Search arXiv⌕ Search

arXiv subjects

Yi Wang

Publications and source records attributed to Yi Wang.

At least 37 records · Page 2Linked to original sources
arXiv2026

Relative Entropy and the Inviscid Limit for Planar Shocks of the Multi-D Burgers' Equation

In recent work (arXiv:2610.10341), the authors introduced a framework for studying the vanishing viscosity limit for sequences of weak solutions of the multi-dimensional compressible Navier-Stokes equations to planar shocks of the compressible Euler equations. In this paper, we introduce these methods and apply them to the multi-dimensional viscous Burgers' equation. We show that arbitrarily large viscous shocks enjoy $L^2$-stability among perturbations whose gradients in the directions transverse to the shock are controlled in an appropriate manner. As an application, we study the rate of convergence to the inviscid shock in the vanishing viscosity limit.

math.AP↗
arXiv2026

Never Too Late for Force: Accelerating VLA Post-Training with Reactive Force Injection

Pretrained vision-language-action (VLA) policies provide strong language-conditioned manipulation knowledge, but they remain largely vision-driven and can struggle once manipulation enters contact states where the scene is occluded, depth is ambiguous, or small force errors push execution off the offline demonstration distribution. We present LIFT (Late Reactive Injection of Force for VLA Post-Training), a force-aware post-training framework that adds contact reactivity to a pretrained VLA policy while preserving its output at initialization. LIFT grafts a reactive action expert beside the original action expert, initializes it from pretrained action weights, and injects recent 6D end-effector force through causal force memory and zero-initialized cross attention, enabling actions to be refreshed during execution. To address the policy-dependent distribution shift of contact feedback, LIFT further couples reactive force injection with an online DAgger loop that trains on a mixture of offline task-alignment data and human-corrected online rollouts. Across towel folding, book insertion, and Hanoi ring placement, LIFT learns faster and reaches higher peak and final performance than vision-only DAgger, while ablations show that reactive force memory and online corrective data are both important for robust contact-rich manipulation. Our code is publicly available at https://github.com/y-wng/lift

cs.RO↗
arXiv2026

ScholarStack: Layered Research Asset Orchestration and Cross-Task Reuse for Scientific Agents

Scientific agents support a range of literature-based research tasks, such as retrieval, question answering, evidence-grounded generation, and claim assessment. Most existing systems, however, are organized around individual tasks: the same papers are repeatedly retrieved, segmented, and interpreted, and the understanding built in one task is difficult to reuse in the next. We present ScholarStack, a layered research asset framework that compiles a paper collection into reusable, versioned, and provenance-preserving assets at three complementary levels: source-grounded paper-level statements, domain-level organization, and evidence-grounded cross-paper syntheses. A common access interface returns task-specific views at the evidence granularity each task requires, preserving study conditions, source traceability, and verification status. We instantiate the framework on four task families spanning ten task settings, comparing agents that use the compiled assets with task-specific baselines under matched base models. Quality gains concentrate on tasks that require cross-paper evidence, such as multi-paper question answering and literature review generation, and query-time token cost falls on every task where it is measured, with assets compiled once and reused across tasks. These results suggest that layered research assets can serve as shared infrastructure for scientific agents, shifting literature-based assistance from isolated document processing toward cumulative, evidence-grounded workflows.

cs.AI↗
arXiv2026

Differential Privacy Protected Preference Alignment on Survey Derived Data

Preference alignment enables language models to better reflect human values, but the preference data contains sensitive information, especially when derived from surveys about political beliefs, social norms, religion, gender attitudes, and cultural values. This paper studies privacy-preserving alignment on questionnaire-derived data from the World Values Survey, where supervision takes the form of ordinal labels rather than standard pairwise rankings. Existing efforts mainly focus on general privacy protections upon model training, while data-specific methods for survey data remain unexplored. We first show the vulnerability of aligned models, then formulate the task as rating prediction and introduce label differential privacy. Building on this formulation, we construct a differential private pipeline utilizing three privacy mechanisms: randomized response, exponential mechanism, and DP-SGD. Experiments show that simple label-level mechanisms outperform gradient-level methods, and proper aggregation function for preprocessing also make large contribution. The new fine-grained private comparison motivates explorations toward language model alignment with formal privacy guarantees.

cs.CR↗
arXiv2026

X-Ragent: Tool-Augmented Reinforcement Learning for Evidence-Grounded Chest X-Ray Reasoning

Chest X-ray (CXR) interpretation often requires integrating visual findings with task-specific evidence rather than relying on direct visual recognition alone. While tool-augmented medical agents can supply such evidence via external modules, they often lack explicit mechanisms for learning when auxiliary evidence is needed and for preventing inapplicable quantitative evidence from entering diagnostic reasoning. To address this, we propose X-Ragent, a post-training framework for tool-augmented reinforcement learning that decouples learned auxiliary-evidence seeking from validity-gated quantitative measurement acquisition for evidence-grounded CXR reasoning. We construct Rad-CoT, a 7.7K-sample corpus combining causally ordered tool-augmented trajectories with report-style diagnostic reasoning, and use it to initialize Qwen3-VL-8B via agentic supervised fine-tuning (SFT). We then optimize the policy with Group Relative Policy Optimization (GRPO) using an accuracy-gated reward that applies process-level terms for measurement consistency and auxiliary-tool cost only to correct trajectories, preventing plausible process behavior from compensating for an incorrect diagnosis. Across three CXR benchmarks, X-Ragent achieves the strongest results, including an 8.6-point improvement on the fully held-out ChestAgentBench. By seeking evidence selectively and admitting only valid measurements, X-Ragent supports more faithful and evidence-grounded CXR reasoning.

cs.CV↗
arXiv2026

SEDualVLN: A Spatially-Enhanced Dual-System Framework for Vision-Language Navigation

Vision-Language Navigation (VLN) approaches have currently followed two primary paradigms: the end-to-end Vision-Language Model (VLM) policy fine-tuned on navigation trajectories to directly predict actions, and the zero-shot modular pipeline integrating pre-trained Multimodal Large Language Model (MLLM) for training-free generalization to unseen environments. However, end-to-end methods struggle with long-horizon navigation and lack dynamic reasoning ability, whereas zero-shot methods are constrained by limited spatial grounding for reliable planning and require substantial reasoning time. To bridge this gap, we introduce SEDualVLN, a spatially-enhanced dual-system VLN framework. System 1 is a VLM model enhanced with both global and local spatial awareness, tailored for high-frequency action generation. System 2 integrates a general MLLM with a mapping module, wherein the MLLM performs low-frequency waypoint planning by leveraging top-down views of the real-time 3D map alongside streams of rendered path images. Both systems exploit complementary spatial representations to improve the agent's spatial understanding in VLN tasks. Ultimately, they cooperate to complete the navigation task through a fast-slow coordinated approach. SEDualVLN achieves state-of-the-art performance on VLN-CE benchmarks, and further ablation studies demonstrate the effectiveness of each system and module.

cs.RO↗
arXiv2026

LERR-Nav: Learning to Coordinate Exploration, Recovery, and Reminiscing for Object Navigation

Object Navigation in unseen environments remains a fundamental challenge in embodied AI, as it requires agents to generalize visual and spatial reasoning to novel layouts. While recent advances in large language model (LLM) and vision-language model (VLM) have enhanced semantic mapping, spatial memory, and waypoint selecting for navigation, successful navigation requires more than selecting the next promising waypoint. A robot must also recognize stalled progress, escape unproductive behaviors, and revisit overlooked target cues. Addressing these challenges requires both specialized navigation strategies and a high-level policy that coordinates their execution. Motivated by the analysis of failed navigation episodes, we propose LERR-Nav, an object navigation framework that coordinates exploration, recovery, and reminiscing through a learned high-level policy. The framework comprises four complementary navigation strategies: value-function-guided exploration, LLM-guided exploration, recovery from stalled or repetitive behavior, and memory-guided reminiscing. To support history-aware coordination, we maintain the execution memory that preserves textual summaries of all strategy executions alongside a sliding window of map sequences. To learn the coordination policy, we initialize a high-level vision-language agent from Qwen2.5-VL-7B-Instruct and train it through a two-stage curriculum. The first stage uses map-centric supervised fine-tuning (SFT) to establish spatial grounding. The second stage performs SFT on variable-length navigation segments to learn which navigation strategy to invoke next based on current maps and the hybrid execution memory. Experiments on HM3D and MP3D demonstrate state-of-the-art navigation performance, while ablation studies validate the contributions of individual components.

cs.RO↗
arXiv2026

Have You Seen It Clearly? Uncertainty-Guided Belief Refinement for Zero-Shot Object Navigation

Zero-Shot Object Navigation (ZSON) requires an agent to locate target objects in unfamiliar environments without additional training for the test categories or environments. Recent approaches leverage large language models and vision-language models to construct spatial representations and guide exploration. However, whether the available evidence sufficiently supports a navigation choice, and how new evidence changes the search value of previously visited locations, remain insufficiently addressed. We propose RefBeliefMap, an uncertainty-guided mapping framework that distinguishes target-location belief from spatial and semantic evidence uncertainty. By jointly modeling intra-observation uncertainty and inter-observation disagreement over a sliding memory window, RefBeliefMap assesses the reliability of both evidence channels. When competing frontiers remain insufficiently resolved, these uncertainty estimates guide active observation and semantic reasoning to refine the evidence supporting target-location beliefs before navigation commitment. Building on the refined map, we introduce RefBeliefNav, which jointly evaluates unexplored frontiers and historical waypoints according to their target-finding potential, expected information gain, and navigation cost. This unified objective allows historical locations to be reconsidered as new evidence changes their search value, coordinating exploration and revisitation. Experiments on HM3D and MP3D demonstrate state-of-the-art performance among the evaluated zero-shot baselines, with ablation studies examining the contributions of modules. Real-world experiments on a Unitree Go2 quadruped robot further demonstrate the sim-to-real transferability of our method.

cs.RO↗
arXiv2026

VideoEvoHarness: Self Evolving Agent Harness from Unlabeled Videos for Video Understanding

Video understanding agents rely on a harness to acquire evidence, use tools, and reason, but improving it requires substantial effort. Recent self evolution methods seek to optimize harnesses through execution feedback to reduce human intervention. However, existing methods often rely on annotated video questions and answers or focus on updating model parameters, leaving harness evolution from unlabeled videos underexplored. VideoEvoHarness jointly evolves a Questioner and a Solver harness from unlabeled videos with frozen model parameters. The Questioner constructs questions and computes reference answers directly from video memory records. Question quality assessments and Solver execution trajectories guide question generation policy revisions. The Solver supports evolving skills, strategies, hyperparameters, and tools using execution feedback. Executable strategies define workflows in code, reducing repeated interpretation of natural language instructions. Each round, candidate harnesses are compared on identical validation questions, with validated improvements retained for later use. Experiments on benchmarks and a dedicated benchmark question set, using videos disjoint from evolution videos, show higher overall accuracy than initially and transfer gains across backbones. Overall accuracy on this set also improves progressively across rounds. This supports our foundational framework for harness evolution from unlabeled videos, opening a promising direction for self evolving video agents. Code is available at https://github.com/Wei-Xin-Xu/VideoEvoHarness.

cs.CV↗
arXiv2026

Data-Centric Recursive Self-Improvement for Navigation via Policy-Synchronized Language-Action Dual Bootstrapping

Vision-language navigation requires agents to follow natural-language instructions to reach target locations, making high-quality language supervision essential. Since human annotation is costly, prior work has explored scalable data synthesis methods. However, existing methods typically either use separate models for navigation and instruction generation or couple the two tasks through task-specific components; most also annotate the full trajectory corpus with a fixed model before updating, which can cause generated supervision to lag behind the evolving policy. Therefore, we introduce RSI-Nav, a data-centric recursive self-improvement framework for navigation via policy-synchronized language-action dual bootstrapping, which unifies vision-language-to-action instruction following and vision-action-to-language instruction generation within a shared model. Specifically, after supervised fine-tuning establishes fundamental capabilities, RSI-Nav progressively processes unlabeled trajectories in small shards. The current model generates instructions for these trajectories, executes them to evaluate goal completion and path efficiency, retains qualified samples, and immediately updates itself before processing the next shard. This shard-wise update keeps newly generated supervision aligned with the evolving policy. We also incorporate spatial understanding data, since stronger spatial reasoning benefits navigation. Extensive experiments show that RSI-Nav reaches 68.6% SR on R2R-CE and 72.4% SR on RxR-CE, while providing stronger instruction-generation utility and modestly improved spatial understanding after recursive evolution.

cs.CV↗
arXiv2026

Stability of composite waves consisting of a non-classical Liu shock and a rarefaction wave for a non-convex viscoelastic system

We investigate the time-asymptotic stability of composite waves consisting of a non-classical Liu shock and a rarefaction wave for non-convex viscoelastic system. By choosing delicate time-dependent shift functions to the viscous shock and suitable weight functions for the relative entropy, we succeed in proving the time-asymptotic stability of the composite of a viscous Liu shock and a rarefaction wave from two different characteristic families for the one-dimensional viscoelastic system with a cubic non-convex stress-strain relation by $a$-contraction method. Here the non-classical Liu shock can be either degenerate or non-degenerate, which can be seen as the system version of the scalar Oleinik shock. Note that both the shift and the weight functions are chosen quite differently in the two cases of nearly degenerate and fully non-degenerate. The paper represents the first time-asymptotic stability result for the composite waves consisting of both non-classical Liu shock and rarefaction wave from two different families for the non-convex physical system.

math.AP↗
arXiv2026

Thinking with Images without Coordinates

Recent advances in multi-modal large language models have shifted toward the "thinking with images" paradigm to improve reasoning faithfulness, yet existing methods rely heavily on explicit coordinate- based grounding. We identify two fundamental limitations in this approach, i.e., a semantic gap where sparse regressions miss high-dimensional latent structures, and a resolution gap due to the granularity mismatch between patch-level tokens and pixel-level coordinates. To address these, we propose TiCO (Thinking with images without COordinates). It reformulates visual reasoning as a semantic evidence discovery process within the latent space, and evidence is injected as token-level regions without pixel coordinates. Specifically, TiCO utilizes a dedicated probe token to estimate similarity distributions and performs importance sampling over spatially connected components to generate diverse, semantically dominant evidence rollouts. Extensive experiments across multiple high-resolution and general visual reasoning benchmarks demonstrate that our TiCO consistently outperforms state-of-the-art coordinate-based methods with significantly improved inference efficiency.

cs.CV↗
arXiv2026

Brain foundation model-guided source-selective domain adaptation for cross-subject EEG decoding

Cross-subject motor-imagery electroencephalography (MI-EEG) decoding remains challenging because substantial inter-subject variability can cause both negative transfer from poorly matched source subjects and persistent distribution discrepancies between source and target domains. Existing multi-source domain adaptation methods often incorporate all available source domains or estimate source relevance using signal-level or task-specific representations, while distribution alignment is frequently performed only at the feature level. These limitations may introduce irrelevant source knowledge and fail to preserve class-discriminative structures across subjects. In this study, we propose a brain foundation model-guided multi-source domain adaptation framework (BFM-MSDA) for cross-subject MI-EEG decoding. The method first utilizes representations learned by a pretrained brain foundation model to estimate source--target compatibility and retrieve target-relevant sources. Subsequently, a relevance-weighted dual alignment strategy is applied to the selected sources and the unlabeled target domain. Specifically, Cauchy--Schwarz (CS) divergence is used to reduce discrepancies in marginal feature distributions, while conditional Cauchy--Schwarz (CCS) divergence further aligns class-dependent decision distributions. Source relevance is incorporated into both alignment terms so that more transferable source subjects contribute more strongly to adaptation. Experiments on two public MI-EEG benchmarks achieve average accuracies of 86.16% and 78.41%, outperforming representative cross-subject decoding and domain adaptation methods. Additional experiments with a large source pool further demonstrate that target-aware source retrieval improves scalability while mitigating negative transfer. These results highlight the importance of informed source selection under cross-subject distribution shift.

cs.LG↗
arXiv2026

Uniqueness and stability of planar shock wave to 2D compressible Euler equations in the vanishing viscosity limit of compressible Navier-Stokes equations

It is well known that the compressible Euler equations with planar shock initial data may admit infinitely many entropy weak solutions, as shown by Chiodaroli, De Lellis and Kreml [Comm. Pure Appl. Math. (2015)]. In this paper, we introduce a suitable notion of global-in-time weak solutions to the two-dimensional (2D) compressible Navier-Stokes equations with density-dependent viscosities in $\mathbb{R} \times \mathbb{T}$. Within this solution framework, we establish the first vanishing viscosity limit selection criterion for the physically relevant planar shock solution to the 2D compressible Euler equations. More precisely, we prove the uniqueness and stability of the 2D Euler planar shock solution within a class of inviscid limits of Navier-Stokes solutions emanating from near-planar initial data while the shock direction perturbation can be arbitrarily large. Starting from the relative $κ$-entropy for 2D compressible Navier-Stokes equations in $\mathbb{T}^2$ by Bresch, Noble and Vila [ESAIM Proc. Surveys (2017)], we first establish the relative $\frac12$-entropy between 2D weak solution of compressible Navier-Stokes equations in $\mathbb{R} \times \mathbb{T}$ and one-dimensional (1D) strong solution for averaged initial data in $\mathbb{R}$. Then we achieve the desired vanishing viscosity limit selection criterion by successfully bridging the fundamental structural gap between 2D Eulerian formulation of the original Navier-Stokes system in the relative $\frac12$-entropy and 1D vanishing viscosity limit to a shock solution of Euler equations in Lagrangian coordinates by Kang and Vasseur [Invent. Math. (2021)]. The framework developed herein can be applied to the three-dimensional limit selection criterion in $\mathbb{R} \times \mathbb{T}^2$, as well as to more complex planar Riemann solutions and interacting wave patterns.

math.AP↗
arXiv2026

Detected Seifert surfaces and intervals of left-orderable surgeries

We give a geometric criterion for the existence of one-sided intervals of left-orderable Dehn fillings near the longitudinal slope. Let $M$ be an irreducible integral homology solid torus containing an essential free genus-one Seifert surface $S$ which is not a fiber. Suppose that the longitudinal filling $M(0)$ is irreducible and that the capped surface $\widehat S$ is its unique JSJ torus. We prove that if the complementary piece is Seifert-fibered, or hyperbolic with a real place in its trace field, then all sufficiently small rational fillings on one side of zero have left-orderable fundamental group. The side is determined by the sign of an explicit invariant of the limiting representation. The proof starts from a real holonomy representation of the complementary piece. Peripheral infinitesimal regularity produces a smooth character-matching branch on the cut-open handlebody, and one real half-branch glues to $SL_2(\mathbb R)$-representations of $π_1(M)$ whose characters approach an ideal point detecting $S$. Their peripheral evaluations form a nonhorizontal end of the zero-sheet of the holonomy extension locus asymptotic to the horizontal axis. As an application, we show that for $n \geq 1$, there exists $a_n > 0$ such that for all rational $r \in (0, a_n)$, the $r$-Dehn filling of the $(-3,3,2n+1)$-pretzel knot complement is left-orderable.

math.GT↗
arXiv2026

Grounded in Time: A Multi-Source Dataset and Benchmark for Temporal Grounding in Robotic Manipulation

Robotic manipulation often requires inferring task-relevant states from past interactions when the current observation alone is insufficient to determine the appropriate action. Despite progress in benchmarking memory-augmented vision-language-action (VLA) models, application-oriented tasks requiring history-dependent semantic inference remain underrepresented. We introduce GiT (Grounded in Time), a dataset and benchmark for grounding manipulation decisions in past events across biolaboratory, household, and industrial scenarios. It includes real-robot and Universal Manipulation Interface (UMI) style demonstrations covering 18 bimanual tasks, together with simulation data and a ManiSkill-based evaluation suite covering nine tasks. Fine-grained subtask annotations and annotated counterfactual task pairs, in which similar current observations require different actions depending on prior events, support policy learning and targeted evaluation of history use. Evaluations of representative end-to-end VLA models in simulation and on selected real-world tasks reveal substantial room for improvement in history-dependent manipulation. The dataset and benchmark are available at the project page.

cs.RO↗
arXiv2026

Proximal Causal Learning under Unmeasured Confounding

Estimating treatment effects from observational data typically relies on the No Unmeasured Confounding Assumption (NUCA), which rarely holds in practice. Proximal causal learning (PCL) addresses unmeasured confounding via proxy variables, yet existing methods require the proxy variables to be pre-specified. Thus, we propose PCL-U, a framework that learns proxy variables directly from observed covariates. PCL-U uses neural encoders to decompose covariates into treatment-inducing, outcome-inducing, and shared proxies, guided by minimax mutual information objectives, and obtains causal estimates through a practical moment-based risk function. Experiments on benchmarks show that PCL-U matches or outperforms existing baselines. Besides, there are two types of synthetic datasets with varying dimensions and confounding strengths that illustrate that our method maintains stable estimation accuracy.

cs.LG↗
arXiv2026

RMCW: A Deletion-Robust Watermark Based on Reed--Muller Codes for Language Models

Large Language Model (LLM) watermarking provides a lightweight mechanism for identifying text generated by a specific model, but its robustness remains fragile under post-processing attacks. Deletion attacks are particularly challenging because they shift token positions and break the alignment between observed tokens and their original watermark positions. We propose Reed--Muller Code Watermarking (RMCW), an LLM watermarking method based on Reed--Muller codes. In contrast to global codeword recovery, RMCW searches for surviving local algebraic structure, leveraging the Reed--Solomon consistency induced by affine-line restrictions of Reed--Muller codewords. During generation, RMCW injects a Reed--Muller structure into the sequence via a secret-keyed vocabulary partition. During detection, it maps the given text to keyed vocabulary bins and tests local subsequences for low-degree Reed--Solomon consistency using Berlekamp--Welch tests. Experiments on C4 and ELI5 datasets with OPT-1.3B and Llama-3.1-8B-Instruct show that RMCW preserves strong clean-text detectability and outperforms or matches the baseline methods under several deletion and rewriting attacks. Our code is available at https://github.com/BaichengDanny/RMCW.

cs.CR↗