arXiv subjects

Lei Han

Publications and source records attributed to Lei Han.

At least 55 records · Page 3Linked to original sources

arXiv2025

AgentWorld: An Interactive Simulation Platform for Scene Construction and Mobile Robotic Manipulation

We introduce AgentWorld, an interactive simulation platform for developing household mobile manipulation capabilities. Our platform combines automated scene construction that encompasses layout generation, semantic asset placement, visual material configuration, and physics simulation, with a dual-mode teleoperation system supporting both wheeled bases and humanoid locomotion policies for data collection. The resulting AgentWorld Dataset captures diverse tasks ranging from primitive actions (pick-and-place, push-pull, etc.) to multistage activities (serve drinks, heat up food, etc.) across living rooms, bedrooms, and kitchens. Through extensive benchmarking of imitation learning methods including behavior cloning, action chunking transformers, diffusion policies, and vision-language-action models, we demonstrate the dataset's effectiveness for sim-to-real transfer. The integrated system provides a comprehensive solution for scalable robotic skill acquisition in complex home environments, bridging the gap between simulation-based training and real-world deployment. The code, datasets will be available at https://yizhengzhang1.github.io/agent_world/

cs.RO↗

arXiv2025

Pinning "Reflection" on the Agenda: Investigating Reflection in Human-LLM Co-Creation for Creative Coding

Large language models (LLMs) are increasingly integrated into creative coding, yet how users reflect, and how different co-creation conditions influence reflective behavior, remains underexplored. This study investigates situated, moment-to-moment reflection in creative coding under two prompting strategies: the entire task invocation (T1) and decomposed subtask invocation (T2), to examine their effects on reflective behavior. Our mixed-method results reveal three distinct reflection types and show that T2 encourages more frequent, strategic, and generative reflection, fostering diagnostic reasoning and goal redefinition. These findings offer insights into how LLM-based tools foster deeper creative engagement through structured, behaviorally grounded reflection support.

cs.HC↗

arXiv2025

VLM-TDP: VLM-guided Trajectory-conditioned Diffusion Policy for Robust Long-Horizon Manipulation

Diffusion policy has demonstrated promising performance in the field of robotic manipulation. However, its effectiveness has been primarily limited in short-horizon tasks, and its performance significantly degrades in the presence of image noise. To address these limitations, we propose a VLM-guided trajectory-conditioned diffusion policy (VLM-TDP) for robust and long-horizon manipulation. Specifically, the proposed method leverages state-of-the-art vision-language models (VLMs) to decompose long-horizon tasks into concise, manageable sub-tasks, while also innovatively generating voxel-based trajectories for each sub-task. The generated trajectories serve as a crucial conditioning factor, effectively steering the diffusion policy and substantially enhancing its performance. The proposed Trajectory-conditioned Diffusion Policy (TDP) is trained on trajectories derived from demonstration data and validated using the trajectories generated by the VLM. Simulation experimental results indicate that our method significantly outperforms classical diffusion policies, achieving an average 44% increase in success rate, over 100% improvement in long-horizon tasks, and a 20% reduction in performance degradation in challenging conditions, such as noisy images or altered environments. These findings are further reinforced by our real-world experiments, where the performance gap becomes even more pronounced in long-horizon tasks. Videos are available on https://youtu.be/g0T6h32OSC8

cs.RO↗

arXiv2025

Drivers of Layered Circulations in the South China Sea: Volume Flux or Vorticity Flux?

The South China Sea (SCS) features a unique layered circulation structure known as the cyclonic-anticyclonic-cyclonic (CAC) pattern, whose driving mechanisms remain a subject of debate. This study employs idealized numerical simulations using the MITgcm to investigate the role of volume flux and vorticity flux through the Luzon Strait (LS) to the SCS circulation. The control experiment successfully reproduces the observed "sandwiched" transport structure at the LS and the CAC circulation within the SCS. Sensitivity experiments, in which planetary vorticity is set to zero in the Pacific and LS, reveal that the CAC structure is insensitive to vorticity flux input. By applying the Stommel-Arons model to Cartesian coordinates, we provide analytical solutions that align with the simulation results, supporting the volume flux-driven hypothesis. Our findings suggest that the deep inflow through the LS is the primary driver of the layered circulation system, while the middle-layer outflow is a dynamical consequence. These results challenge the vorticity flux-driven hypothesis and offer new insights into the dynamics of layered circulations in the SCS.

physics.geo-ph↗

arXiv2025

Task Adaptation from Skills: Information Geometry, Disentanglement, and New Objectives for Unsupervised Reinforcement Learning

Unsupervised reinforcement learning (URL) aims to learn general skills for unseen downstream tasks. Mutual Information Skill Learning (MISL) addresses URL by maximizing the mutual information between states and skills but lacks sufficient theoretical analysis, e.g., how well its learned skills can initialize a downstream task's policy. Our new theoretical analysis in this paper shows that the diversity and separability of learned skills are fundamentally critical to downstream task adaptation but MISL does not necessarily guarantee these properties. To complement MISL, we propose a novel disentanglement metric LSEPIN. Moreover, we build an information-geometric connection between LSEPIN and downstream task adaptation cost. For better geometric properties, we investigate a new strategy that replaces the KL divergence in information geometry with Wasserstein distance. We extend the geometric analysis to it, which leads to a novel skill-learning objective WSEP. It is theoretically justified to be helpful to downstream task adaptation and it is capable of discovering more initial policies for downstream tasks than MISL. We finally propose another Wasserstein distance-based algorithm PWSEP that can theoretically discover all optimal initial policies.

cs.LG↗

arXiv2025

TransGI: Real-Time Dynamic Global Illumination With Object-Centric Neural Transfer Model

Neural rendering algorithms have revolutionized computer graphics, yet their impact on real-time rendering under arbitrary lighting conditions remains limited due to strict latency constraints in practical applications. The key challenge lies in formulating a compact yet expressive material representation. To address this, we propose TransGI, a novel neural rendering method for real-time, high-fidelity global illumination. It comprises an object-centric neural transfer model for material representation and a radiance-sharing lighting system for efficient illumination. Traditional BSDF representations and spatial neural material representations lack expressiveness, requiring thousands of ray evaluations to converge to noise-free colors. Conversely, real-time methods trade quality for efficiency by supporting only diffuse materials. In contrast, our object-centric neural transfer model achieves compactness and expressiveness through an MLP-based decoder and vertex-attached latent features, supporting glossy effects with low memory overhead. For dynamic, varying lighting conditions, we introduce local light probes capturing scene radiance, coupled with an across-probe radiance-sharing strategy for efficient probe generation. We implemented our method in a real-time rendering engine, combining compute shaders and CUDA-based neural networks. Experimental results demonstrate that our method achieves real-time performance of less than 10 ms to render a frame and significantly improved rendering quality compared to baseline methods.

cs.GR↗

arXiv2025

Multi-Agent Collaboration via Cross-Team Orchestration

Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. A representative scenario is in software development, where agents can collaborate in a team like humans, following predefined phases to complete sub-tasks sequentially. However, for an agent team, each phase yields only one possible outcome. This results in the completion of only one development chain, thereby losing the opportunity to explore multiple potential decision paths within the solution space. Consequently leading to suboptimal results or extensive trial and error. To address this, we introduce Cross-Team Orchestration (Croto), a scalable multi-team framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation. Experiments reveal a notable increase in software quality compared to state-of-the-art baselines. We further tested our framework on story generation tasks, which demonstrated a promising generalization ability of our framework in other domains. The code and data is available at https://github.com/OpenBMB/ChatDev/tree/macnet

cs.CL↗

arXiv2025

3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model

Manipulation has long been a challenging task for robots, while humans can effortlessly perform complex interactions with objects, such as hanging a cup on the mug rack. A key reason is the lack of a large and uniform dataset for teaching robots manipulation skills. Current robot datasets often record robot action in different action spaces within a simple scene. This hinders the robot to learn a unified and robust action representation for different robots within diverse scenes. Observing how humans understand a manipulation task, we find that understanding how the objects should move in the 3D space is a critical clue for guiding actions. This clue is embodiment-agnostic and suitable for both humans and different robots. Motivated by this, we aim to learn a 3D flow world model from both human and robot manipulation data. This model predicts the future movement of the interacting objects in 3D space, guiding action planning for manipulation. Specifically, we synthesize a large-scale 3D optical flow dataset, named ManiFlow-110k, through a moving object auto-detect pipeline. A video diffusion-based world model then learns manipulation physics from these data, generating 3D optical flow trajectories conditioned on language instructions. With the generated 3D object optical flow, we propose a flow-guided rendering mechanism, which renders the predicted final state and leverages GPT-4o to assess whether the predicted flow aligns with the task description. This equips the robot with a closed-loop planning ability. Finally, we consider the predicted 3D optical flow as constraints for an optimization policy to determine a chunk of robot actions for manipulation. Extensive experiments demonstrate strong generalization across diverse robotic manipulation tasks and reliable cross-embodiment adaptation without hardware-specific training.

cs.RO↗

arXiv2025

Autonomous Collaborative Scheduling of Time-dependent UAVs, Workers and Vehicles for Crowdsensing in Disaster Response

Natural disasters have caused significant losses to human society, and the timely and efficient acquisition of post-disaster environmental information is crucial for the effective implementation of rescue operations. Due to the complexity of post-disaster environments, existing sensing technologies face challenges such as weak environmental adaptability, insufficient specialized sensing capabilities, and limited practicality of sensing solutions. This paper explores the heterogeneous multi-agent online autonomous collaborative scheduling algorithm HoAs-PALN, aimed at achieving efficient collection of post-disaster environmental information. HoAs-PALN is realized through adaptive dimensionality reduction in the matching process and local Nash equilibrium game, facilitating autonomous collaboration among time-dependent UAVs, workers and vehicles to enhance sensing scheduling. (1) In terms of adaptive dimensionality reduction during the matching process, HoAs-PALN significantly reduces scheduling decision time by transforming a five-dimensional matching process into two categories of three-dimensional matching processes; (2) Regarding the local Nash equilibrium game, HoAs-PALN combines the softmax function to optimize behavior selection probabilities and introduces a local Nash equilibrium determination mechanism to ensure scheduling decision performance. Finally, we conducted detailed experiments based on extensive real-world and simulated data. Compared with the baselines (GREEDY, K-WTA, MADL and MARL), HoAs-PALN improves task completion rates by 64.12%, 46.48%, 16.55%, and 14.03% on average, respectively, while each online scheduling decision takes less than 10 seconds, demonstrating its effectiveness in dynamic post-disaster environments.

cs.MA↗

arXiv2025

GLTW: Joint Improved Graph Transformer and LLM via Three-Word Language for Knowledge Graph Completion

Knowledge Graph Completion (KGC), which aims to infer missing or incomplete facts, is a crucial task for KGs. However, integrating the vital structural information of KGs into Large Language Models (LLMs) and outputting predictions deterministically remains challenging. To address this, we propose a new method called GLTW, which encodes the structural information of KGs and merges it with LLMs to enhance KGC performance. Specifically, we introduce an improved Graph Transformer (iGT) that effectively encodes subgraphs with both local and global structural information and inherits the characteristics of language model, bypassing training from scratch. Also, we develop a subgraph-based multi-classification training objective, using all entities within KG as classification objects, to boost learning efficiency.Importantly, we combine iGT with an LLM that takes KG language prompts as input.Our extensive experiments on various KG datasets show that GLTW achieves significant performance gains compared to SOTA baselines.

cs.CL↗

arXiv2025

Cross-Task Experiential Learning on LLM-based Multi-Agent Collaboration

Large Language Model-based multi-agent systems (MAS) have shown remarkable progress in solving complex tasks through collaborative reasoning and inter-agent critique. However, existing approaches typically treat each task in isolation, resulting in redundant computations and limited generalization across structurally similar tasks. To address this, we introduce multi-agent cross-task experiential learning (MAEL), a novel framework that endows LLM-driven agents with explicit cross-task learning and experience accumulation. We model the task-solving workflow on a graph-structured multi-agent collaboration network, where agents propagate information and coordinate via explicit connectivity. During the experiential learning phase, we quantify the quality for each step in the task-solving workflow and store the resulting rewards along with the corresponding inputs and outputs into each agent's individual experience pool. During inference, agents retrieve high-reward, task-relevant experiences as few-shot examples to enhance the effectiveness of each reasoning step, thereby enabling more accurate and efficient multi-agent collaboration. Experimental results on diverse datasets demonstrate that MAEL empowers agents to learn from prior task experiences effectively-achieving faster convergence and producing higher-quality solutions on current tasks.

cs.CL↗

arXiv2025

Co-Saving: Resource Aware Multi-Agent Collaboration for Software Development

Recent advancements in Large Language Models (LLMs) and autonomous agents have demonstrated remarkable capabilities across various domains. However, standalone agents frequently encounter limitations when handling complex tasks that demand extensive interactions and substantial computational resources. Although Multi-Agent Systems (MAS) alleviate some of these limitations through collaborative mechanisms like task decomposition, iterative communication, and role specialization, they typically remain resource-unaware, incurring significant inefficiencies due to high token consumption and excessive execution time. To address these limitations, we propose a resource-aware multi-agent system -- Co-Saving (meaning that multiple agents collaboratively engage in resource-saving activities), which leverages experiential knowledge to enhance operational efficiency and solution quality. Our key innovation is the introduction of "shortcuts" -- instructional transitions learned from historically successful trajectories -- which allows to bypass redundant reasoning agents and expedite the collective problem-solving process. Experiments for software development tasks demonstrate significant advantages over existing methods. Specifically, compared to the state-of-the-art MAS ChatDev, our method achieves an average reduction of 50.85% in token usage, and improves the overall code quality by 10.06%.

cs.CL↗

arXiv2025

Learning 3D Persistent Embodied World Models

The ability to simulate the effects of future actions on the world is a crucial ability of intelligent embodied agents, enabling agents to anticipate the effects of their actions and make plans accordingly. While a large body of existing work has explored how to construct such world models using video models, they are often myopic in nature, without any memory of a scene not captured by currently observed images, preventing agents from making consistent long-horizon plans in complex environments where many parts of the scene are partially observed. We introduce a new persistent embodied world model with an explicit memory of previously generated content, enabling much more consistent long-horizon simulation. During generation time, our video diffusion model predicts RGB-D video of the future observations of the agent. This generation is then aggregated into a persistent 3D map of the environment. By conditioning the video model on this 3D spatial map, we illustrate how this enables video world models to faithfully simulate both seen and unseen parts of the world. Finally, we illustrate the efficacy of such a world model in downstream embodied applications, enabling effective planning and policy learning.

cs.CV↗

arXiv2025

Discovery of a large magnetic nonlinear Hall effect in an altermagnet

Since Edwin Halls groundbreaking discovery of the Hall effect in 1879, magnetism, spin, and quantization have been expanding the scope of Hall effects, continuously driving transformative progress in science and technology. Among them, the latest nonlinear Hall effect (NLHE), where longitudinal electric field tunes quantum geometry to generate nonlinear Hall voltage, attracts wide attention as a sensitive probe of topological phases across a wide range of materials. Here, we report a new Hall effect member: the magnetic nonlinear Hall effect (MNLHE), characterized by a quadratic Hall conductivity dependence on magnetic field, rather than electric field as in NLHE. This finding relies on an altermagnet, Mn5Si3 thin film, whose alternating-sign Berry curvatures ensure higher-order MNLHE clearly distinguishable from the first-order anomalous Hall effect. The observed quadratic dependence originates from chiral next-nearest-neighbor hopping processes that acquire magnetic-exchange-driven Zeeman energies and Haldane-like chiral flux phases. Remarkably, this MNLHE is non-analytic, as reversing the magnetic field flips the alternating spin-splitting bands and reverses the hopping chirality, which is absent in traditional NLHE. Beyond offering a distinctive transport fingerprint for altermagnet Mn5Si3 thin film, this MNLHE is large and unsaturated up to 60 T, providing opportunities for pulsed high-field sensing technologies in both fundamental researches and engineering applications.

cond-mat.mtrl-sci↗

arXiv2025

Tackling Data Corruption in Offline Reinforcement Learning via Sequence Modeling

Learning policy from offline datasets through offline reinforcement learning (RL) holds promise for scaling data-driven decision-making while avoiding unsafe and costly online interactions. However, real-world data collected from sensors or humans often contains noise and errors, posing a significant challenge for existing offline RL methods, particularly when the real-world data is limited. Our study reveals that prior research focusing on adapting predominant offline RL methods based on temporal difference learning still falls short under data corruption when the dataset is limited. In contrast, we discover that vanilla sequence modeling methods, such as Decision Transformer, exhibit robustness against data corruption, even without specialized modifications. To unlock the full potential of sequence modeling, we propose Robust Decision Rransformer (RDT) by incorporating three simple yet effective robust techniques: embedding dropout to improve the model's robustness against erroneous inputs, Gaussian weighted learning to mitigate the effects of corrupted labels, and iterative data correction to eliminate corrupted data from the source. Extensive experiments on MuJoCo, Kitchen, and Adroit tasks demonstrate RDT's superior performance under various data corruption scenarios compared to prior methods. Furthermore, RDT exhibits remarkable robustness in a more challenging setting that combines training-time data corruption with test-time observation perturbations. These results highlight the potential of sequence modeling for learning from noisy or corrupted offline datasets, thereby promoting the reliable application of offline RL in real-world scenarios. Our code is available at https://github.com/jiawei415/RobustDecisionTransformer.

cs.LG↗

arXiv2025

Diffusive and Adiabatic Meridional Overturning Circulations in the Cooling Abyss of the Indo-Pacific Ocean

Recent field campaigns have consistently documented bottom-intensified mixing near the seafloor, suggesting diabatic downwelling in the abyssal ocean. This phenomenon appears to contradict with the mass balance of the abyssal ocean, where dense bottom water plunges into the region from the Antarctic side. Previous studies have sought to resolve this apparent paradox by proposing mixing-induced diabatic upwelling along bottom slopes. In contrast, this study offers an alternative perspective, highlighting the role of isopycnal displacement in the transient abyss. Motivated by emerging evidence of a cooling phase in the abyssal Indo-Pacific, likely linked to the last Little Ice Age, this study reinterprets the interior-downwelling paradox from the perspective of unsteady thermal states. Idealized numerical experiments were conducted to explore the abyssal overturning dynamics, with a focus on the behavior of advective, adiabatic, and diffusive overturning circulation streamfunctions in both cooling and warming scenarios. The results reveal that while the direction of diabatic overturning (upwelling or downwelling) depends on the transient state of the ocean, advective overturning circulation consistently exhibits an upwelling pattern, underscoring the inherent robustness of upward water parcel movement within abyssal dynamics.

physics.ao-ph↗

arXiv2025

Overview of EXL-50 Research Progress and Future Plan

XuanLong-50 (EXL-50) is the first medium-size spherical torus (ST) in China, with the toroidal field at major radius at 50 cm around 0.5T. CS-free and non-inductive current drive via electron cyclotron resonance heating (ECRH) was the main physics research issue for EXL-50. Discharges with plasma currents of 50 kA - 180 kA were routinely obtained in EXL-50, with the current flattop sustained for up to or beyond 2 s. The current drive effectiveness on EXL-50 was as high as 1 A/W for low-density discharges using 28GHz ECRH alone for heating power less than 200 kW. The plasma current reached Ip>80 kA for high-density (5*10e18m-2) discharges with 150 kW 28GHz ECRH. Higher performance discharge (Ip of about 120 kA and core density of about 1*10e19m-3) was achieved with 150 kW 50GHz ECRH. The plasma current in EXL-50 was mainly carried by the energetic electrons.Multi-fluid equilibrium model has been successfully applied to reconstruct the magnetic flux surface and the measured plasma parameters of the EXL-50 equilibrium. The physics mechanisms for the solenoid-free ECRH current drive and the energetic electrons has also been investigated. Preliminary experimental results show that 100 kW of lower hybrid current drive (LHCD) waves can drive 20 kA of plasma current. Several boron injection systems were installed and tested in EXL-50, including B2H6 gas puffing, boron powder injection, boron pellet injection. The research plan of EXL-50U, which is the upgrade machine of EXL-50, is also presented.

physics.plasm-ph↗

arXiv2025

Self-playing Adversarial Language Game Enhances LLM Reasoning

We explore the potential of self-play training for large language models (LLMs) in a two-player adversarial language game called Adversarial Taboo. In this game, an attacker and a defender communicate around a target word only visible to the attacker. The attacker aims to induce the defender to speak the target word unconsciously, while the defender tries to infer the target word from the attacker's utterances. To win the game, both players must have sufficient knowledge about the target word and high-level reasoning ability to infer and express in this information-reserved conversation. Hence, we are curious about whether LLMs' reasoning ability can be further enhanced by Self-Playing this Adversarial language Game (SPAG). With this goal, we select several open-source LLMs and let each act as the attacker and play with a copy of itself as the defender on an extensive range of target words. Through reinforcement learning on the game outcomes, we observe that the LLMs' performances uniformly improve on a broad range of reasoning benchmarks. Furthermore, iteratively adopting this self-play process can continuously promote LLMs' reasoning abilities. The code is available at https://github.com/Linear95/SPAG.

cs.CL↗