arXiv subjects

Qi Wang

Publications and source records attributed to Qi Wang.

At least 19 recordsLinked to original sources

arXiv2026

A Stochastic LineseArch Method (SLAM) for Minimizing Expectation Residuals: Weakening Boundedness of Gradient

We establish convergence guarantees for the Stochastic LineseArch Method (SLAM) proposed and analyzed in Wang et al. (arXiv:2512.14979) for nonconvex composite stochastic optimization, retaining the iteration and sample complexity orders of the original analysis assuming neither the boundedness of true gradients nor the Lipschitz continuity of the convex nonsmooth term $r$. ChatGPT was used to assist in developing a key intermediate result. Under uniformly Lipschitz continuous and unbiased sampled gradients with uniformly bounded variance with mini-batch sizes proportional to the iteration budget, SLAM achieves an iteration complexity $\mathcal{O}(ε^{-2})$ and a sample complexity $\mathcal{O}(ε^{-4})$ for obtaining an iterate whose expected proximal-gradient residual norm is at most $ε$.

math.OC↗

arXiv2026

Representation type of contraction algebras

We classify the representation-finite, tame, and wild contraction algebras arising from 3-fold flopping contractions of isolated cDV singularities with at worst Gorenstein terminal sources. To achieve this, we first determine the representation type of all contracted preprojective algebras of Dynkin types $\mathsf{A}$, $\mathsf{D}$, and $\mathsf{E}$, and then use the representation type invariance under iterated flops and the radical structure of contraction algebras.

math.RT↗

arXiv2026

EagleVLA: Towards Onboard Real-Time Robot Control via Foresight-Aligned Asynchronous Inference

Vision-Language-Action (VLA) models have achieved impressive performance on diverse embodied tasks. However, deploying VLA models on low-power onboard devices, such as the Jetson Orin, remains challenging due to their high computational complexity, which leads to substantial inference latency and low control frequency. Asynchronous inference can partially mask this latency by parallelizing action execution and subsequent inference, but it introduces two critical issues: perception-execution misalignment and long reaction time. In this paper, we propose EagleVLA, a method for efficient VLA deployment on onboard devices via Foresight-Aligned Asynchronous Correction. To address misalignment, we train a lightweight future correction module that predicts future environment representations, allowing the action expert to predict actions from the future time step. To reduce reaction time, we introduce confidence-based scheduling optimization that adaptively balances VLM and action expert invocations. We also build a llama.cpp-based inference engine tailored for onboard VLA deployment, with system-level optimizations including CUDA graph reuse, GPU-resident intermediate buffering, and flow unrolling. Extensive experiments demonstrate that EagleVLA achieves 14.71x and 9.20x improvements in control frequency compared with naive PyTorch and vla.cpp on Jetson Orin, while outperforming VLASH by 14.8% in success rate on LIBERO benchmark. The code of our asynchronous algorithm is available on https://github.com/PKU-SEC-Lab/EagleVLA, and our efficient llama.cpp-based inference engine is available on https://github.com/PKU-SEC-Lab/EagleVLA-Edge.

cs.RO↗

arXiv2026

RAPAC-DP: Response-Aligned Pending-Action Compensation for Diffusion Policies under Delayed Execution

Cloud-side inference expands the computational resources available to imitation-learning policies, but communication and inference latencies create a mismatch between prediction and execution. We propose RAPAC-DP, a response-aligned pending-action compensation framework for diffusion- and flow-based action generators. By conditioning on actions committed during inference, RAPAC-DP generates a full-horizon action chunk aligned with the scheduled handover time. A lightweight pending-action encoder and LoRA adapters learn this compensation while keeping the pretrained base policy frozen. We construct delay-conditioned training samples from delay-free demonstrations, requiring neither an explicit dynamics model nor additional data collected under delayed execution. In simulation benchmarks at the largest evaluated delays, RAPAC-DP retains 81.4\% of its overall delay-free performance on Kinetix and achieves a mean success rate of 63.3\% across three RoboMimic tasks. Across 450 physical trials on a Franka Panda manipulator, RAPAC-DP increases the high-delay mean success rate from 28.9\% for RTC to 60.0\% across static and conveyor-based pick-and-place tasks.

cs.RO↗

arXiv2026

ChartEvo: Self-Evolving Agent Harnesses for Long-Tail Chart Reasoning

Multimodal large language models (MLLMs) have substantially advanced chart understanding and reasoning, yet their performance remains highly uneven across chart types. While modern MLLMs perform well on common charts, their accuracy drops sharply on long-tail charts with diverse visual structures and reasoning requirements. Tool-augmented agents can improve complex chart reasoning by introducing specialized visual capabilities, but manually engineering strategies and tools for the heterogeneous and evolving long tail is difficult to scale. We introduce \textbf{ChartEvo}, a recursive self-improvement framework that enables chart agents to adapt to underperforming chart types through experience-driven harness-level self-improvement. ChartEvo jointly evolves reusable chart-specific Skills and executable Tools, while learning reusable local tool-call chains to compose evolved capabilities and control the inference overhead of tool-augmented reasoning. On long-tail charts from ChartBench and ChartX, ChartEvo improves accuracy over its base MLLM, Qwen3.7-Plus, by \textbf{45.6\%} and \textbf{32.5\%}, respectively, demonstrating the effectiveness of recursive self-improvement for long-tail chart adaptation.

cs.AI↗

arXiv2026

BioProVLA-Agent: An Affordable, Protocol-Driven, Vision-Enhanced VLA-Enabled Embodied Multi-Agent System with Closed-Loop-Capable Reasoning for Biological Laboratory Manipulation

Biological laboratory automation can reduce repetitive manual work and improve reproducibility, but reliable embodied execution in wet-lab environments remains challenging. Protocols are often unstructured, labware is frequently transparent or reflective, and multi-step procedures require state-aware execution beyond one-shot instruction following. Existing robotic systems often rely on costly hardware, fixed workflows, dedicated instruments, or robotics-oriented interfaces. Here, we introduce BioProVLA-Agent, an affordable, protocol-driven, vision-enhanced embodied multi-agent system enabled by Vision-Language-Action (VLA) models for biological manipulation. The system uses protocols as the task interface and integrates protocol parsing, visual state verification, and embodied execution in a closed-loop workflow. A Tailored LLM Protocol Agent converts protocols into verifiable subtasks; a VLM-RAG Verification Agent assesses readiness and completion using observations, robot states, retrieved knowledge, and success/failure examples; and a VLA Embodied Agent executes verified subtasks through a lightweight policy. To improve robustness under wet-lab visual perturbations, we develop AugSmolVLA, an online augmentation strategy targeting transparent labware, reflections, illumination shifts, and overexposure. We evaluate the system on a hierarchical benchmark covering 15 atomic tasks, 6 composite workflows, and 3 bimanual tasks, including tube loading, sorting, waste disposal, cap twisting, and liquid pouring. Across normal and high-exposure settings, AugSmolVLA improves execution stability over ACT, X-VLA, and the original SmolVLA, especially for precise placement, transparent-object manipulation, composite workflows, and visually degraded scenes. These results suggest a practical route toward accessible, protocol-centered, and verification-capable embodied AI for biological manipulation.

cs.RO↗

arXiv2026

PhyPro-FM: A Physics and Prompt-Guided Graph Foundation Model for Contingency Analysis

The continuous evolution of next-generation power systems, characterized by the high penetration of renewable energy resources and dynamic topology variations, poses formidable challenges to traditional N-1/N-2 contingency analysis in terms of computational efficiency and scalability. While deep learning-based methods offer accelerated inference, existing studies predominantly treat contingency analysis as a pure regression problem, often overlooking the physical essence of grid operation and engineering requirements of real-world scenarios. To bridge this gap, this paper proposes a physics and prompt-guided graph foundation model (PhyPro-FM) for generalizable and engineering-viable contingency analysis. The proposed architecture integrates graph neural networks with a learnable global query mechanism and, notably, introduces a prompt-guided learning paradigm. By leveraging historical snapshots as few-shot prompts, the model dynamically captures correlations between target and historical operating conditions, significantly enhancing generalization capabilities under unseen topologies. Furthermore, we design a physics-informed training mechanism that prioritizes branch power flow errors over nodal voltage errors, aligning the optimization objective with critical grid security constraints. To ensure engineering applicability, a physics-informed inference mechanism is also developed, incorporating a residual-based correction module and a specialized post-processing strategy for singular branches to circumvent numerical instability. Comprehensive experiments demonstrate that PhyPro-FM outperforms state-of-the-art methods in accuracy and generalization, validating its superior physical consistency and robustness for practical engineering applications.

eess.SY↗

arXiv2026

Action-Dynamics Modeling and Cross-Temporal Interaction for Online Action Understanding

Online action understanding, encompassing action detection and anticipation, is central to numerous practical applications. However, untrimmed videos contain substantial redundant and noisy historical information, and the complementary interactions among historical, current, and future-oriented representations remain underexplored. To address these challenges, we propose the State-Specific Model (SSM), a unified framework for online action detection and anticipation. Its Representative State-Based Memory Compression module selects representative anchor frames from the observed memory and aggregates anchor-conditioned context into a compact set of representative memory states, thereby reducing memory redundancy. The subsequent Action Pattern Learning module learns multi-dimensional relations among these states and performs graph reasoning over the resulting directed representative-state graph to model action dynamics and derive a future-oriented cue. The Cross-Temporal Interaction module then enables this cue to interact with historical and current cues, refining the representations used for simultaneous online action detection and anticipation. Extensive experiments on EPIC-Kitchens-100, THUMOS'14, TVSeries, and the introduced Parkinson's Disease Mouse Behaviour dataset demonstrate competitive performance and generalizability across diverse online action understanding settings. These results underscore the value of graph-based action-dynamics modelling and cross-temporal interaction for online action understanding.

cs.CV↗

arXiv2026

OrbiSim: World Models as Differentiable Physics Engines for Embodied Intelligence

We present OrbiSim, a novel robotic simulation paradigm that redefines world models as a fully differentiable physics engine for embodied intelligence. Unlike prior world models that focus on unconstrained imagination in latent or visual domains, OrbiSim establishes a unified, physically-grounded pathway that bridges structured scene assets, neural dynamics, and downstream reinforcement learning. By enabling end-to-end differentiability throughout the entire simulation loop -- spanning from explicit state transitions to visual observation generation -- OrbiSim supports tasks traditionally intractable for classical simulators, such as differentiable contact modeling, gradient-based policy optimization under sparse rewards, and intuitive physical inference. Empirical results demonstrate that OrbiSim significantly outperforms state-of-the-art world models in both predictive fidelity and control performance. Furthermore, its consistent responsiveness to asset configurations and physical parameters suggests its potential as a differentiable tool for enhancing robot simulation and policy training.

cs.RO↗

arXiv2026

SALTO: Solver-Anchored Lifted Transfer Operators for Nonlinear Event Inference

Learned dynamical models can accurately predict trajectories while producing unreliable sensitivities when differentiated or transposed, limiting their use in inverse problems and scientific decision-making. Classical adjoints provide exact local derivatives, but a single adjoint cannot represent the nonlinear response of a system to a family of finite-amplitude perturbations. We introduce SALTO (Solver-Anchored Lifted Transfer Operators), a Koopman-based framework for inferring finite-amplitude sources. In the lifted space, the nonlinear dynamics are approximated by a linear propagator, and its transpose carries each sensor backward in a single solve. The result is a reusable lifted adjoint that predicts the measurement produced by any candidate localized event with one encoder pass and an inner product. To give the model the simulator's exact local behavior, SALTO imposes three structural constraints: it anchors the physical-state dynamics to the simulator's linearized propagator, centers the learned observables so that they vanish to second order at the reference state, and uses a block-triangular lifted propagator. These constraints guarantee that the model reduces to the simulator's tangent dynamics and classical adjoint as the amplitude vanishes, while the learned observables carry only the finite-amplitude correction. On three nonlinear PDE systems, SALTO predicts the measurements of finite-amplitude sources to within 2-8% where the classical adjoint is in error by 41-165%, recovers source position and intensity from sparse sensors nearly as accurately as inversion through the solver, and samples the joint posterior of two interacting sources, matching the solver's posterior on reaction-diffusion at a twentieth of its cost. One trained model serves new sensor layouts and measurement times with a single backward solve.

cs.LG↗

arXiv2026

Tree-Aware Posterior Distillation for Long-Horizon Agentic Reinforcement Learning

Reinforcement learning with verifiable rewards has become a scalable post-training paradigm for large language models. However, training agents over long-horizon interactions presents two challenges: using only terminal rewards makes turn-level credit assignment sparse and high-variance, while sequential mini-batch updates on a fixed rollout batch introduce policy staleness as the current policy drifts from the behavior policy. Existing approaches obtain denser credit via learned critics, process reward models, or on-policy distillation, but they rely on a value network, step-level annotations, or a stronger external teacher that increase training complexity. Meanwhile, importance sampling and clipping mitigate policy drift, but they do not specify a finite target that stops sequential updates from overshooting. In this work, we introduce TreeOPSD, a critic-free, tree-aware posterior self-distillation framework for long-horizon agentic reinforcement learning. Treating each interaction turn as a tree node, TreeOPSD branches alternative continuations from shared prefixes and recursively backs up terminal rewards into implicit turn-level credit. It then maps each credit to a closed-form, bounded teacher distribution parameterized by the likelihood ratio relative to the frozen behavior policy. Minimizing the divergence between this teacher and the student policy recovers the policy-gradient direction as the tangent at the behavior policy while bounding updates toward a finite target across sequential mini-batches. Empirically, TreeOPSD improves agentic capabilities across several competitive benchmarks and model scales, especially for long-horizon tasks, e.g., raising the average accuracy of Qwen3-30B-A3B-Thinking-2507 by 4.97 points over GRPO on the Deep Research setting.

cs.LG↗

arXiv2026

Fast-VLA: You Only Think Once for Robot Manipulation

Vision-language-action (VLA) policies commonly place a multi-billion-parameter model inside the feedback loop, repeatedly recomputing task context whenever they predict a new action chunk. Yet task understanding changes far more slowly than the robot state. We introduce Fast-VLA, which invokes a frozen 4B VLM once per episode to contextualize the instruction and initial views as fixed, multi-layer key-value task memory. During execution, a lightweight online actor fuses learned time- and arm-indexed queries with current visual and proprioceptive feedback to form action queries. These queries retrieve task context from the fixed memory and predict action chunks without re-running the foundation model. Fast-VLA achieves 92.46% and 92.40% success on RoboTwin 2.0 Clean and Randomized, and 95.95% and 79.11% on LIBERO and LIBERO-Plus evaluation. Against three continually conditioned baselines on the same hardware, it reduces RoboTwin amortized policy inference time by 10.9-17.1x and requires 1.22 GiB of post-prefill online resident memory. Task-memory swaps further show that the actor relies on episode-matched task memory. These results show that task context can be established once while closed-loop control remains responsive throughout execution. Project page: https://garfield-kh.github.io/FastVLA

cs.RO↗

arXiv2026

Euler: Towards Human-Centered Multi-Agent Mathematical Discovery

Mathematical research drives scientific discovery, and recent advances in AI for mathematics have shown that language-model agents can solve challenging problems and develop substantial mathematical proofs. Yet much of today's AI-for-mathematics work centers on obtaining a final answer. This emphasis leaves the exploration behind a result difficult for researchers to understand, while long-running investigations face fragmented context and the risk of unsupported claims propagating across reasoning steps. We present Euler, a human-centered mathematical research system built around a shared, structured representation of the research process. Euler organizes mathematical statements, assumptions, proof dependencies, alternative approaches, failed attempts, and verification evidence into connected research graphs. This representation allows researchers to trace how results are developed and supplies agents with persistent, task-relevant knowledge for planning, collaboration, and verification across sessions. Researchers can also select a graph node linked to a saved team state, revisit the agents' earlier reasoning, and explore alternative directions through continued interaction. We illustrate Euler's capabilities through three mathematical research case studies and describe the implemented system and its software validation.

cs.AI↗

arXiv2026

Model Predictive Task Sampling for Efficient and Robust Adaptation

Foundation models have revolutionized general-purpose problem-solving, offering rapid task adaptation through pretraining, meta-training, and finetuning. Recent crucial advances in these paradigms reveal the importance of challenging task prioritized sampling to enhance adaptation robustness under distribution shifts. However, ranking task difficulties over iteration as a preliminary step typically requires exhaustive task evaluation, which is practically unaffordable in computation and data-annotation. This study provides a novel perspective to illuminate the possibility of leveraging the dual importance of adaptation robustness and learning efficiency, particularly in scenarios where task evaluation is risky or costly, such as iterative agent-environment interactions for robotic policy evaluation or computationally intensive inference steps for finetuning foundation models. Firstly, we introduce Model Predictive Task Sampling (MPTS), a framework that bridges the task space and adaptation risk distributions, providing a theoretical foundation for robust active task sampling. MPTS employs a generative model to characterize the episodic optimization process and predicts task-specific adaptation risk via posterior inference. The resulting risk predictive model amortizes the costly evaluation of task adaptation performance and provably approximates task difficulty rankings. MPTS seamlessly integrates into zero-shot, few-shot, and supervised finetuning settings. Empirically, we conduct extensive experiments in pattern recognition using foundation models and sequential decision-making. Our results demonstrate that MPTS significantly enhances adaptation robustness for tail risk or out-of-distribution (OOD) tasks and improves learning efficiency compared to state-of-the-art (SoTA) methods. The code is available at the project site https://github.com/thu-rllab/MPTS.

cs.LG↗

arXiv2026

You Only Edit Once: Incentivizing In-Context Capability of LLMs via Local Demonstration Refinement

In-context learning (ICL) is crucial for boosting the inference performance of large language models (LLMs). However, the effectiveness of ICL in LLMs is greatly influenced by the choice of demonstration sets. Exhaustive searches over these sets are combinatorial, and existing selectors often rely on relevance or likelihood proxies to implicitly assess ICL quality. Making repeated queries to the target LLM with these strategies can incur substantial costs. This work simplifies selection by framing it as a constrained local search problem and presents local demonstration editing (LDE). Starting with an initially retrieved set of demonstrations, LDE employs a single structured edit to explore its surrounding neighborhood while balancing performance gains with search costs. Technically, LDE is reduced to a policy search problem, for which we train a small LLM, referred to as Jev-LDE. This model as the System-1 modifies the retrieved demonstration set by performing actions such as \texttt{Keep}, \texttt{Delete}, or \texttt{Replace} elements, all within a framework of reinforcement learning with verifiable rewards. At test time, Jev-LDE executes a single edit of the retrieved demonstration set, followed by one inference from the target LLM, avoiding the need for iterative context scoring or subset searches. Across standard classification benchmarks, various target LLMs with Jev-LDE as the plug-and-play module consistently improve ICL performance, and Jev-LDE shows transferability to held-out benchmarks and models without retraining. These findings indicate that the LDE approach offers an efficient and adaptable method for harnessing the ICL capabilities of target LLMs.

cs.LG↗

arXiv2026

Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling

Reinforcement learning (RL) is essential for adaptive decision-making, e.g., robust Meta-RL and domain randomization (DR), and efficient post-training of large language models (LLMs), where tasks are commonly structured as Markov decision processes or prompts. A central bottleneck in all these settings is the cost of agent-environment interactions required for task selection and policy optimization. Model predictive task sampling (MPTS) has emerged as a promising approach to improve sample efficiency by querying informative tasks via a risk predictive model (RPM) trained on optimization history. However, existing RPMs suffer from two failure modes: (i) sparse optimization histories, which limit RPMs' generalization across the task space, and (ii) a one-step lag in risk approximation, which causes biased difficulty estimation as the policy evolves. This work formalizes these failure modes, derives lagged-risk decompositions that expose the resulting temporal bias, and recasts risk prediction as an in-context sequence modeling problem. The developed RPM integrates a one-step look-ahead mechanism with a temporal-weighted sliding window to mitigate data non-stationarity and scarcity, without requiring additional rollouts. Empirically, our approach yields more reliable difficulty estimates and consistent performance gains across robust Meta-RL, DR, and prompt curriculum RL post-training of LLMs.

cs.AI↗

arXiv2026

Intra- and Cross-Scale Feature Interaction Network for Referring Remote Sensing Image Segmentation

Referring remote sensing image segmentation (RRSIS) is a challenging multimodal task that requires accurate localization and pixel-level segmentation of targets specified by natural-language expressions. Existing RRSIS datasets remain limited in image resolution, scene diversity, and category coverage, which restricts the generalization ability and practical applicability of current methods. To advance this field, we introduce NWPU-Refer, the largest and most diverse bilingual RRSIS dataset to date. It contains 15,003 high-resolution images (1024--2048 px) collected from more than 30 countries across five continents, together with 49,745 annotated targets covering single-object, multi-object, and no-target scenarios. We further propose the Multi-scale Referring Segmentation Network (MRSNet), a framework tailored to the characteristics of remote sensing imagery. Specifically, MRSNet incorporates an Intra-scale Feature Interaction Module (IFIM) to refine fine-grained features within each encoder stage and a Hierarchical Feature Interaction Module (HFIM) to integrate cross-scale information while preserving spatial structure. Extensive experiments on NWPU-Refer and RRSIS-D demonstrate that MRSNet achieves strong and competitive performance across multiple metrics, especially under strict IoU thresholds and IoU-based evaluation, validating the effectiveness of the proposed dataset and model. The dataset and code are publicly available at https://github.com/CVer-Yang/NWPU-Refer.

cs.CV↗

arXiv2026

A Stochastic LineseArch Method (SLAM) for Minimizing Expectation Residuals

Most existing rate and complexity guarantees for stochastic gradient methods in $L$-smooth settings mandates that such sequences be non-adaptive, non-increasing, and upper bounded by $\tfrac{a}{L}$ for $a > 0$. This requires knowledge of $L$ and may preclude larger steps. Motivated by these shortcomings, we present an Armijo-enabled stochastic linesearch framework with common random number (CRN)-enabled stochastic zeroth- and first-order oracles. The resulting steplength sequence is non-monotone and requires neither knowledge of $L$ nor any other problem parameters. We then prove that the expected stationarity residual diminishes at a rate of $\mathcal{O}(1/\sqrt{K})$, where $K$ denotes the iteration budget. Furthermore, the resulting iteration and sample complexities for computing an $ε$-stationary point are $\mathcal{O}(ε^{-2})$ and $\mathcal{O}\left(ε^{-4}\right)$. The proposed method allows for a simple nonsmooth convex component in the objective, addressed through proximal gradient updates. Analogous guarantees are provided in the Polyak-Lojasiewicz (PL) setting and convex regimes. Preliminary numerical experiments are seen to be promising.

math.OC↗