AI.info

Jiangmiao Pang

Explore Jiangmiao Pang on AI.info.

• GAUGE: A Measurement-Grounded Benchmark for Physical Fidelity in Simulation Engines and Video World Models
• Exploratory, Communicative, and Deployable: Vision-Driven Embodied Agents for Open-World Mobile Manipulation
• ST4VLA: Spatially Guided Training for Vision-Language-Action Models
• RoboInter: A Holistic Intermediate Representation Suite Towards Robotic Manipulation
• Robo3R: Enhancing Robotic Manipulation with Accurate Feed-Forward 3D Reconstruction
• SynthVerse: A Large-Scale Diverse Synthetic Dataset for Point Tracking
• UniCon: A Unified System for Efficient Robot Learning Transfers
• RoboVIP: Multi-View Video Generation with Visual Identity Prompting Augments Robot Manipulation
• VLNVerse: A Benchmark for Vision-Language Navigation with Versatile, Embodied, Realistic Simulation and Evaluation
• MMSI-Video-Bench: A Holistic Benchmark for Video-Based Spatial Intelligence
• G$^2$VLM: Geometry Grounded Vision Language Model with Unified 3D Reconstruction and Spatial Reasoning
• EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
• Towards Adaptable Humanoid Control via Adaptive Motion Tracking
• InternVLA-M1: A Spatially Guided Vision-Language-Action Framework for Generalist Robot Policy
• PhysHSI: Towards a Real-World Generalizable and Natural Humanoid-Scene Interaction System