Chen Gao

Beihang University

収録論文 30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

• EmbodiedVAE: 効率的で制御可能な身体化操作のための分離型ビデオVAE
  操作2026/8/4

  ロボット操作の世界モデル向けに、ロボットアームの動きと背景を分離して圧縮する新しいビデオVAEを提案し、高圧縮率で高品質な再構成と精密な動作制御を実現した。

• EmbodiedVAE: Disentangled Video VAE for Efficient and Controllable Embodied Manipulation
  2026/8/1
• Worldscape-MoE: A Unified Mixture-of-Experts World Model for Scalable Heterogeneous Action Control
  2026/7/1
• ActiveFly-Bench: Aligning Embodied Question Answering with Vision-Language-Action for Aerial Embodied Perception
  2026/7/1
• TacWAM: Anchor-Guided World Action Model with Mechanics-Aware Tactile Prediction
  2026/7/1
• WorldScape Policy 2.0: Empowering Steerable World Action Modeling with Reasoning-Augmented Memory
  2026/7/1
• Dreaming when Necessary: Advancing World Action Models with Adaptive Multi-Modal Reasoning
  2026/6/1
• Supervise What Survives: Geometry-Guided VLA Adaptation from Synthetic Robot Videos
  2026/6/1
• TacForeSight: Force-Guided Tactile World Model for Contact-Rich Manipulation
  2026/6/1
• WorldVLN: Autoregressive World Action Model for Aerial Vision-Language Navigation
  2026/5/1
• GE-Sim 2.0: A Roadmap Towards Comprehensive Closed-loop Video World Simulators for Robotic Manipulation
  2026/5/1
• WorldArena 2.0: Extending Embodied World Model Benchmarking on Modality, Functionality and Platform
  2026/5/1
• ManiSoft: Towards Vision-Language Manipulation for Soft Continuum Robotics
  2026/5/1
• Escaping the Diversity Trap in Robotic Manipulation via Anchor-Centric Adaptation
  2026/5/1
• WorldMAP: Bootstrapping Vision-Language Navigation Trajectory Prediction with Generative World Models
  2026/4/1
• BiCoord: A Bimanual Manipulation Benchmark towards Long-Horizon Spatial-Temporal Coordination
  2026/4/1
• OmniVTA: Visuo-Tactile World Modeling for Contact-Rich Robotic Manipulation
  2026/3/1
• WorldArena: A Unified Benchmark for Evaluating Perception and Functional Utility of Embodied World Models
  2026/2/1
• Aerial World Model for Long-horizon Visual Generation and Navigation in 3D Space
  2025/12/1
• EVOLVE-VLA: Test-Time Training from Environment Feedback for Vision-Language-Action Models
  2025/12/1
• RoboScape-R: Unified Reward-Observation World Models for Generalizable Robotics Training via RL
  2025/12/1
• SDA-PLANNER: State-Dependency Aware Adaptive Planner for Embodied Task Planning
  2025/9/1
• AirScape: An Aerial Generative World Model with Motion Controllability
  2025/7/1
• RoboCerebra: A Large-scale Benchmark for Long-horizon Robotic Manipulation Evaluation
  2025/6/1
• RoboScape: Physics-informed Embodied World Model
  2025/6/1
• OctoNav: Towards Generalist Embodied Navigation
  2025/6/1
• CityNavAgent: Aerial Vision-and-Language Navigation with Hierarchical Semantic Planning and Global Memory
  2025/5/1
• GeoNav: Empowering MLLMs with dual-scale geospatial reasoning for language-goal aerial navigation
  2025/4/1
• TopV-Nav: Unlocking the Top-View Spatial Reasoning Potential of MLLM for Zero-shot Object Navigation
  2024/11/1
• EmbodiedCity: A Benchmark Platform for Embodied Agent in Real-world City Environment
  2024/10/1