arXiv subjects

Han Wang

Publications and source records attributed to Han Wang.

At least 145 records · Page 8Linked to original sources

arXiv2025

FreeAskWorld: An Interactive and Closed-Loop Simulator for Human-Centric Embodied AI

As embodied intelligence emerges as a core frontier in artificial intelligence research, simulation platforms must evolve beyond low-level physical interactions to capture complex, human-centered social behaviors. We introduce FreeAskWorld, an interactive simulation framework that integrates large language models (LLMs) for high-level behavior planning and semantically grounded interaction, informed by theories of intention and social cognition. Our framework supports scalable, realistic human-agent simulations and includes a modular data generation pipeline tailored for diverse embodied tasks. To validate the framework, we extend the classic Vision-and-Language Navigation (VLN) task into a interaction enriched Direction Inquiry setting, wherein agents can actively seek and interpret navigational guidance. We present and publicly release FreeAskWorld, a large-scale benchmark dataset comprising reconstructed environments, six diverse task types, 16 core object categories, 63,429 annotated sample frames, and more than 17 hours of interaction data to support training and evaluation of embodied AI systems. We benchmark VLN models, and human participants under both open-loop and closed-loop settings. Experimental results demonstrate that models fine-tuned on FreeAskWorld outperform their original counterparts, achieving enhanced semantic understanding and interaction competency. These findings underscore the efficacy of socially grounded simulation frameworks in advancing embodied AI systems toward sophisticated high-level planning and more naturalistic human-agent interaction. Importantly, our work underscores that interaction itself serves as an additional information modality.

cs.AI↗

arXiv2025

MEML-GRPO: Heterogeneous Multi-Expert Mutual Learning for RLVR Advancement

Recent advances demonstrate that reinforcement learning with verifiable rewards (RLVR) significantly enhances the reasoning capabilities of large language models (LLMs). However, standard RLVR faces challenges with reward sparsity, where zero rewards from consistently incorrect candidate answers provide no learning signal, particularly in challenging tasks. To address this, we propose Multi-Expert Mutual Learning GRPO (MEML-GRPO), an innovative framework that utilizes diverse expert prompts as system prompts to generate a broader range of responses, substantially increasing the likelihood of identifying correct solutions. Additionally, we introduce an inter-expert mutual learning mechanism that facilitates knowledge sharing and transfer among experts, further boosting the model's performance through RLVR. Extensive experiments across multiple reasoning benchmarks show that MEML-GRPO delivers significant improvements, achieving an average performance gain of 4.89% with Qwen and 11.33% with Llama, effectively overcoming the core limitations of traditional RLVR methods.

cs.AI↗

arXiv2025

Multimodal DeepResearcher: Generating Text-Chart Interleaved Reports From Scratch with Agentic Framework

Visualizations play a crucial part in effective communication of concepts and information. Recent advances in reasoning and retrieval augmented generation have enabled Large Language Models (LLMs) to perform deep research and generate comprehensive reports. Despite its progress, existing deep research frameworks primarily focus on generating text-only content, leaving the automated generation of interleaved texts and visualizations underexplored. This novel task poses key challenges in designing informative visualizations and effectively integrating them with text reports. To address these challenges, we propose Formal Description of Visualization (FDV), a structured textual representation of charts that enables LLMs to learn from and generate diverse, high-quality visualizations. Building on this representation, we introduce Multimodal DeepResearcher, an agentic framework that decomposes the task into four stages: (1) researching, (2) exemplar report textualization, (3) planning, and (4) multimodal report generation. For the evaluation of generated multimodal reports, we develop MultimodalReportBench, which contains 100 diverse topics served as inputs along with 5 dedicated metrics. Extensive experiments across models and evaluation methods demonstrate the effectiveness of Multimodal DeepResearcher. Notably, utilizing the same Claude 3.7 Sonnet model, Multimodal DeepResearcher achieves an 82% overall win rate over the baseline method.

cs.CL↗

arXiv2025

RoadSceneBench: A Lightweight Benchmark for Mid-Level Road Scene Understanding

Understanding mid-level road semantics, which capture the structural and contextual cues that link low-level perception to high-level planning, is essential for reliable autonomous driving and digital map construction. However, existing benchmarks primarily target perception tasks such as detection or segmentation, overlooking the reasoning capabilities required to infer road topology and dynamic scene structure. To address this gap, we present RoadSceneBench, a lightweight yet information-rich benchmark designed to evaluate and advance visual reasoning in complex road environments. Unlike large-scale perception datasets, RoadSceneBench emphasizes relational understanding and structural consistency, encouraging models to capture the underlying logic of real-world road scenes. Furthermore, to enhance reasoning reliability, we propose Hierarchical Relational Reward Propagation with Temporal Consistency (HRRP-T), a training framework for Vision-Language Models (VLMs) in which reward signals adaptively promote spatial coherence and semantic alignment throughout the reasoning process. This paradigm enables models to move beyond static recognition toward geometry-aware and temporally consistent reasoning. Extensive experiments demonstrate that our method achieves state-of-the-art performance across diverse road configurations. RoadSceneBench thus provides a compact yet powerful foundation for studying mid-level road semantics and fostering structure-aware autonomous perception. Our dataset is available at https://github.com/XiyanLiu/RoadSceneBench.

cs.CV↗

arXiv2025

On the Design of Rational Polynomial State Feedback Controllers

One of the desirable objectives in feedback control design is to formulate and solve the design problem as an optimisation problem that is convex, so that an optimal solution can be found efficiently. Unfortunately many control design problems are non-convex: approximations, relaxations, or iterative schemes are usually employed to solve them. Several such approaches have been developed in the literature, for example Sum-of-Squares (SOSs) methods have been used for systems described by polynomial dynamics. Alternatively, and relevant to this paper, one can choose a (non-unique) linear-like representation of the system and solve the resulting state-dependent Linear Matrix Inequalities (LMIs) or use SOSs optimisation techniques to derive a control law. This SOS method has been shown to effectively design polynomial and rational controllers for nonlinear polynomial systems, offering a broader class of controllers and the potential for improved performance and robustness guarantees. In this paper, we start off by considering rational functions as controllers for nonlinear systems and propose a procedure for designing such controllers by iteratively solving convex SOS optimisation problems. Our approach decouples the controller structure from the system dynamics and incorporates it as a constraint within the optimisation problem, which results in an optimisation that co-designs aspects of the controller and the Lyapunov function at the same iterative step. We theoretically establish the properties of this procedure by showing that several existing rational controller design methods can be recovered as special cases of this procedure. The proposed method is evaluated on various nonlinear benchmark system examples, demonstrating improved performance and robustness over both polynomial controllers and rational controllers obtained by existing approaches.

math.OC↗

arXiv2025

ChineseVideoBench: Benchmarking Multi-modal Large Models for Chinese Video Question Answering

This paper introduces ChineseVideoBench, a pioneering benchmark specifically designed for evaluating Multimodal Large Language Models (MLLMs) in Chinese Video Question Answering. The growing demand for sophisticated video analysis capabilities highlights the critical need for comprehensive, culturally-aware evaluation frameworks. ChineseVideoBench addresses this gap by providing a robust dataset and tailored evaluation metrics, enabling rigorous assessment of state-of-the-art MLLMs on complex Chinese video content. Specifically, ChineseVideoBench comprises 8 main classes and 12 sub-classes, encompassing tasks that demand both deep video understanding and nuanced Chinese linguistic and cultural awareness. Our empirical evaluations reveal that ChineseVideoBench presents a significant challenge to current MLLMs. Among the models assessed, Gemini 2.5 Pro achieves the highest performance with an overall score of 77.9%, while InternVL-38B emerges as the most competitive open-source model.

cs.CV↗

arXiv2025

Bench2FreeAD: A Benchmark for Vision-based End-to-end Navigation in Unstructured Robotic Environments

Most current end-to-end (E2E) autonomous driving algorithms are built on standard vehicles in structured transportation scenarios, lacking exploration of robot navigation for unstructured scenarios such as auxiliary roads, campus roads, and indoor settings. This paper investigates E2E robot navigation in unstructured road environments. First, we introduce two data collection pipelines - one for real-world robot data and another for synthetic data generated using the Isaac Sim simulator, which together produce an unstructured robotics navigation dataset -- FreeWorld Dataset. Second, we fine-tuned an efficient E2E autonomous driving model -- VAD -- using our datasets to validate the performance and adaptability of E2E autonomous driving models in these environments. Results demonstrate that fine-tuning through our datasets significantly enhances the navigation potential of E2E autonomous driving models in unstructured robotic environments. Thus, this paper presents the first dataset targeting E2E robot navigation tasks in unstructured scenarios, and provides a benchmark based on vision-based E2E autonomous driving algorithms to facilitate the development of E2E navigation technology for logistics and service robots. The project is available on Github.

cs.RO↗

arXiv2025

Revealing the dynamic responses of Pb under shock loading based on DFT-accuracy machine learning potential

Lead (Pb) is a typical low-melting-point ductile metal and serves as an important model material in the study of dynamic responses. Under shock-wave loading, its dynamic mechanical behavior comprises two key phenomena: plastic deformation and shock induced phase transitions. The underlying mechanisms of these processes are still poorly understood. Revealing these mechanisms remains challenging for experimental approaches. Non-equilibrium molecular dynamics (NEMD) simulations are an alternative theoretical tool for studying dynamic responses, as they capture atomic-scale mechanisms such as defect evolution and deformation pathways. However, due to the limited accuracy of empirical interatomic potentials, the reliability of previous NEMD studies is questioned. Using our newly developed machine learning potential for Pb-Sn alloys, we revisited the microstructure evolution in response to shock loading under various shock orientations. The results reveal that shock loading along the [001] orientation of Pb exhibits a fast, reversible, and massive phase transition and stacking fault evolution. The behavior of Pb differs from previous studies by the absence of twinning during plastic deformation. Loading along the [011] orientation leads to slow, irreversible plastic deformation, and a localized FCC-BCC phase transition in the Pitsch orientation relationship. This study provides crucial theoretical insights into the dynamic mechanical response of Pb, offering a theoretical input for understanding the microstructure-performance relationship under extreme conditions.

cond-mat.mtrl-sci↗

arXiv2025

Dynamic Risk Assessment for Autonomous Vehicles from Spatio-Temporal Probabilistic Occupancy Heatmaps

Accurately assessing collision risk in dynamic traffic scenarios is a crucial requirement for trajectory planning in autonomous vehicles~(AVs) and enables a comprehensive safety evaluation of automated driving systems. To that end, this paper presents a novel probabilistic occupancy risk assessment~(PORA) metric. It uses spatiotemporal heatmaps as probabilistic occupancy predictions of surrounding traffic participants and estimates the risk of a collision along an AV's planned trajectory based on potential vehicle interactions. The use of probabilistic occupancy allows PORA to account for the uncertainty in future trajectories and velocities of traffic participants in the risk estimates. The risk from potential vehicle interactions is then further adjusted through a Cox model\edit{,} which considers the relative \edit{motion} between the AV and surrounding traffic participants. We demonstrate that the proposed approach enhances the accuracy of collision risk assessment in dynamic traffic scenarios, resulting in safer vehicle controllers, and provides a robust framework for real-time decision-making in autonomous driving systems. From evaluation in Monte Carlo simulations, PORA is shown to be more effective at accurately characterizing collision risk compared to other safety surrogate measures. Keywords: Dynamic Risk Assessment, Autonomous Vehicle, Probabilistic Occupancy, Driving Safety

cs.RO↗

arXiv2025

Multi-Agent VLMs Guided Self-Training with PNU Loss for Low-Resource Offensive Content Detection

Accurate detection of offensive content on social media demands high-quality labeled data; however, such data is often scarce due to the low prevalence of offensive instances and the high cost of manual annotation. To address this low-resource challenge, we propose a self-training framework that leverages abundant unlabeled data through collaborative pseudo-labeling. Starting with a lightweight classifier trained on limited labeled data, our method iteratively assigns pseudo-labels to unlabeled instances with the support of Multi-Agent Vision-Language Models (MA-VLMs). Un-labeled data on which the classifier and MA-VLMs agree are designated as the Agreed-Unknown set, while conflicting samples form the Disagreed-Unknown set. To enhance label reliability, MA-VLMs simulate dual perspectives, moderator and user, capturing both regulatory and subjective viewpoints. The classifier is optimized using a novel Positive-Negative-Unlabeled (PNU) loss, which jointly exploits labeled, Agreed-Unknown, and Disagreed-Unknown data while mitigating pseudo-label noise. Experiments on benchmark datasets demonstrate that our framework substantially outperforms baselines under limited supervision and approaches the performance of large-scale models

cs.LG↗

arXiv2025

ROI-based Deep Image Compression with Implicit Bit Allocation

Region of Interest (ROI)-based image compression has rapidly developed due to its ability to maintain high fidelity in important regions while reducing data redundancy. However, existing compression methods primarily apply masks to suppress background information before quantization. This explicit bit allocation strategy, which uses hard gating, significantly impacts the statistical distribution of the entropy model, thereby limiting the coding performance of the compression model. In response, this work proposes an efficient ROI-based deep image compression model with implicit bit allocation. To better utilize ROI masks for implicit bit allocation, this paper proposes a novel Mask-Guided Feature Enhancement (MGFE) module, comprising a Region-Adaptive Attention (RAA) block and a Frequency-Spatial Collaborative Attention (FSCA) block. This module allows for flexible bit allocation across different regions while enhancing global and local features through frequencyspatial domain collaboration. Additionally, we use dual decoders to separately reconstruct foreground and background images, enabling the coding network to optimally balance foreground enhancement and background quality preservation in a datadriven manner. To the best of our knowledge, this is the first work to utilize implicit bit allocation for high-quality regionadaptive coding. Experiments on the COCO2017 dataset show that our implicit-based image compression method significantly outperforms explicit bit allocation approaches in rate-distortion performance, achieving optimal results while maintaining satisfactory visual quality in the reconstructed background regions.

eess.IV↗

arXiv2025

R-Tuning: Wavelet-Decomposed Replay and Semantic Alignment for Continual Adaptation of Pretrained Time-Series Models

Pre-trained models have demonstrated exceptional generalization capabilities in time-series forecasting; however, adapting them to evolving data distributions remains a significant challenge. A key hurdle lies in accessing the original training data, as fine-tuning solely on new data often leads to catastrophic forgetting. To address this issue, we propose Replay Tuning (R-Tuning), a novel framework designed for the continual adaptation of pre-trained time-series models. R-Tuning constructs a unified latent space that captures both prior and current task knowledge through a frequency-aware replay strategy. Specifically, it augments model-generated samples via wavelet-based decomposition across multiple frequency bands, generating trend-preserving and fusion-enhanced variants to improve representation diversity and replay efficiency. To further reduce reliance on synthetic samples, R-Tuning introduces a latent consistency constraint that aligns new representations with the prior task space. This constraint guides joint optimization within a compact and semantically coherent latent space, ensuring robust knowledge retention and adaptation. Extensive experimental results demonstrate the superiority of R-Tuning, which reduces MAE and MSE by up to 46.9% and 46.8%, respectively, on new tasks, while preserving prior knowledge with gains of up to 5.7% and 6.0% on old tasks. Notably, under few-shot settings, R-Tuning outperforms all state-of-the-art baselines even when synthetic proxy samples account for only 5% of the new task dataset.

cs.LG↗

arXiv2025

LLM-based Relevance Assessment for Web-Scale Search Evaluation at Pinterest

Relevance evaluation plays a crucial role in personalized search systems to ensure that search results align with a user's queries and intent. While human annotation is the traditional method for relevance evaluation, its high cost and long turnaround time limit its scalability. In this work, we present our approach at Pinterest Search to automate relevance evaluation for online experiments using fine-tuned LLMs. We rigorously validate the alignment between LLM-generated judgments and human annotations, demonstrating that LLMs can provide reliable relevance measurement for experiments while greatly improving the evaluation efficiency. Leveraging LLM-based labeling further unlocks the opportunities to expand the query set, optimize sampling design, and efficiently assess a wider range of search experiences at scale. This approach leads to higher-quality relevance metrics and significantly reduces the Minimum Detectable Effect (MDE) in online experiment measurements.

cs.IR↗

arXiv2025

A comprehensive search for Long and Short Periodic Features from an Extremely Active Cycle of FRB 20240114A

Possible periodic features in fast radio bursts (FRBs) may provide insights into their astrophysical origins. Using extensive observations from the Five-hundred-meter Aperture Spherical radio Telescope (FAST), we conduct a multi-timescale periodicity search for the exceptionally active repeater FRB~20240114A. Our analysis is based on different datasets for different timescales: for short-timescale periodicity in Time of Arrivals (TOAs), we use 57 observations from January to August 2024; for long-timescale periodicity, we employ an extended TOA dataset comprising 111 observations spanning from January 2024 to October 2025; and for burst time series analysis, we utilize individual burst data from the 57 FAST observations. We identify three candidate short-timescale periodic signals (0.673~s, 0.635~s, and 0.536~s) with significances of $3.2σ$--$6σ$, each detected in two independent observations. On longer timescales, we detect a significant $143.40\pm7.19$-day periodicity with $5.2σ$ significance, establishing FRB~20240114A as a periodic repeater. In burst time series, we find quasi-periodic oscillations in the few hundred Hz range ($3.4σ$ and $3.7σ$) and periodic burst trains with periods of several to tens of milliseconds ($3σ$--$3.9σ$), though these periodic features appear transient and short-lived. The detection of periodic signals at these different time scales indicates that FRB 20240114A exhibits intriguing periodic self-similar characteristics. Despite the comprehensive dataset, no definitive periodicity linked to the source's rotation is confirmed, placing stringent constraints on the intrinsic source properties and the modulation mechanisms. All data are available via the Science Data Bank.

astro-ph.HE↗

arXiv2025

The U2H map explains the effect of (sub)mesoscale currents on significant wave height statistics

Currents modulate the energy of surface gravity waves, leading to spatial inhomogeneities in significant wave height (SWH). Previous work indicates that the overall scale of the inhomogeneities is set by the scale of the currents, that the inhomogeneities are strongly anisotropic even for isotropic currents, and that the rotational and divergent components of the currents have sharply distinct effects. We explain these and other features of current-induced SWH inhomogeneities using the U2H map, a linear relation between SWH and currents deduced from wave-action conservation by making simplifying assumptions. We obtain a linear law relating the spectrum of SWH to the spectra of rotational and divergent kinetic energy of the current. This makes it possible to relate SWH statistics (such as variance and anisotropy) to the current statistics and wave properties including directional spreading.

physics.flu-dyn↗

arXiv2025

Embodied Cognition Augmented End2End Autonomous Driving

In recent years, vision-based end-to-end autonomous driving has emerged as a new paradigm. However, popular end-to-end approaches typically rely on visual feature extraction networks trained under label supervision. This limited supervision framework restricts the generality and applicability of driving models. In this paper, we propose a novel paradigm termed $E^{3}AD$, which advocates for comparative learning between visual feature extraction networks and the general EEG large model, in order to learn latent human driving cognition for enhancing end-to-end planning. In this work, we collected a cognitive dataset for the mentioned contrastive learning process. Subsequently, we investigated the methods and potential mechanisms for enhancing end-to-end planning with human driving cognition, using popular driving models as baselines on publicly available autonomous driving datasets. Both open-loop and closed-loop tests are conducted for a comprehensive evaluation of planning performance. Experimental results demonstrate that the $E^{3}AD$ paradigm significantly enhances the end-to-end planning performance of baseline models. Ablation studies further validate the contribution of driving cognition and the effectiveness of comparative learning process. To the best of our knowledge, this is the first work to integrate human driving cognition for improving end-to-end autonomous driving planning. It represents an initial attempt to incorporate embodied cognitive data into end-to-end autonomous driving, providing valuable insights for future brain-inspired autonomous driving systems. Our code will be made available at Github

cs.RO↗

arXiv2025

Conformal Prediction in The Loop: A Feedback-Based Uncertainty Model for Trajectory Optimization

Conformal Prediction (CP) is a powerful statistical machine learning tool to construct uncertainty sets with coverage guarantees, which has fueled its extensive adoption in generating prediction regions for decision-making tasks, e.g., Trajectory Optimization (TO) in uncertain environments. However, existing methods predominantly employ a sequential scheme, where decisions rely unidirectionally on the prediction regions, and consequently the information from decision-making fails to be fed back to instruct CP. In this paper, we propose a novel Feedback-Based CP (Fb-CP) framework for shrinking-horizon TO with a joint risk constraint over the entire mission time. Specifically, a CP-based posterior risk calculation method is developed by fully leveraging the realized trajectories to adjust the posterior allowable risk, which is then allocated to future times to update prediction regions. In this way, the information in the realized trajectories is continuously fed back to the CP, enabling attractive feedback-based adjustments of the prediction regions and a provable online improvement in trajectory performance. Furthermore, we theoretically prove that such adjustments consistently maintain the coverage guarantees of the prediction regions, thereby ensuring provable safety. Additionally, we develop a decision-focused iterative risk allocation algorithm with theoretical convergence analysis for allocating the posterior allowable risk which closely aligns with Fb-CP. Furthermore, we extend the proposed method to handle distribution shift. The effectiveness and superiority of the proposed method are demonstrated through benchmark experiments.

math.OC↗

arXiv2025

MRSAudio: A Large-Scale Multimodal Recorded Spatial Audio Dataset with Refined Annotations

Humans rely on multisensory integration to perceive spatial environments, where auditory cues enable sound source localization in three-dimensional space. Despite the critical role of spatial audio in immersive technologies such as VR/AR, most existing multimodal datasets provide only monaural audio, which limits the development of spatial audio generation and understanding. To address these challenges, we introduce MRSAudio, a large-scale multimodal spatial audio dataset designed to advance research in spatial audio understanding and generation. MRSAudio spans four distinct components: MRSLife, MRSSpeech, MRSMusic, and MRSSing, covering diverse real-world scenarios. The dataset includes synchronized binaural and ambisonic audio, exocentric and egocentric video, motion trajectories, and fine-grained annotations such as transcripts, phoneme boundaries, lyrics, scores, and prompts. To demonstrate the utility and versatility of MRSAudio, we establish five foundational tasks: audio spatialization, and spatial text to speech, spatial singing voice synthesis, spatial music generation and sound event localization and detection. Results show that MRSAudio enables high-quality spatial modeling and supports a broad range of spatial audio research. Demos and dataset access are available at https://mrsaudio.github.io.

cs.SD↗