arXiv subjects

Xu Jiang

Publications and source records attributed to Xu Jiang.

At least 19 recordsLinked to original sources

arXiv2026

PDRVLA: A Vision-Language-Action Model with Physical Dynamics Representations

Vision--Language--Action (VLA) models generate robot actions from visual observations and language instructions, but their understanding of physical dynamics remains limited. Video world models can capture scene dynamics, yet generating future videos introduces high latency into the control loop. We introduce PDRVLA, whose lightweight Physical Dynamics Module extracts physical tokens from vision--language features to condition action generation without online video generation. The module learns through direct prediction of future RGB, depth, and optical-flow features, with auxiliary supervision through a frozen pretrained video world model. Training relies entirely on publicly available data, expanded through human-to-robot synthesis, subtask annotation, and embodied chain-of-thought (ECoT) annotation. Across four simulation benchmarks, PDRVLA achieves success rates of 99.3% on LIBERO, 89.9% on LIBERO-Plus, 93.6% on RoboTwin~2.0, and 81.5% on SimplerEnv. Ablations show improved future prediction with world-model supervision and evaluate how subtask conditioning, future object-pose supervision, and ECoT training affect action success.

cs.RO↗

arXiv2026

EditJev: System One Routing for Image Editing Models

Instruction-based image editing models exhibit pronounced sample-specific performance variation: different models can produce substantially different results for the same source image and editing instruction, and the best-performing model often varies across requests. These models also differ substantially in inference latency, making fixed-model deployment inefficient. We therefore study image editing model routing, which dynamically selects an editor from a candidate pool given an input image and editing instruction. We introduce EditJev, a System One routing model that directly predicts sample-level preference scores over candidate image editing models in a single forward pass. A lightweight preference head on a vision-language backbone produces a fixed-dimensional score vector without autoregressive model-name generation or response parsing. To train EditJev, we construct pairwise preferences from offline candidate outputs and optimize a pairwise ranking objective to learn relative model suitability. At inference time, EditJev combines the predicted preference scores with model-level speed scores to balance editing quality and generation latency. Experiments on ImgEdit and GEdit-En show that EditJev improves aggregate quality over the strongest fixed editor, from 4.540 to 4.592 and from 8.194 to 8.255, respectively, while reducing estimated end-to-end latency by 60.8% and 31.7%. These results demonstrate the effectiveness of direct, structured model routing for efficient image editing.

cs.CV↗

arXiv2026

ProsaBuddy: Assisting Mechanized Real-Time Schedulability Analysis with LLM-based Agents

Rigorous schedulability analysis is essential for the design of hard real-time systems, yet errors in pen-and-paper proofs threaten the safety of critical applications. The Prosa initiative addresses this by offering a foundation for building machine-checkable schedulability analysis proofs in the Rocq proof assistant. However, the substantial time and expertise required to construct such proofs remain a major barrier for wider adoption of Prosa. This work presents ProsaBuddy, an LLM?based agent system designed to lower the effort needed to develop mechanized real-time schedulability proofs. ProsaBuddy employs a ReAct loop with retrieval over the Prosa codebase, access to Rocq tools and optional human-written hints. It uses a subgoal?delegation architecture, decomposing a lemma into subgoals and dispatches them to subagents for proof. We evaluate ProsaBuddy on a mini benchmark drawn from real-time scheduling literature. Experiment results show that ProsaBuddy significantly outper?forms state-of-the-art LLM-based Rocq automated proving agent systems and a general coding agent OpenCode

cs.LO↗

arXiv2026

A scattering correction method for CT reconstruction based on the Wavelet Adaptive Material-dependent Boltzmann Transport Equation (WAM-BTE)

X-ray computed tomography (CT) is an essential imaging technology in clinical diagnosis. However, scattered photons can reduce image contrast and introduce CT value bias, which severely degrades image quality. Recently, scatter correction methods based on the Boltzmann transport equation (BTE) have attracted increasing attention due to their high physical accuracy and flexibility. Nevertheless, existing BTE-based methods usually employ single-material models, which cannot accurately describe the nonlinear energy dependence of photon interaction cross-sections in different materials. In this work, a scatter correction method based on the wavelet adaptive material-dependent BTE (WAM-BTE) is proposed. The conventional single-material model is extended to a multi-material model by introducing material-dependent scattering distributions. Furthermore, an adaptive multi-scale framework is established through wavelet decomposition. The low-frequency wavelet coefficients are used for coarse-scale scatter estimation to reduce computational complexity, while the high-frequency wavelet energy of high attenuation materials is utilized for adaptive local refinement. Theoretical analysis demonstrates that, when using the Haar basis function, the low-frequency wavelet coefficients at the $w$-th level are mathematically equivalent to block-average downsampling with a scale factor of $2^w$, except for a deterministic normalization factor. Experimental results show that the proposed WAM-BTE method achieves comparable accuracy to the Monte Carlo method while preserving the computational efficiency of coarse-scale estimation. The scatter calculation time for a single projection view is reduced to the millisecond level.

physics.med-ph↗

arXiv2026

VISD: Enhancing Video Reasoning via Structured Self-Distillation

Training VideoLLMs for complex reasoning remains challenging due to sparse sequence level rewards and the lack of fine grained credit assignment over long, temporally grounded reasoning trajectories. While reinforcement learning with verifiable rewards (RLVR) provides reliable supervision, it fails to capture token level contributions, leading to inefficient learning. Conversely, existing self distillation methods offer dense supervision but lack structure and diagnostic specificity, and often interact unstably with reinforcement learning. In this work, we propose VISD, a structured self distillation framework that introduces diagnostically meaningful privileged information for video reasoning. VISD employs a video aware judge model to decompose reasoning quality into multiple dimensions, including answer correctness, logical consistency, and spatio-temporal grounding, and uses this structured feedback to guide a teacher policy for token level supervision. To stably integrate dense supervision with RL, we introduce a direction magnitude decoupling mechanism, where rollout level advantages computed from rewards determine update direction, while structured privileged signals modulate token level update magnitudes. This design enables semantically aligned and fine grained credit assignment, improving both reasoning faithfulness and training efficiency. Additionally, VISD incorporates curriculum scheduling and EMA based teacher stabilization to support robust optimization over long video sequences. Experiments on diverse benchmarks show that VISD consistently outperforms strong baselines, improving answer accuracy and spatio temporal grounding quality. Notably, VISD reaches these gains with nearly 2x faster convergence in optimization steps, highlighting the effectiveness of structured self supervision in improving both performance and sample efficiency for VideoLLMs.

cs.CV↗

arXiv2026

Topologically Configurable Nonlinear Vortex Generation at van der Waals Heterostructures

van der Waals (vdW) materials offer a highly tunable and efficient platform at nanoscale for nonlinear and quantum optics. Twist-stacked vdW heterostructures enable elegant control of symmetry and interlayer coupling. Prior studies mainly focus on planar twisted interfaces, while neglecting the naturally formed and mandatory defects in such vdW heterostructures. Here, we demonstrate nonlinear singular optics with topologically configurable nonlinear vortex generation at the corner singularity of vdW heterostructures. By tailoring azimuthally discrete second-harmonic phase gradients at each interface, we obtain programmable nonlinear vortex emitters with dominant target OAM components. Nonlinear OAM beams with topological charge $\ell = 1$ and $\ell = -2$ are experimentally realized, respectively. Our work unlocks the untapped potentials of nonlinear singular optics in twisted vdW materials as a reconfigurable and lithography-free platform for nonlinear structured light generation, important in quantum nonlinear optics and related fields.

physics.optics↗

arXiv2026

SCMA: Structure-Conditioned and Metal-Aware Flow Matching for CT Metal Artifact Reduction

In X-ray CT, metallic objects cause beam hardening, photon starvation, and scattering, leading to projection inconsistency, streaks, dark bands, and structural distortions that compromise clinical diagnosis and quantitative analysis. Existing metal artifact reduction (MAR) methods remain limited: optimization-based methods may leave residual artifacts or blur structures, regression networks may generalize poorly across scenarios, and generative models without sample-specific structural guidance and physical constraints may produce anatomically inconsistent structures. Flow Matching learns a continuous-time velocity field that deterministically transports a source distribution to a target distribution, providing a flexible MAR prior. However, standard unconditional Flow Matching does not exploit sample-specific structure, spatially nonuniform metal-induced degradation, or measured projections. To address these limitations, we propose SCMA, a structure-conditioned and metal-aware Flow Matching framework. First, a linear-interpolation-corrected image is fed into the velocity network with the intermediate state as a sample-specific structural condition, guiding inference toward artifact-free CT images while preserving anatomy. Second, time-varying spatial weights from the metal mask and its distance transform are incorporated into the Flow Matching loss to emphasize severe degradation within and around metal regions. Finally, conditional Flow Matching updates alternate with projection-consistency correction during inference, allowing reliable measurements outside metal traces to constrain predictions. Experiments on simulated and real CT data demonstrate that SCMA more effectively suppresses metal artifacts, preserves local anatomical structures, and reduces hallucination-like structures inconsistent with projection measurements than representative MAR methods.

cs.CV↗

arXiv2026

FreshRetailNet-50K: A Stockout-Annotated Censored Demand Dataset for Latent Demand Recovery and Forecasting in Fresh Retail

Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products. However, it faces fundamental challenges from censored sales data during stockouts, where unobserved demand creates systemic policy biases. Existing datasets lack the temporal resolution and annotations needed to address this censoring effect. To fill this gap, we present FreshRetailNet-50K, the first large-scale benchmark for censored demand estimation. It comprises 50,000 store-product time series of detailed hourly sales data from 898 stores in 18 major cities, encompassing 863 perishable SKUs meticulously annotated for stockout events. The hourly stock status records unique to this dataset, combined with rich contextual covariates, including promotional discounts, precipitation, and temporal features, enable innovative research beyond existing solutions. We demonstrate one such use case of two-stage demand modeling: first, we reconstruct the latent demand during stockouts using precise hourly annotations. We then leverage the recovered demand to train robust demand forecasting models in the second stage. Experimental results show that this approach achieves a 2.73% improvement in prediction accuracy while reducing the systematic demand underestimation from 7.37% to near-zero bias. With unprecedented temporal granularity and comprehensive real-world information, FreshRetailNet-50K opens new research directions in demand imputation, perishable inventory optimization, and causal retail analytics. The unique annotation quality and scale of the dataset address long-standing limitations in retail AI, providing immediate solutions and a platform for future methodological innovation. The data (https://huggingface.co/datasets/Dingdong-Inc/FreshRetailNet-50K) and code (https://github.com/Dingdong-Inc/frn-50k-baseline}) are openly released.

cs.LG↗

arXiv2026

OctoT2I: A Self-Evolving Agentic Text-to-Image Router

The explosive growth of Text-to-Image (T2I) models, from large-scale versions to lightweight, real-time ones, now faces diminishing marginal returns from single-model scaling. Agentic T2I methods emerged to alleviate this bottleneck by using multiple models. However, existing agentic T2I methods suffer from three key challenges: reliance on expensive handcrafted priors or human annotations, rigid single-path decision mechanisms, and a neglect of inference efficiency. To address these challenges, we introduce OctoT2I, a novel agentic framework that reformulates the T2I task as a joint optimization of generation quality and inference efficiency. OctoT2I implements a stateful, multi-round routing strategy that adaptively selects the most suitable tool based on its knowledge and memory. This strategy is enabled by a knowledge base built from scratch by our novel Self-Evolving Mechanism. This mechanism, which requires no human supervision, first autonomously defines foundational Conceptual Dimensions (eg, style, color, count) and then intelligently explores their combinations via an iterative" Propose--Solve--Evaluate--Learn"(PSEL) loop. The PSEL loop efficiently discovers each tool's capability frontier, driving continuous improvement without external guidance. Extensive experiments demonstrate that OctoT2I achieves competitive performance (0.96) on GenEval while delivering a 90.3% inference speedup and a 56.6% energy-efficiency gain over the leading baseline (Flow-GRPO), striking an exceptional balance between performance and efficiency. Code and models will be made available.

cs.AI↗

arXiv2026

ContextGuard: Structured Self-Auditing for Context Learning in Language Models

Recent benchmarks reveal that despite strong reasoning capabilities, large language models (LLMs) still struggle to faithfully apply complex contextual knowledge. These failures are often not wholesale reasoning collapses: in context-rich tasks, models may follow the central reasoning path while missing peripheral, persistent, or format-sensitive requirements.

cs.CL↗

arXiv2026

Context-CoT: Enhancing Context Learning via High-Quality Reasoning Synthesis

While LLMs excel at reasoning over prompts using static pretrained knowledge, they struggle significantly with context learning-the ability to dynamically extract, internalize, and apply new knowledge from complex, task-specific contexts. Recent evaluations on the CL-Bench reveal a critical capability gap: frontier models solve only 17.2% of context-dependent tasks on average.

cs.AI↗

arXiv2026

DGPO: Distribution Guided Policy Optimization for Fine Grained Credit Assignment

Reinforcement learning is crucial for aligning large language models to perform complex reasoning tasks. However, current algorithms such as Group Relative Policy Optimization suffer from coarse grained, sequence level credit assignment, which severely struggles to isolate pivotal reasoning steps within long Chain of Thought generations. Furthermore, the standard unbounded Kullback Leibler divergence penalty induces severe gradient instability and mode seeking conservatism, ultimately stifling the discovery of novel reasoning trajectories. To overcome these limitations, we introduce Distribution Guided Policy Optimization, a novel critic free reinforcement learning framework that reinterprets distribution deviation as a guiding signal rather than a rigid penalty. DGPO replaces the volatile KL divergence with the bounded Hellinger distance to safely quantify token level exploration without the risk of gradient explosion. To effectively distinguish genuine reasoning breakthroughs from hallucinatory noise, we propose an entropy gating mechanism that scales this deviation by the policy`s epistemic uncertainty. By dynamically redistributing the coarse sequence-level advantage to individual tokens based on these gated scores, DGPO heavily incentivizes critical exploratory steps while suppressing unwarranted, low-entropy deviations. Consequently, DGPO completely eliminates the traditional token-level KL penalty and achieves fine-grained credit reallocation without the computational overhead of an additional value network. Extensive empirical evaluations demonstrate that DGPO sets a new state-of-the-art for critic free alignment. Notably, on the Qwen2.5-32B architecture, DGPO achieves 60.0% Avg@32 accuracy and 46.0% Avg@32 accuracy on the challenging AIME2024 and AIME2025 benchmarks respectively, substantially outperforming competitive baselines like DAPO.

cs.LG↗

arXiv2026

Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding

Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines feeding Large Language Models (LLMs) or native Multimodal LLMs (MLLMs), face key limitations: the former loses structural detail, while the latter struggles with context modeling. Retrieval-Augmented Generation (RAG) helps ground models in external data, but documents' multimodal nature, i.e., combining text, tables, charts, and layout, demands a more advanced paradigm: Multimodal RAG. This approach enables holistic retrieval and reasoning across all modalities, unlocking comprehensive document intelligence. Recognizing its importance, this paper presents a systematic survey of Multimodal RAG for document understanding. We propose a taxonomy based on domain, retrieval modality, and granularity, and review advances involving graph structures and agentic frameworks. We also summarize key datasets, benchmarks, applications and industry deployment, and highlight open challenges in efficiency, fine-grained representation, and robustness, providing a roadmap for future progress in document AI.

cs.CL↗

arXiv2026

A Theory of Covenant Accounting Adjustment

We develop an incomplete-contracting model with accounting-based covenants to study how covenant accounting adjustments are made and what properties they exhibit. Standard accounting rules (e.g., GAAP) can generate false-alarm errors or undue-optimism errors. The manager can exert costly effort to privately identify these errors and propose adjustments. If errors are not corrected, control rights may be inefficiently allocated, leading to costly renegotiation. We show that (1) adjustments always correct false-alarm errors, but correct undue-optimism errors only when their magnitude is small; and (2) the manager may expend socially wasteful effort to identify these errors. The model yields testable empirical predictions and policy implications.

econ.GN↗

arXiv2026

Neural Collapse in Test-Time Adaptation

Test-Time Adaptation (TTA) enhances model robustness to out-of-distribution (OOD) data by updating the model online during inference, yet existing methods lack theoretical insights into the fundamental causes of performance degradation under domain shifts. Recently, Neural Collapse (NC) has been proposed as an emergent geometric property of deep neural networks (DNNs), providing valuable insights for TTA. In this work, we extend NC to the sample-wise level and discover a novel phenomenon termed Sample-wise Alignment Collapse (NC3+), demonstrating that a sample's feature embedding, obtained by a trained model, aligns closely with the corresponding classifier weight. Building on NC3+, we identify that the performance degradation stems from sample-wise misalignment in adaptation which exacerbates under larger distribution shifts. This indicates the necessity of realigning the feature embeddings with their corresponding classifier weights. However, the misalignment makes pseudo-labels unreliable under domain shifts. To address this challenge, we propose NCTTA, a novel feature-classifier alignment method with hybrid targets to mitigate the impact of unreliable pseudo-labels, which blends geometric proximity with predictive confidence. Extensive experiments demonstrate the effectiveness of NCTTA in enhancing robustness to domain shifts. For example, NCTTA outperforms Tent by 14.52% on ImageNet-C. Project page is publicly available at https://github.com/Cevaaa/NCTTA.

cs.CV↗

arXiv2026

Beyond Fixed Inference: Quantitative Flow Matching for Adaptive Image Denoising

Diffusion and flow-based generative models have shown strong potential for image restoration. However, image denoising under unknown and varying noise conditions remains challenging, because the learned vector fields may become inconsistent across different noise levels, leading to degraded restoration quality under mismatch between training and inference. To address this issue, we propose a quantitative flow matching framework for adaptive image denoising. The method first estimates the input noise level from local pixel statistics, and then uses this quantitative estimate to adapt the inference trajectory, including the starting point, the number of integration steps, and the step-size schedule. In this way, the denoising process is better aligned with the actual corruption level of each input, reducing unnecessary computation for lightly corrupted images while providing sufficient refinement for heavily degraded ones. By coupling quantitative noise estimation with noise-adaptive flow inference, the proposed method improves both restoration accuracy and inference efficiency. Extensive experiments on natural, medical, and microscopy images demonstrate its robustness and strong generalization across diverse noise levels and imaging conditions.

cs.CV↗

arXiv2026

RealOSR: Latent Guidance Boosts Diffusion-based Real-world Omnidirectional Image Super-Resolutions

Omnidirectional image super-resolution (ODISR) aims to upscale low-resolution (LR) omnidirectional images (ODIs) to high-resolution (HR), catering to the growing demand for detailed visual content across a $ 180^{\circ}\times360^{\circ}$ viewport. Existing ODISR methods are limited by simplified degradation assumptions (e.g., bicubic downsampling), failing to model and exploit the real-world degradation information. Recent latent-based diffusion approaches using condition guidance suffer from slow inference due to their hundreds of updating steps and frequent use of VAE. To tackle these challenges, we propose \textbf{RealOSR}, a diffusion-based framework tailored for real-world ODISR, featuring efficient latent-based condition guidance within a one-step denoising paradigm. Central to efficient latent-based condition guidance is the proposed \textbf{Latent Gradient Alignment Routing (LaGAR)}, a lightweight module that enables effective pixel-latent space interactions and simulates gradient descent directly in the latent space, thereby leveraging the semantic richness and multi-scale features captured by the denoising UNet. Compared to the recent diffusion-based ODISR method, OmniSSR, RealOSR achieves significant improvements in visual quality and over \textbf{200$\times$} inference acceleration. Our code and models will be released upon acceptance.

eess.IV↗

arXiv2026

Polarization Engineering of Second-Harmonic Generation in 3R-MoS$_2$ Waveguides

Chip-scale nonlinear optics enables strong light-matter interactions within compact devices, serving as a fundamental platform for multifunctional integrated photonics from classical optical signal processing to quantum information technologies. Transition metal dichalcogenide (TMDC) waveguides have recently emerged as a highly promising platform owing to their giant material nonlinearity and extended interaction lengths. To date, however, research has predominantly focused on conversion efficiency, leaving the mechanisms governing the polarization state of nonlinear signal largely unexplored. Here, we establish a comprehensive framework for engineering the polarization of second-harmonic generation (SHG) in 3R-MoS$_2$ waveguides. By synergizing polarization-resolved measurements with theoretical modeling, we reveal that the SHG polarization is determined by guided-mode interactions constrained by waveguide geometry and crystal symmetry, and further reshaped during propagation. We demonstrate that thickness-dependent guided-mode confinement and in-plane crystal symmetry provide robust, static control over SHG polarization, while propagation length offers a dynamic tuning knob for continuously tailoring the nonlinear output. Our findings provide a deterministic approach for on-chip polarization engineering, opening opportunities for reconfigurable nonlinear light sources and quantum photonic circuits.

physics.optics↗