novels with an automated protocol of nine objective metrics spanning three dimensions: cinematic presentation, film consistency, and novel fidelity. Experiments demonstrate that FilmWorld consistently outperforms state-of-the-art video generation agent systems, with particularly pronounced improvements in narrative fidelity and cross-scene consistency.

cs.CV↗
arXiv2026

WP-MIP: An Artificial Intelligence, Hybrid, and Physically Based Model Intercomparison Project for Weather Prediction

Rapid progress in the field of machine-learning for weather prediction has led to the emergence of algorithms whose forecasting skill can exceed that of traditional physically based models. This development represents an opportunity to improve the quality of forecasting services provided by operational centers, particularly given the speed at which machine-learning based models generate predictions. Despite the clear promise of these systems, questions remain about the ability of the current generation of machine-learning models to generate physically consistent predictions of the full suite of required forecast fields under all conditions. Answering these questions will require careful comparisons between the well-understood physically based models, current state-of-the-art machine-learning models, and the hybrid models that combine elements of these two archetypes. The Weather Prediction Model Intercomparison Project (WP-MIP) is a World Meteorological Organization-supported initiative whose initial goal is to create a centralized database of physically based, machine-learning, and hybrid model forecasts to enable a distributed assessment and evaluation effort. The first instance of WP-MIP focuses on global deterministic predictions using both center-specific and common initializations to facilitate sensitivity studies. Forecasts contributed by institutions across six continents will be used to develop AI-ready verification techniques that highlight the strengths and weaknesses of each class of prediction system, with the goal of establishing best-practice guidance to model developers and national weather centers. The broad engagement of the operational and forecast-evaluation communities in WP-MIP will ensure that the project results are highly relevant to the development and deployment of next-generation weather prediction systems.

physics.ao-ph↗
arXiv2026

FVAttn: Adaptive Sparse Attention with Runtime Load Balancing for Video Generation

Video Diffusion Transformers process long spatio-temporal sequences, making self-attention the main bottleneck in high-resolution video generation. Training-free sparse attention reduces this cost, but adaptive Top-$p$ routing creates uneven per-head workloads under multi-GPU sequence parallelism. The resulting workload heterogeneity turns sparse attention into a rank-level straggler problem. We present \method{}, a training-free sparse-attention system that improves the distributed execution efficiency of adaptive sparse attention under multi-GPU sequence parallelism. \method{} uses Top-$p$ routing, a Top-$k$ safety floor, and video-aware block organization as the sparse-routing frontend, then repairs the materialized mask at runtime. Runtime Load Balancing migrates a small number of heavy heads via P2P communication to shorten the current critical path. Slack-Aware Sparse Augmentation fills residual non-critical-rank slack with additional high-value blocks, while overlap hides scheduling and migration overhead behind existing computation. On step-distilled Wan2.2 I2V, \method{} reduces average load imbalance from 1.34 to 1.08 and delivers a $4.41\times$ attention speedup over FlashAttention, while achieving a $2.02$--$2.11\times$ DiT inference speedup with competitive video quality.

cs.CV↗
arXiv2026

Observation of A Solar Like Magnetic Reconnection Event in an AGN Corona with XRISM

The X-ray source in AGN is commonly referred to as the corona by analogy to stellar coronae. The similarities between the two suggest that the heating mechanism of AGN coronae is magnetic reconnection -- as in cool stars -- but this has not yet been directly observed. This work presents the first observational evidence for a magnetic reconnection flare in an AGN corona. We report on a flare in NGC 3783, which was observed with XRISM/Xtend and XMM-Newton/EPIC-PN exhibiting distinct temporal evolution in soft ($<2.0\,$keV) and hard ($>2.0\,$keV) X-rays. An Ultra-Fast Outflow (UFO) was detected during the event. The flare features the Neupert effect -- a temporal signature of the hard light curve correlating with the time derivative of the soft light curve, which shows that the flare is powered by magnetic reconnection, The Neupert effect is widely observed in the Sun, with Coronal Mass Ejections (CMEs) playing a role analogous to the UFO. We derive an upper limit of $30 \, R_g$ on the height of the magnetic loop from which the flare originates. Using the UFO's measured properties to characterize the magnetic field, we obtain $B > 1.3 \times 10^4\,$G for the field annihilated during the flare from total energy considerations, and $B \approx 500\,$G for the momentary magnetic field during reconnection from a dynamical consideration.

astro-ph.HE↗
arXiv2026

Gene Expression-Informed Jointly Controlled Generative Modeling for Precision Molecular Design

Precision molecular design aims to discover personalized drug candidates through joint control of multiple conditions, such as biological relevance and molecular design strategies. Biological relevance reflects cellular functional states under disease or perturbation conditions, while molecular design strategies provide complementary guidance in terms of structural intentions and property optimization. In this study, we propose JoPMol, a jointly controlled precision molecular generative model that integrates biological states encoded by gene expression profiles with molecular structure information expressed in text, and chemical properties quantified by numerical values within a unified modeling framework. This formulation enables coordinated generation and optimization of candidate molecules under joint condition control. Experimental results show that JoPMol outperforms state-of-the-art methods across multiple evaluation metrics. Moreover, JoPMol demonstrates strong generalization ability in both transfer tasks and biologically grounded simulation scenarios, validating its effectiveness for precision molecular design. The source code is publicly available at https://github.com/hala-yh/JoPMol.

cs.LG↗
arXiv2026

Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation

On-Policy Self-Distillation (OPSD) has emerged as a crucial paradigm for enhancing and aligning Large Language Models (LLMs). However, in complex reasoning tasks, OPSD paradoxically degrades downstream performance. In this paper, we systematically investigate this pathology and identify a severe optimization trap we define as \textbf{Thinking Collapse} -- a sharp decline in the model's native intermediate reasoning behavior, measured by epistemic-token density (ET per 1k). Through entropy-based gradient masking and token-level target analysis, we show that this collapse is triggered by aggressive teacher gradients at high-student-entropy decision forks, where student epistemic tokens are frequently suppressed into teacher non-epistemic targets and are highly concentrated in high pointwise student-teacher divergence regions. To resolve this optimization pathology, we propose \textbf{Adaptive Dual-Perspective OPSD (AD-OPSD)}, a robust control framework that dynamically moderates the self-distillation objective. AD-OPSD selectively anchors high-suppression-risk sandboxed tokens to a reference prior derived from the frozen base model via an asymmetrical pointwise divergence gate, preserving native thinking capacity while retaining OPSD's error-correcting power. Extensive experiments across competitive mathematical benchmarks show that AD-OPSD improves over standard OPSD by up to \textbf{+4.1\%} absolute average accuracy across diverse model scales and datasets. Further analysis demonstrates that AD-OPSD mitigates thinking collapse and generalizes robustly to different post-training paradigms.

cs.CL↗
arXiv2026

Cognitive-structured Multimodal Agent for Multimodal Understanding, Generation, and Editing

Recent unified multimodal models show a single architecture can jointly perform vision/language understanding and image generation/editing. However, they repeatedly feed all historical visual and textual inputs into a shared context window, limiting long-horizon multimodal dialogue due to visual token explosion and unreliable cross-turn referencing. We propose a Cognitive-structured Multimodal Agent that externalizes visual information into an Episodic Visual Memory and selectively reactivates relevant episodes during reasoning. The agent consists of a Perceptual Abstraction Engine for structured visual abstraction, a Cognitive Retrieval Engine for cross-turn memory retrieval, and a Multimodal Executive Controller for autonomous task inference and action planning. To address the lack of turn-level retrieval supervision in existing datasets, we develop a Unified Scenario Engine that programmatically generates structured multi-turn conversations with fine-grained retrieval annotations, enabling reinforcement learning to optimize abstraction and retrieval policies. We also construct a long-horizon visual-dialogue benchmark stratified by difficulty to evaluate episodic visual recall. Our 8B agent achieves 91.4% retrieval accuracy over 20-turn sessions, surpassing 32B baselines by +8.2% while nearly halving per-turn inference time (23.1s -> 12.7s). We further present the Cognitive-structured Multimodal Agent Harness (CMA-Harness), a tool-augmented deployment of the same cognitive structure integrating persistent multimodal memory, web access, image generation/editing/composition tools, and OpenAI-compatible serving. Structured memory and modular decision-making offer a more scalable, efficient paradigm for long-horizon multimodal agents than monolithic parameter scaling. Code: https://github.com/caseclose/cma-harness ; Project page: https://caseclose.github.io/cma-harness/

cs.CV↗
arXiv2026

Markovian Arrival Process Parameter Estimation of Quasi-birth-death Queueing Systems with Utilization Data

Parameter estimation for queueing systems is commonly performed using inter-arrival times, waiting times, or queue-length observations. However, such detailed observations are often unavailable in practical computer systems, where utilization data, such as CPU utilization, is much easier to collect. Utilization data provides only the fraction of time during which the system is busy within each monitoring interval, while the exact arrivals, services, phase transitions, and system states in unobservable periods remain hidden. This paper proposes an expectation-maximization (EM) algorithm for estimating the parameters of Markovian arrival process (MAP)-driven quasi-birth-death (QBD) queueing systems from utilization data. The proposed method formulates the underlying queueing dynamics as a QBD process and derives the expected sufficient statistics for sojourn times, phase transitions, arrivals, and services over both observable and unobservable intervals. These expectations are then used to iteratively update the MAP and service parameters under the maximum likelihood framework. In addition, Akaike's information criterion is introduced to select the appropriate number of MAP phases and mitigate overfitting. The proposed framework enables MAP-based queueing parameter estimation from incomplete utilization observations and provides a practical modeling approach for systems where detailed event-level measurements are difficult to obtain.

cs.PF↗
arXiv2026

Multi-Channel Uncertainty-Weighted Score Matching for Conditional Diffusion in Medical UDA

Robust medical image segmentation across modalities remains challenging due to severe domain shifts and the lack of target-domain labels. While diffusion models have been explored for cross-domain generation and augmentation, target-domain conditional diffusion training typically relies on highly noisy pseudo masks; naively conditioning on a single Arg-Max pseudo-label can corrupt diffusion training and downstream segmentation. We propose UPDiff-UDA, a unified UDA framework whose core is an uncertainty-guided training objective for target-domain conditional diffusion. Given an imperfect source-trained segmenter, we use its per-pixel softmax distribution to form ranked pseudo-label maps (Arg-Max, Arg-2nd, Arg-3rd, ...). Each map yields a conditional score estimate, and we aggregate them via pixel-wise confidence weighting to obtain an uncertainty-reweighted score for score matching, improving robustness to pseudo-label noise while leveraging alternative plausible labels in uncertain regions. We further provide a theoretical justification showing that confidence-weighted aggregation follows a minimum-MSE convex-combination principle under the segmenter-induced surrogate label distribution. To improve pseudo-condition quality, we also introduce a feature-guided, low-degree-of-freedom Bézier curve adaptation to reduce appearance gaps. Experiments on multiple public datasets and modality shifts show that UPDiff-UDA generates high-fidelity labeled target-style samples for augmentation and consistently outperforms strong UDA baselines. The code for this project is available at: https://github.com/superlc1995/Multi-Channel-Uncertainty-Diffusion-UDA

cs.CV↗
arXiv2026

FAIL: Flow Matching Adversarial Imitation Learning for Image Generation

Post-training of flow matching models-aligning the output distribution with a high-quality target-is mathematically equivalent to imitation learning. While Supervised Fine-Tuning mimics expert demonstrations effectively, it cannot correct policy drift in unseen states. Preference optimization methods address this but require costly preference pairs or reward modeling. We propose Flow Matching Adversarial Imitation Learning (FAIL), which minimizes policy-expert divergence through adversarial training without explicit rewards or pairwise comparisons. We derive two algorithms: FAIL-PD exploits differentiable ODE solvers for low-variance pathwise gradients, while FAIL-PG provides a black-box alternative for discrete or computationally constrained settings. Fine-tuning FLUX with only 13,000 demonstrations from Nano Banana pro, FAIL achieves competitive performance on prompt following and aesthetic benchmarks. Furthermore, the framework generalizes effectively to discrete image and video generation, and functions as a robust regularizer to mitigate reward hacking in reward-based optimization. Code and data are available at https://github.com/HansPolo113/FAIL.

cs.CV↗
arXiv2026

EMOSH: Expressive Motion and Shape Disentanglement for Human Animation

High-fidelity and expressive controllable human animation is essential for content creation and digital avatar applications. However, existing methods face a dilemma between expressiveness and disentanglement. Mainstream 2D pose-conditioned approaches suffer from "motion-shape entanglement", leading to the leakage of the driving subject's body shape. Conversely, methods relying on 3D priors (e.g., SMPL) achieve geometric disentanglement but struggle to capture facial expressions and complex gestures, resulting in rigid animations. To this end, we propose EMOSH, a novel framework for high-fidelity controllable human video generation. First, an Expressive Human Model (EHM) is introduced as the core control representation. By explicitly disentangling shape and pose parameters, we fundamentally resolve the body shape leakage issue. Alongside this, a robust motion tracker is designed to accurately estimate EHM parameters from video. Second, we propose a Coarse-to-Fine Hybrid Motion Injection strategy, enabling more fine-grained control over expressions and gestures. Furthermore, we introduce a Spatially-Aligned Conditioning mechanism to bridge the domain gap between training and inference, improving identity consistency. Extensive experiments demonstrate that EMOSH outperforms previous methods in both self-driven and cross-driven scenarios, producing high-fidelity videos with vivid expressions while maintaining shape disentanglement.

cs.CV↗