Junwei Liang
収録論文 31本 ・ フィジカルAI/ロボット学習
※arXiv著者名で収集。同姓同名の別人の論文が含まれる場合があります。
論文
- Multi-View Unified Camera Fields: Geometry-Shaped Action-Facing Representations for RGB-Only Multi-Camera VLA Policies2026/8/1
- Token-Wise Latent Streaming from Slow Reasoners to Fast Planners for Dynamic Vision Language Navigation2026/7/1
- FutureNav: Unified World-Action Modeling for Vision-and-Language Navigation2026/6/1
- Perceptive Behavior Foundation Model: Adapting Human Motion Priors to Robot-Centric Terrain2026/6/1
- MotionWAM: Towards Foundation World Action Models for Real-Time Humanoid Loco-Manipulation2026/6/1
- AffordanceVLA: A Vision-Language-Action Model Empowering Action Generation through Affordance-Aware Understanding2026/6/1
- DiT4DiT: Jointly Modeling Video Dynamics and Actions for Generalizable Robot Control2026/3/1
- NavThinker: Action-Conditioned World Models for Coupled Prediction and Planning in Social Navigation2026/3/1
- FLUX: Accelerating Cross-Embodiment Generative Navigation Policies via Rectified Flow and Static-to-Dynamic Learning2026/3/1
- MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction2026/2/1
- The RoboSense Challenge: Sense Anything, Navigate Anywhere, Adapt Across Platforms2026/1/1
- Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future2025/12/1
- 3EED: Ground Everything Everywhere in 3D2025/11/1
- EgoTraj-Bench: Towards Robust Trajectory Prediction Under Ego-view Noisy Observations2025/10/1
- From Watch to Imagine: Steering Long-horizon Manipulation via Human Demonstration and Future Envisionment2025/9/1
- End-to-End Humanoid Robot Safe and Comfortable Locomotion Policy2025/8/1
- Stairway to Success: An Online Floor-Aware Zero-Shot Object-Goal Navigation Framework via LLM-Driven Coarse-to-Fine Exploration2025/5/1
- Omni-Perception: Omnidirectional Collision Avoidance for Legged Locomotion in Dynamic Environments2025/5/1
- GLOVER++: Unleashing the Potential of Affordance Learning from Human Behaviors for Robotic Manipulation2025/5/1
- Exploring the Limits of Vision-Language-Action Manipulations in Cross-task Generalization2025/5/1
- Zero-Shot 3D Visual Grounding from Vision-Language Models2025/5/1
- SD-OVON: A Semantics-aware Dataset and Benchmark Generation Pipeline for Open-Vocabulary Object Navigation in Dynamic Scenes2025/5/1
- SeeGround: See and Ground for Zero-Shot Open-Vocabulary 3D Visual Grounding2024/12/1
- GaussianProperty: Integrating Physical Properties to 3D Gaussians with LMMs2024/12/1
- GLOVER: Generalizable Open-Vocabulary Affordance Reasoning for Task-Oriented Grasping2024/11/1
- LHPF: Look back the History and Plan for the Future in Autonomous Driving2024/11/1
- From Cognition to Precognition: A Future-Aware Framework for Social Navigation2024/9/1
- Mitigating the Human-Robot Domain Discrepancy in Visual Pre-training for Robotic Manipulation2024/6/1
- Contrastive Imitation Learning for Language-guided Multi-Task Robotic Manipulation2024/6/1
- Open-vocabulary Mobile Manipulation in Unseen Dynamic Environments with 3D Semantic Maps2024/6/1
- DragTraffic: Interactive and Controllable Traffic Scene Generation for Autonomous Driving2024/4/1