arXiv subjects

Hao Wang

Publications and source records attributed to Hao Wang.

At least 343 records · Page 19Linked to original sources

arXiv2026

Faster Stochastic ADMM for Nonsmooth Composite Convex Optimization in Hilbert Space

In this paper, a stochastic alternating direction method of multipliers (ADMM) is proposed for a class of nonsmooth composite and stochastic convex optimization problems in Hilbert space, motivated by optimization problems constrained by partial differential equation (PDE) with random coefficients. We prove the strong convergence of the proposed ADMM algorithm in the strongly convex case, and show the faster nonergodic convergence rates in terms of functional values and feasibility violation for both strongly convex and general convex cases. We demonstrate the application of the proposed method to solve certain model problems, along with its associated probability bound of large deviation. Some preliminary numerical results illustrate the efficiency of our method.

math.OC↗

arXiv2026

VLM-AutoDrive: Post-Training Vision-Language Models for Safety-Critical Autonomous Driving Events

The rapid growth of ego-centric dashcam footage presents a major challenge for detecting safety-critical events such as collisions and near-collisions, scenarios that are brief, rare, and difficult for generic vision models to capture. While multimodal large language models (MLLMs) demonstrate strong general reasoning ability, they underperform in driving contexts due to domain and temporal misalignment. We introduce VLM-AutoDrive, a modular post-training framework for adapting pretrained Vision-Language Models (VLMs) to high-fidelity anomaly detection. The framework integrates metadata-derived captions, LLM-generated descriptions, visual question answering (VQA) pairs, and chain-of-thought (CoT) reasoning supervision to enable domain-aligned and interpretable learning. Off-the-shelf VLMs such as NVIDIA's Cosmos-Reason1 7B (CR1) exhibit near-zero Collision recall in zero-shot settings; fine-tuning with VLM-AutoDrive improves Collision F1 from 0.00 to 0.69 and overall accuracy from 35.35% to 77.27%. VLM-AutoDrive offers a scalable recipe for adapting general-purpose VLMs to safety-critical, temporally localized perception tasks. Evaluated on real-world Nexar dashcam videos, it achieves substantial gains in Collision and Near-Collision detection while producing interpretable reasoning traces, bridging the gap between perception, causality, and decision reasoning in autonomous driving.

cs.CV↗

arXiv2026

Privacy-Preserving Federated Radio Map Learning for Wireless Digital Twins via Adaptive Noise Allocation

Radio maps provide a foundational data layer for wireless digital twins, and federated learning offers a natural framework for their distributed construction without centralizing raw radio environment data. However, the exchanged client model updates may still leak transmitter-location information, even when the underlying measurement data are never shared. Existing noise-based privacy defenses inject perturbation either uniformly across all uploaded coordinates or according to a fixed static rule, thereby ignoring the architecture-specific structure of this leakage. This paper proposes a budget-constrained adaptive noise allocation mechanism that redistributes a fixed perturbation budget across transmitter-sensitive upload groups identified from the two-stage RadioUNet architecture. The proposed method uses low-dimensional upload statistics to dynamically adjust group-wise noise scales and is integrated locally before client upload transmission. We evaluate the framework on a federated radio map learning task under a unified noise multiplier, comparing it against uniform and structure-aware baselines using reconstruction mean squared error and transmitter localization error as metrics. Results show that adaptive allocation achieves the strongest privacy protection while maintaining the best reconstruction quality among all noise-based defenses under a matched perturbation budget.

eess.SP↗

arXiv2026

TFZ-Tree: An Ultra-Lightweight Waveform Classification Framework for Resource-Constrained Devices

Under the trend of multi-waveform coexistence in 6G IoT, intelligent receivers must first identify physical-layer waveform types before performing correct demodulation and resource scheduling. However, existing signal identification research largely focuses on symbol-level modulation classification. Research directly targeting physical-layer waveform types (e.g., OFDM, OTFS, LoRa) is not only extremely scarce but also heavily reliant on deep neural networks and complex time-frequency transforms, making deployment on resource-constrained terminals difficult. Symbol modulation classification methods themselves cannot circumvent the prerequisite of ``waveform identification first.'' To address this dual gap, we propose an ultra-lightweight waveform classification framework based on time-frequency multidimensional features with a cooperative Z-test tree (ZTree). The framework employs low-complexity time-domain feature extraction, and the classification backend adopts a ZTree optimized by Z-statistical testing, which uses hypothesis testing confidence to automatically control decision tree splitting and size, ensuring efficient execution on resource-limited processors. Tested on ten 6G candidate waveforms including OFDM, OTFS, DSSS, LoRa, and NB-IoT, the method achieves 99.5\% average accuracy under AWGN and 87.4\% under TDL-C multipath channels, with main confusion between OTFS and LoRa. Implemented in C on an x86 platform, single inference latency is under 4~ms. To the best of our knowledge, this is the first work achieving real-time recognition of ten IoT waveform types. Future work will target deployment acceleration on embedded MCUs. Code and dataset are open-sourced at: https://github.com/Einstein-sworder/IoT-wave.

eess.SP↗

arXiv2026

PersonaFingerprint: Measuring Persona Inference on Modern Websites with LLM-Driven Browsing

Website Fingerprinting (WFP) has traditionally focused on inferring which website a user visits from encrypted traffic metadata such as packet sizes and timing. In this paper, we identify and quantify a new privacy risk in modern web settings: an adversary can infer a user's persona using only packet-length and inter-arrival-time sequences. To study this risk at scale, we build an LLM-driven multi-agent browsing framework that enforces controllable persona constraints while a computer-use agent interacts with real websites and collects corresponding encrypted traffic traces. We formalize persona fingerprinting under both closed-set and open-world settings and further evaluate whether persona information is already embedded in representations learned by existing WFP models and can be amplified at low cost. Across 10 modern websites and 15 personas (plus an open-world class), persona inference achieves about 84% accuracy on mixed-site traffic; moreover, a lightweight multi-task objective can boost persona accuracy to around 80% while retaining strong site classification performance (about 93% baseline). Our results show that, on modern websites, encrypted traffic metadata can leak not only which site a user visits, but also how they browse and who is browsing.

cs.CR↗

arXiv2026

The Very Late Time Afterglow of GW170817 Favors a Wobbling Jet

GW170817 remains the only binary neutron star merger detected through multimessenger emission. Its afterglow has been monitored for nearly a decade, offering an unprecedented opportunity to probe the properties of the outflow. The shallow decay of the very late-time afterglow challenges the prediction of a collimated structured jet. Motivated by recent general-relativistic magnetohydrodynamic simulations, we propose that the GW170817 afterglow is powered by a wobbling jet that drags a ring on the sky. This structure predicts a post-break decay rate shallower than that of a collimated jet, as observers will see a progressively longer emitting arc after the break. A misaligned ring-shaped jet can therefore self-consistently explain the multimessenger data without invoking any extra component. Through a Bayesian analysis of the multimessenger data, we find a ring-shaped jet is favored over a collimated jet at a significance level of 4.8$σ$. Our results imply a wobbling angle of $\sim 27^\circ$. Such a large angle points to a significant disk tilt, potentially arising from disk-infalling gas interaction or asymmetric angular momentum ejection. Similar shallow decays have also been found in other GRB afterglows, raising the possibility that wobbling jets are common among GRBs.

astro-ph.HE↗

arXiv2026

Rongzai agent: A Large Language Model-Based Autonomous Assistant for Rietveld Refinement of Neutron Diffraction Data

Neutron diffraction (ND) is an indispensable technique for determining atomic positions (especially light elements) and thus serves as a critical probe for revealing microscopic structures in materials science. However, traditional Rietveld refinement of ND data relies heavily on manual operation of specialized software, which is time-consuming, labor-intensive, and highly dependent on user expertise, severely hindering automated analysis. The automation of Rietveld refinement has long been a long-standing and challenging problem in crystallography. To address this challenge, this paper presents the Dr.Sai-Rongzai agent, an autonomous refinement assistant based on a large language model (LLM), a specialist knowledge base, and the GSAS-II refinement engine, achieving for the first time an intelligent refinement that integrates knowledge-driven decision-making. The agent accomplishes a fully automated workflow from natural language task parsing to autonomous decision-making, execution of refinement strategies, and report generation. Evaluation on five representative samples shows that the Rongzai agent achieves lower Rwp values than human specialists on three samples (2.88% vs. 4.42%, 5.06% vs. 5.40%, 7.60% vs. 9.00%), while on the other two samples its results are very close to those of the specialists. The agent is currently deployed at the China Spallation Neutron Source (CSNS) and is open for external user registration, providing an intelligent and user-friendly analytical tool for materials research. This work fully leverages the cutting-edge advantages of LLM, offers a new path to solve the long-standing problem of automated refinement, takes a key step toward intelligent and fully automated crystallographic analysis, and holds great potential to accelerate AI for Science discoveries in neutron-based materials characterization.

cond-mat.mtrl-sci↗

arXiv2026

Turning Intent into Specifications: A Benchmark and an Interactive User-Assistant Agent

Today's agents are highly effective at implementing well-scoped software design plans, but user intent is often vague and admits multiple equally valid solutions. In this paper, we introduce SpecBench, a new benchmark for evaluating an agent's ability to translate user intent into a structured, executable specification that aligns with user preferences. The agent is given access to past user conversations and may interact with the user for a fixed number of rounds to ask clarifying questions. We find that existing agents exhibit two extreme behaviors: they either (i) struggle to collaborate proactively with users, entering implementation mode too quickly while overestimating their understanding of user preferences, or (ii) exhaust their question budget by asking about every ambiguous design choice. To address this limitation, we introduce a user-assistant agent: Buddy. It follows a workflow inspired by classical morphological analysis, decomposing user intent into a structured space of design dimensions and candidate choices. It then creates simulated users to evaluate these choices, before engaging the real user to resolve remaining ambiguities and finalize the specification. By shifting the focus from execution to specification, SpecBench and Buddy emphasize agent-user collaboration (not just code generation) as a key frontier in future agent design.

cs.HC↗

arXiv2026

MotionGRPO: Overcoming Low Intra-Group Diversity in GRPO-Based Egocentric Motion Recovery

This paper studies full-body 3D human motion recovery from head-mounted device signals. Existing diffusion-based methods often rely on global distribution matching, leading to local joint reconstruction errors. We propose MotionGRPO, a novel framework leveraging reinforcement learning post-training to inject fine-grained guidance into the diffusion process. Technically, we model diffusion sampling as a Markov decision process optimized via Group Relative Policy Optimization (GRPO). To this end, we introduce a hybrid reward mechanism that combines a learned conditioned perceptual model for global visual plausibility and explicit constraints for local joint precision. Our key technical insight is that policy optimization in diffusion-based recovery suffers from vanishing gradients due to limited intra-group sample diversity. To address this, we further introduce a noise-injection strategy that explicitly increases sample variance and stabilizes learning. Extensive experiments demonstrate that MotionGRPO achieves state-of-the-art performance with superior visual fidelity

cs.CV↗

arXiv2026

Offline Policy Evaluation for Manipulation Policies via Discounted Liveness Formulation

Policy evaluation is a fundamental component of the development and deployment pipeline for robotic policies. In modern manipulation systems, this problem is particularly challenging: rewards are often sparse, task progression of evaluation rollouts are often non-monotonic as the policies exhibit recovery behaviors, and evaluation rollouts are necessarily of finite length. This finite length introduces truncation bias, breaking the infinite-horizon assumptions underlying standard methods relying on Bellman equations/principle of optimality. In this work, we propose a framework for offline policy evaluation from sparse rewards based on a liveness-based Bellman operator. Our formulation interprets policy evaluation as a task-completion problem and yields a conservative fixed-point value function that is robust to finite-horizon truncation. We analyze the theoretical properties of the proposed operator, including contraction guarantees, and show how it encodes task progression while mitigating truncation bias. We evaluate our method on two simulated manipulation tasks using both a Vision-Language-Action model and a diffusion policy, and a cloth folding task using human demonstrations. Empirical results demonstrate that our approach more accurately reflects task progress and substantially reduces truncation bias, outperforming classical baselines such as TD(0) and Monte Carlo policy evaluation.

cs.RO↗

arXiv2026

StepCodeReasoner: Aligning Code Reasoning with Stepwise Execution Traces via Reinforcement Learning

Existing code reasoning methods primarily supervise final code outputs, ignoring intermediate states, often leading to reward hacking where correct answers are obtained through inconsistent reasoning. We propose StepCodeReasoner, a framework that introduces explicit intermediate execution-state supervision. By automatically inserting structured print-based execution-trace anchors into code, the model is trained to predict runtime states at each step, transforming code reasoning into a verifiable, stepwise execution modeling problem. Building on this execution-aware method, we introduce Bi-Level GRPO, a reinforcement learning algorithm for structured credit assignment at two levels: inter-trajectory, comparing alternative execution paths, and intra-trajectory, rewarding intermediate accuracy based on its impact on downstream correctness. Extensive experiments demonstrate that StepCodeReasoner achieves SOTA performance in code reasoning. In particular, our 7B model achieves 91.1\% on CRUXEval and 86.5\% on LiveCodeBench, outperforming the CodeReasoner-7B baseline (86.0\% and 77.7\%) and GPT-4o (85.6\% and 75.1\%). Furthermore, on the execution-trace benchmark REval, our model scores 82.9\%, outperforming baseline CodeReasoner-7B (72.3\%), its 14B counterpart (81.1\%), and GPT-4o (77.3\%). Additionally, our approach also improves code generation performance, demonstrating that explicit execution modeling enhances both code reasoning and code generation.

cs.SE↗

arXiv2026

Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack

Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a score without performing the intended task, emerges spontaneously in frontier models without overfitting. We argue that benchmarks must be secure by design. From past incidents of reward hacks, we derive a taxonomy of eight recurring flaw patterns and compile them into the Agent-Eval Checklist for benchmark designers. We condense the insights into BenchJack, an automated red-teaming system that drives coding agents to audit benchmarks and identify possible reward-hacking exploits in a clairvoyant manner. Moreover, we extend BenchJack to an iterative generative-adversarial pipeline that discovers new flaws and patches them iteratively to improve benchmark robustness. We apply BenchJack to 10 popular agent benchmarks spanning software engineering, web navigation, desktop computing, and terminal operations. BenchJack synthesizes reward-hacking exploits that achieve near-perfect scores on most of the benchmarks without solving a single task, surfacing 219 distinct flaws across the eight classes. Moreover, BenchJack's extended pipeline reduces the hackable-task ratio from near 100% to under 10% on four benchmarks without fatal design flaws, fully patching WebArena and OSWorld within three iterations. Our results show that evaluation pipelines have not internalized an adversarial mindset, and that proactive auditing could help close the security gap for the fast-paced benchmarking space.

cs.AI↗

arXiv2026

EvoDriveVLA: Evolving Driving VLA Models via Collaborative Perception-Planning Distillation

Vision-Language-Action models have shown great promise for autonomous driving, yet they suffer from degraded perception after unfreezing the visual encoder and struggle with accumulated instability in long-term planning. To address these challenges, we propose EvoDriveVLA-a novel collaborative perception-planning distillation framework that integrates self-anchored perceptual constraints and future-informed trajectory optimization. Specifically, self-anchored visual distillation leverages self-anchor teacher to deliver visual anchoring constraints, regularizing student representations via trajectory-guided key-region awareness. In parallel, future-informed trajectory distillation employs a future-aware oracle teacher with coarse-to-fine trajectory refinement and Monte Carlo dropout sampling to synthesize reasoning trajectories that model future evolutions, enabling the student model to internalize the future-aware insights of the teacher. EvoDriveVLA achieves SOTA performance in nuScenes open-loop evaluation and significantly enhances performance in NAVSIM closed-loop evaluation. Our code is available at: https://github.com/hey-cjj/EvoDriveVLA.

cs.CV↗

arXiv2026

ReCAPA: Hierarchical Predictive Correction to Mitigate Cascading Failures

Vision-Language-Action systems follow instructions to execute multi-step tasks in multimodal environments. Recent VLA approaches typically rely on post-hoc correction mechanisms or operate under fixed task decompositions and alignment schemes. However, once an intermediate step is mis-specified, local errors propagate through subsequent steps and eventually accumulate into cascading failures. To mitigate this compounding effect, we propose Predictive Alignment and Planning Architecture, a framework that uses prediction and contrast to adjust deviations across three levels: actions, subgoals, and trajectories. Semantic alignment is enforced at all levels using a Sinkhorn-based module and a Score-field module. The predictive correction and alignment jointly update the action generator during training, enabling it to adjust fine-grained steps to remain aligned with the overall intent. We further introduce two new metrics to quantify error propagation and recovery processes in tasks, capturing how mistakes spread and fade over long-horizon execution. Experiments show that ReCAPA achieves competitive results on embodied agent benchmarks such as VisualAgentBench, MineDojo, and AI2-THOR, outperforming strong proprietary and open-source Large Language Model baselines.

cs.AI↗

arXiv2026

Comparing Qubit and Qudit Encodings for EV Charging and Trip Assignment Problems

Variational quantum algorithms have attracted attention for their potential to solve combinatorial optimization problems. We study how the choice of encoding affects the resource requirements and optimization behavior of a variational quantum optimization algorithm. In order to quantify these effects, realistically inspired constrained electric vehicle (EV) fleet management problems were considered. These problems couple determining the optimal EV battery charging schedule with assigning EVs to trips requested by customers. We compare a conventional binary (qubit) trip encoding with an integer (qudit) encoding that represents assignments more directly. Both encodings guarantee the same feasible solution set, while the qudit encoding exponentially reduces the required Hilbert-space dimension. We solve many random instances of highly constrained uni- and bi-directional charging problems using qudit-based quantum approximate optimization algorithm (QAOA) and thoroughly evaluate the performance results. We find that the qudit encoding of customer trips achieves similar or better optimization performance at much reduced resource requirements and shorter simulation runtime. These results highlight qudit-native encodings as a practical route for integer and multi-valued scheduling problems in variational quantum optimization.

quant-ph↗

arXiv2026

VEGA: Visual Encoder Grounding Alignment for Spatially-Aware Vision-Language-Action Models

Precise spatial reasoning is fundamental to robotic manipulation, yet the visual backbones of current vision-language-action (VLA) models are predominantly pretrained on 2D image data without explicit 3D geometric supervision, resulting in representations that lack accurate spatial awareness. Existing implicit spatial grounding methods partially address this by aligning VLA features with those of 3D-aware foundation models, but they rely on empirical layer search and perform alignment on LLM-level visual tokens where spatial structure has already been entangled with linguistic semantics, limiting both generalizability and geometric interpretability. We propose VEGA (Visual Encoder Grounding Alignment), a simple yet effective framework that directly aligns the output of the VLA's visual encoder with spatially-aware features from DINOv2-FiT3D, a DINOv2 model fine-tuned with multi-view consistent 3D Gaussian Splatting supervision. By performing alignment at the visual encoder output level, VEGA grounds spatial awareness before any linguistic entanglement occurs, offering a more interpretable and principled alignment target. The alignment is implemented via a lightweight projector trained with a cosine similarity loss alongside the standard action prediction objective, and is discarded at inference time, introducing no additional computational overhead. Extensive experiments on simulation benchmark and real-world manipulation tasks demonstrate that VEGA consistently outperforms existing implicit spatial grounding baselines, establishing a new state-of-the-art among implicit spatial grounding methods for VLA models.

cs.RO↗

arXiv2026

BabelDOC: Better Layout-Preserving PDF Translation via Intermediate Representation

As global cross-lingual communication intensifies, language barriers in visually rich documents such as PDFs remain a practical bottleneck. Existing document translation pipelines face a tension between linguistic processing and layout preservation: text-oriented Computer-Assisted Translation (CAT) systems often discard structural metadata, while document parsers focus on extraction and do not support faithful re-rendering after translation. We introduce BabelDOC, an Intermediate Representation (IR)-based framework for layout-preserving PDF translation. BabelDOC decouples visual layout metadata from semantic content, enabling document-level translation operations such as terminology extraction, cross-page context handling, glossary-constrained generation, and formula placeholdering. The translated content is then re-anchored to the original layout through an adaptive typesetting engine. Experiments on a curated 200-page benchmark, together with human evaluation and multimodal LLM-as-a-judge evaluation, show that BabelDOC improves layout fidelity, visual aesthetics, and terminology consistency over representative baselines, while maintaining competitive translation precision. The open-source toolkit and its interactive downstream applications are publicly available and have attracted over 8.4K GitHub stars and 17 contributors at the time of writing. A demonstration video is also available.

cs.CV↗

arXiv2026

Can Recommender Systems Teach Themselves? A Recursive Self-Improving Framework with Fidelity Control

The scarcity of high-quality training data presents a fundamental bottleneck to scaling machine learning models. This challenge is particularly acute in recommendation systems, where extreme sparsity in user interactions leads to rugged optimization landscapes and poor generalization. We propose the Recursive Self-Improving Recommendation (RSIR) framework, a paradigm in which a model bootstraps its own performance without reliance on external data or teacher models. RSIR operates in a closed loop: the current model generates plausible user interaction sequences, a fidelity-based quality control mechanism filters them for consistency with user's approximate preference manifold, and a successor model is augmented on the enriched dataset. Our theoretical analysis shows that RSIR acts as a data-driven implicit regularizer, smoothing the optimization landscape and guiding models toward more robust solutions. Empirically, RSIR yields consistent, cumulative gains across multiple benchmarks and architectures. Notably, even smaller models benefit, and weak models can generate effective training curricula for stronger ones. These results demonstrate that recursive self-improvement is a general, model-agnostic approach to overcoming data sparsity, suggesting a scalable path forward for recommender systems and beyond. Our anonymized code is available at https://github.com/USTC-StarTeam/RSIR.

cs.IR↗