arXiv subjects

Hesheng Wang

Publications and source records attributed to Hesheng Wang.

At least 19 recordsLinked to original sources

arXiv2026

Teach and Grow: An Agent-Centered Architecture for General Robot Learning

Vision-language-action (VLA) and world-action models typically absorb unfamiliar manipulation tasks through additional robot data collection and policy optimization. This recurring retraining burden slows the acquisition of new behavior. We present Teach-and-Grow Learning (TGL), a training-free architecture that turns a few successful demonstrations into reusable robot skills. Task acquisition requires no gradient updates, fine-tuning, or reinforcement learning: pretrained model weights remain fixed as the robot expands its explicit knowledge. Teaching is an accelerator, not a precondition, because the agent can also drive the robot directly, and demonstrations mainly improve reliability. Our implementation uses OpenAI GPT-6 Astra for multimodal reasoning and Codex to connect the agent to robot tools. The agent identifies subgoals shared across demonstrations, expresses them as closed-loop Skill Blocks, and grounds each block in the current scene. Physical feedback guides the next action and any recovery. Verified behaviors enter a persistent Skill Library; Experience Memory records the conditions and repairs that inform later decisions. TGL reaches 99.9% mean success on four LIBERO suites and 92.4% on seven LIBERO-Plus perturbation categories. Controlled studies show that taught blocks persist and improve related-task execution under the same model weights and executors. We further formulate a scaling hypothesis that relates effective reusable experience to falling future-task error and teaching demand. Code and demonstration videos: https://tgl.changnie.top

cs.RO↗

arXiv2026

GraphPoint: Semantic Entity Graphs and Point Trajectories for Compositional Robot Manipulation

Robot manipulation policies often struggle to generalize beyond their demonstrations, even when new instructions involve familiar objects and behaviors. When language and scenes are strongly correlated during training, a policy can learn a fixed visual-action mapping rather than respond to the requested behavior. We investigate compositional reuse at two levels: within a subtask, combining familiar entities, action types, and action modifiers; and across subtasks, reusing learned subtasks in unseen long-horizon tasks. We introduce CoMani, a benchmark with controlled splits for evaluating both capabilities. Matched initial scenes and controlled changes to a single semantic factor encourage reliance on language rather than visual shortcuts. We further propose GraphPoint, which connects semantic entity graphs to geometric control by predicting future gripper point trajectories and converting them into actions using robot geometry. The framework organizes the gripper and objects by semantic roles and conditions their interactions on action types and modifiers, while predicted progress guides transitions during execution. Experiments and ablations on CoMani validate the effectiveness of our method for instruction-dependent generalization at both levels. Code will be released at GraphPoint.

cs.RO↗

arXiv2026

Adaptive World Memory 3D Foundation Model for Scalable 3D Mapping, Localization, and Rendering

Recent 3D foundation models enable generalizable geometric reasoning from RGB images but remain limited in persistent memory, scalability, and renderable scene modeling. We present a memory-centric 3D foundation model for scalable robotic localization, reconstruction, and Gaussian rendering. Its core is an adaptive world memory mechanism that combines transformer-based gated updates with test-time temporal-spatial regulation. Learned gates control recurrent memory propagation, while temporal state evolution and spatial observation-state consistency regulate token-wise updates and forgetting over long image sequences. To support large-scale mapping, we organize memory into local submaps and integrate progressive mapping and tracking, loop closure, and SL(4)-based global refinement to maintain local accuracy and global consistency. A Gaussian reconstruction head decodes memory-enhanced features into renderable primitives, unifying camera pose estimation, dense point-cloud reconstruction, and photorealistic rendering within a single model. Experiments on public benchmarks and self-collected datasets from diverse robotic platforms demonstrate improved trajectory accuracy, reconstruction completeness, and rendering quality over existing 3D foundation reconstruction and SLAM baselines. These results support adaptive memory as a foundation for persistent robotic world modeling. The dataset and code will be made publicly available at \href{https://github.com/dtc111111/AWM-3DFM}{https://github.com/dtc111111/AWM-3DFM}.

cs.CV↗

arXiv2026

Towards the Vision-Sound-Language-Action Paradigm: The HEAR Framework for Sound-Centric Manipulation

While recent Vision-Language-Action (VLA) models have begun to incorporate audio, they typically treat sound as static pre-execution prompts or focus exclusively on human speech. This leaves a significant gap in real-time, sound-centric manipulation where fleeting environmental acoustics provide critical state verification during task execution. Consequently, key sounds are easily missed due to low-frequency updates or system latency. This problem is exacerbated by action chunking with open-loop execution, which creates a Blind Execution Interval where acoustic events are lost between discrete audio observation windows. Recognizing the necessity of continuous auditory awareness, we formalize Vision-Sound-Language-Action (VSLA) as a continuous control paradigm conditioned on vision, streaming audio, language, and proprioception under delayed decision loops. As an instantiation, we introduce HEAR, a VSLA framework integrating four components: (i) a streaming Historizer to maintain a compact, causal audio context across execution gaps; (ii) an Envisioner adapted from omni foundation models to reason over multi-sensory inputs; (iii) an Advancer, formulated as an audio world model, to learn temporal dynamics by predicting near-future audio codes; and (iv) a flow-matching Realizer policy to generate smooth action chunks. To address the scarcity of pretraining data and evaluations for VSLA, we construct OpenX-Sound for pretraining, alongside HEAR-Bench, the first sound-centric manipulation benchmark with strict causal timing rules. Our results suggest that robust sound-centric manipulation necessitates causal persistence and explicit temporal learning. This framework provides a practical step toward multi-sensory foundation models for embodied agents, enabling robots to perceive and interact with dynamic environments. Code and videos are available at https://hear.irmv.top

cs.RO↗

arXiv2026

VT-MUSE: Multimodal Unified Sequential Visuotactile Representation Learning for Manipulation

We propose VT-MUSE, a Multimodal Unified SEquential representation learning framework for visuotactilemanipulation. Existing approaches often encode visual and tactile observations independently before fusion, limiting their ability to capture fine-grained cross-modal dependencies. Moreover, most methods focus on observations at the current time step and overlook the temporal evolution of contact. VT-MUSE addresses both limitations through a two-stage representation learning framework. In Stage I, modality specific encoders are jointly adapted via cross-modal temporal alignment and masked-view consistency. In Stage II, a conditional variational latent model processes masked visual sequences together with full tactile histories. Auxiliary decoders reconstruct the masked recent visual observations and predict tactile depth changes, encouraging the latent representation to retain both global visual context and local contact dynamics. The learned representation is subsequently integrated into a lightweight Transformer policy through gated cross-attention. On the simulation benchmark, VT-MUSE outperforms the strongest baseline evaluated on all tasks by 11 percentage points and also achieves substantial improvements in real-world experiments.

cs.RO↗

arXiv2026

WM-VS: Progress-Aligned World Models for Closed-Loop Visual Servoing

Closed-loop visual servoing requires predictions that indicate whether an action reduces task error, not only whether the action is plausible. We call this gap the prediction-control mismatch and introduce WM-VS, a target-centric progress-aligned world-model framework for closed-loop visual servoing. Offline target-region DINOv2 correspondences define a signed four-dimensional servo coordinate for translation, scale, and in-plane rotation. Stage 1 aligns action-conditioned latent transitions with this coordinate; Stage 2 freezes the world model and trains a reactive joint-velocity policy with action imitation, consequence supervision, and short imagined rollouts that favor error contraction. Deployment is RGB-only and reactive, without online trajectory optimization. On a real 7-DoF eye-to-hand system, WM-VS reaches a corner RMSE no larger than 10 percent of its initial value in 30/30 trials and retains this criterion at the final valid frame in 25/30 (83.33 percent). Removing future-error alignment reduces retention to 26.67 percent. The learned progress signal agrees with an external AprilTag corner error not used for training or control (mean Spearman rho = 0.8778). Without retraining, two unseen 3D targets achieve translation-error reductions of 86.48 percent and 90.27 percent and rotation-error reductions of 70.01 percent and 65.70 percent. These results link progress-aligned action consequences to repeated closed-loop correction and transfer. Code and data will be released as open source.

cs.RO↗

arXiv2026

HAP: A Hand-Driven Active Perception Framework for Egocentric Head Motion Prediction

Egocentric motion forecasting has primarily focused on hands and manipulated objects, leaving future human head motion comparatively underexplored. During manipulation, the head both redirects perception toward the target to acquire task-relevant evidence and coordinates with body and hand motion. We therefore formulate future six Degree of Freedom (6-DoF) head-motion prediction conditioned on observed hand motion and inferred target context, and propose HAP, a Hand-Driven Active Perception framework. HAP infers confidence for each target object from observed hand motion and object geometry. Then constructs a dynamic Predictive Target-Centric Amodal Occlusion Graph (P-TAOG) representing current and potential occlusion among candidate objects. Directed graph and causal temporal reasoning encode the evolving target conditioned perceptual state, which is fused with hand and head motion history. A horizon-wise gate then blends the learned trajectory with a constant velocity prior. We further introduce Bottle, an egocentric RGB-D dataset of object manipulation toward specified targets, with coordinated head and hand motion under changing target visibility. Experiments on the public dataset and Bottle show that HAP achieves lower head motion prediction errors than representative baselines, supporting the value of hand driven intention and dynamic occlusion reasoning for anticipating human head motion. Code will be released at https://HAP-ego.github.io/HAP.

cs.CV↗

arXiv2026

Robust Multi-Model Fitting through Learning Neighbor Regions

Multi-model fitting involves fitting multiple models accurately in a noisy environment. It is the basis for computer vision tasks such as scene reconstruction and mixed reality. However, its performance is often limited by insufficient feature utilization, inefficient optimization, model overlap, and the non-differentiable pipelines. To overcome these limitations, we introduce a robust coarse-to-fine framework called Learning Neighbor Regions (LNR). Recognizing that substantial computational resources are wasted on numerous bad minimum sets, we propose the coarse-level module. This module utilizes a neural network to extract and analyze geometric feature of both local point-wise relationships and global contextual information in minimum sets, outputting confidence to pre-select a small number of good minimum sets, thereby enhancing overall efficiency before solving hypotheses. To address model overlap, LNR encodes neighbor region features for each hypothesis in its fine-level module. These region features consist of geometric features of neighboring data points, which can be used by multiple regions simultaneously. This design allows the neural network to individually refine and score each hypothesis. Importantly, LNR is trained to learn directly from data point features rather than from the hypothesis parameters, thus avoiding differentiating the sampling process and the model solvers. Extensive experiments on four classic multi-model fitting tasks demonstrate that LNR achieves state-of-the-art performance. The analysis suggests that LNR can be easily adapted to various robust multi-model fitting tasks.

cs.CV↗

arXiv2026

Ergodic Trajectory Planning with Dynamic Sensor Footprints

This paper addresses the problem of trajectory planning for information gathering with a dynamic and resolution-varying sensor footprint. Ergodic planning offers a principled framework that balances exploration (visiting all areas) and exploitation (focusing on high-information regions) by planning trajectories such that the time spent in a region is proportional to the amount of information in that region. Existing ergodic planning often oversimplifies the sensing model by assuming a point sensor or a footprint with constant shape and resolution. In practice, the sensor footprint can drastically change over time as the robot moves, such as aerial robots equipped with downward-facing cameras, whose field of view depends on the orientation and altitude. To overcome this limitation, we propose a new metric that accounts for dynamic sensor footprints, analyze the theoretic local optimality conditions, and propose numerical trajectory optimization algorithms. Experimental results show that the proposed approach can simultaneously optimize both the trajectories and sensor footprints, with up to an order of magnitude better ergodicity than conventional methods. We also deploy our approach in a multi-drone system to ergodically cover an object in 3D space.

cs.RO↗

arXiv2026

CoMo3R-SLAM: Collaborative Monocular Dense SLAM with Learned 3D Reconstruction Priors for Outdoor Multi-Agent Systems

Outdoor robot teams need a shared dense map despite limited overlap, independent reference frames, and uncertain monocular scale. Collaborative dense SLAM systems typically resolve this with depth sensors, which add payload, power, and calibration cost. We present CoMo3R-SLAM, a collaborative monocular dense SLAM system that places learned feed-forward 3D reconstruction priors at the center of the multi-agent problem: their dense pointmaps anchor scale across agents and supply correspondences strong enough to verify inter-agent links geometrically. Each agent tracks and fuses its own keyframes from a single RGB stream, while a coordinator retrieves cross-agent keyframes over the prior's encoder features, verifies them by bidirectional dense pointmap matching, synchronizes the independent similarity gauges in closed form, and refines every keyframe in one unified multi-agent sim(3) graph. Finally, a pose-depth alternation over geometry-aware segments lets inter-agent observations constrain dense structure as well as trajectories. Requiring neither measured depth nor supplied intrinsics, CoMo3R-SLAM attains the lowest trajectory error on three of four Tanks and Temples scenes, and competitive accuracy on Waymo driving sequences, while running at approximately 6-8 FPS on RTX 3080 Ti. A long-horizon traversal, independently captured day and night streams, and teams of up to four agents further map its operating range.

cs.RO↗

arXiv2026

DIAL-GS: Dynamic Instance Aware Reconstruction for Label-free Street Scenes with 4D Gaussian Splatting

Urban scene reconstruction is critical for autonomous driving, enabling structured 3D representations for data synthesis and closed-loop testing. Supervised approaches rely on costly human annotations and lack scalability, while current self-supervised methods often confuse static and dynamic elements and fail to distinguish individual dynamic objects, limiting fine-grained editing. We propose DIAL-GS, a novel dynamic instance-aware reconstruction method for label-free street scenes with 4D Gaussian Splatting. We first accurately identify dynamic instances by exploiting appearance-position inconsistency between warped rendering and actual observation. Guided by instance-level dynamic perception, we employ instance-aware 4D Gaussians as the unified volumetric representation, realizing dynamic-adaptive and instance-aware reconstruction. Furthermore, we introduce a reciprocal mechanism through which identity and dynamics reinforce each other, enhancing both integrity and consistency. Experiments on urban driving scenarios show that DIAL-GS surpasses existing self-supervised baselines in reconstruction quality and instance-level editing, offering a concise yet powerful solution for urban scene modeling.

cs.CV↗

arXiv2026

DiffSAC: Diffusion-guided Sampling for Consensus-based Robust Estimation

Robust estimation is a core computer vision task frequently tackled using sample consensus. However, traditional methods suffer from inefficient sampling as they struggle to identify effective minimum sets before hypothesis evaluation. To address these challenges, we propose a novel Diffusion-guided Sampling for Consensus-based Robust Estimation (DiffSAC) framework. DiffSAC introduces a diffusion model to learn the distribution of effective minimum sets. It refines the confidence for each data point, indicating whether it belongs to a good minimum set, rather than ranking the data points as in previous work. This significantly reduces the need to process numerous bad sets. To constrain the refinement direction, geometric features are incorporated as conditions within our diffusion model. Consequently, DiffSAC outputs a small number of high-quality minimum sets, enabling identification of the best hypothesis via consensus evaluation. Notably, compared to previous works requiring evaluating over ten thousand hypotheses, DiffSAC achieves state-of-the-art performance with only dozens, significantly boosting efficiency. Extensive experiments across five classic computer vision tasks demonstrate the superiority of DiffSAC. The diffusion model's sampling accelerators enable real-time operation, and DiffSAC can be used as a plug-and-play module to improve existing sample consensus methods.

cs.CV↗

arXiv2026

RoGS: Adaptive Meshgrid Gaussian for Large-Scale Road Surface Mapping

Road surface mapping plays a crucial role in autonomous driving, supporting high-definition map generation, lane-level perception, and automatic road annotation. Recent mesh-based road surface reconstruction methods have shown promising results, but they still suffer from limited reconstruction quality and high optimization cost, especially in large-scale driving scenarios. To address these limitations, we propose ROADGS-T, a robust and efficient large-scale road surface mapping framework based on adaptive meshgrid Gaussian representation. Specifically, we model the road surface by placing 2D Gaussian surfels on a meshgrid, where each surfel explicitly stores color, semantic, and geometric information. Compared with conventional mesh-based representations and 3D Gaussian primitives, the proposed meshgrid Gaussian representation better matches the thin-surface property of roads while significantly reducing redundant primitives and overlap during optimization. To further improve representation efficiency and structural fidelity, we introduce a road-structure-aware adaptive meshgrid strategy, which allocates denser Gaussian surfels to geometrically or semantically complex regions, such as lane markings, road boundaries, and height discontinuities, while maintaining a compact representation in flat road areas. Moreover, instead of relying on a single nearest vehicle pose, we design a trajectory-consistency-guided pose-robust refinement strategy, which estimates local surface priors from multiple neighboring poses and adaptively weights pose-guided height regularization according to their geometric consistency.

cs.CV↗

arXiv2026

GaussianDWM++: Language-Grounded 3D Gaussian Driving World Model for Unified Scene Understanding, Editing, and Multi-Modal Generation

Driving World Models (DWMs) have recently advanced rapidly with generative models, yet most existing methods mainly focus on conditional scene generation and lack explicit 3D scene understanding, language-grounded reasoning, and controllable 4D editing capabilities. Moreover, commonly used point cloud, occupancy, or BEV representations make it difficult to achieve fine-grained alignment between textual information and the underlying 3D scene structure. To address these limitations, we propose a foundation-feature Gaussian driving world model that unifies scene understanding, language-grounded reasoning, controllable 4D editing, and multi-modal generation within a single framework. Specifically, we introduce a foundation-feature Gaussian tokenizer that directly distills Qwen/SigLIP visual-language features into 3D Gaussian primitives, building a compact open-vocabulary Gaussian semantic field. We further design a geometry-aware Gaussian adapter that combines importance-aware hierarchical selection with text-conditioned Perceiver-style cross-attention to aggregate dense Gaussian primitives into compact world tokens. To improve representation compatibility, we introduce a KL-based Gaussian--image distribution alignment objective that aligns Gaussian world tokens with foundation image tokens. Based on the aligned Gaussian representation, our framework further supports instruction-controllable scene editing, including weather-conditioned generation and dynamic vehicle manipulation. Extensive experiments on broader driving benchmarks demonstrate that our method achieves state-of-the-art performance across scene understanding, visual grounding, planning-oriented reasoning, and controllable 4D generation tasks. We will release the code and datasets publicly on Github.

cs.CV↗

arXiv2026

Multi-Submap Implicit Neural SLAM with Local-to-Global Loop Closure for Large-Scale Scene Reconstruction

Neural Radiance Fields (NeRF)-based SLAM has demonstrated impressive results in small-scale scene reconstruction, yet scaling these methods to extensive, complex environments remains challenging due to catastrophic forgetting and accumulated trajectory drift. This paper presents a robust, large-scale neural SLAM system featuring a multi-submap architecture and a dual-tier loop closure mechanism. Specifically, we propose a progressive mapping strategy that dynamically allocates neural submaps to maintain high-fidelity representations without memory explosion. For robust pose estimation, an optical-flow-based tracking module is integrated to handle aggressive motions. To address global consistency, we introduce a local-to-global loop closure framework leveraging the foundation model for high-performance global descriptor extraction, significantly enhancing relocalization accuracy under varying viewpoints. Furthermore, an inter-submap online distillation algorithm is designed during back-end optimization to enforce geometric and appearance consistency across overlapping submap boundaries. To validate the system, we developed a customized handheld mechatronic platform and conducted extensive evaluations on both public benchmarks and our large-scale indoor-outdoor datasets. Experimental results, including direct deployment on an onboard computing unit, demonstrate that our approach outperforms state-of-the-art neural SLAM methods in reconstruction quality and localization robustness, providing a scalable solution for real-world robotic perception and digital twinning. We will release the code publicly on \href{https://github.com/dtc111111/MSN-SLAM}{https://github.com/dtc111111/MSN-SLAM} .

cs.CV↗

arXiv2026

MAGS-SLAM: Monocular Multi-Agent Gaussian Splatting SLAM for Geometrically and Photometrically Consistent Reconstruction

Collaborative photorealistic 3D reconstruction from multiple agents enables rapid large-scale scene capture for virtual production and cooperative multi-robot exploration. While recent 3D Gaussian Splatting (3DGS) SLAM algorithms can generate high-fidelity real-time mapping, most of the existing multi-agent Gaussian SLAM methods still rely on RGB-D sensors to obtain metric depth and simplify cross-agent alignment, limiting their deployment on low-cost or power-constrained robotic platforms, especially given the wider availability of RGB cameras. To address this challenge, we propose MAGS-SLAM, the first RGB-only multi-agent 3DGS SLAM framework for collaborative scene reconstruction. Each agent independently builds local monocular Gaussian submaps and transmits compact submap summaries rather than raw observations or dense maps. To facilitate robust collaboration in the presence of monocular scale ambiguity, our framework integrates compact submap communication, geometry- and appearance-aware loop verification, and occupancy-aware Gaussian fusion, enabling coherent global reconstruction without active depth sensors. We further introduce ReplicaMultiagent Plus, a benchmark containing larger robot teams for evaluating collaborative Gaussian SLAM. Extensive experiments on synthetic and real-world datasets show that MAGS-SLAM achieves tracking accuracy and rendering quality competitive with or superior to those of state-of-the-art RGB-D collaborative Gaussian SLAM methods using RGB images alone.

cs.RO↗

arXiv2026

ExtraGS: Enhancing Endoscopic View Extrapolation via Diffusion-Guided 3D Gaussian Splatting

Robot-assisted minimally invasive surgery (MIS) critically depends on reliable endoscopic perception for navigation and safety. However, conventional endoscopes provide only a limited field of view, leaving large portions of the surrounding anatomy unobserved. Recent neural rendering approaches, such as Neural Radiance Fields and 3D Gaussian Splatting, enable novel view synthesis from endoscopic videos, but their reliance on sparse observations often leads to severe artifacts when extrapolating beyond the training trajectory. In this work, we propose ExtraGS, a framework for enhancing endoscopic view extrapolation through diffusion-guided 3D Gaussian Splatting. Starting from an initial reconstruction, we introduce an uncertainty-guided virtual camera sampling strategy to actively explore blind spots and maximize information gain. The rendered views from these sampled locations are refined using a diffusion model to recover plausible anatomical structures, producing pseudo-observations that guide further optimization. To prevent the generated content from degrading reliable regions, we adopt a confidence-weighted fine-tuning strategy when incorporating these pseudo-observations. Extensive experiments on multiple public endoscopic datasets demonstrate that ExtraGS significantly reduces extrapolation artifacts and achieves state-of-the-art performance in endoscopic novel view synthesis.

cs.CV↗

arXiv2026

Wearing A Coat: Dual-Arm Robot-Assisted Dressing with Differentiable Clothing Simulation

The development of assistive robots for dressing tasks serves to augment human convenience and improve the quality of life for individuals with physical impairments. However, due to the intricate contact interactions between garments and the human limbs during dressing, most robot-assisted dressing algorithms treat clothing as an assembly of discrete segments, thereby struggling to manage the partial worn garments under contact constraints. To overcome this challenge, we propose a novel robotic dressing control algorithm that integrates realtime differentiable clothing simulation. The simulation algorithm employs explicit iterative scheme with intentionally introduced higher-order perturbations to enhance computational efficiency while maintaining stability under large time-step conditions. Through simulation, we resolve the garment state under contact constraints, which then enables a multi-phase control strategy for successful coat dressing assistance. To further improve real-time performance, we introduce a constrained local model along with its corresponding optimization solver, permitting high-frequency local compensation for the differentiable simulation based global controller. Finally, we experimentally validate our approach through both simulated and physical dressing scenarios, conclusively demonstrating its feasibility and efficacy

cs.RO↗