Songlin Wei
5 papers · 2024–2025 · 2 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+1 more ↓ Show less ↑
🌍 Conference Polyglot (2) 🌈 Renaissance Researcher (6) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐝 Cross-Pollinator (15)
👥
Mega-Team
(34)
Conferences
RSS (3)
CORL (2)
Top co-authors
Keywords
reinforcement learning
(1)
imitation learning
(1)
sim-to-real transfer
(1)
robot navigation
(1)
multimodal learning
(1)
video understanding
(1)
synthetic data generation
(1)
vision language model
(1)
end-to-end learning
(1)
articulated object
(1)
natural language instruction
(1)
embodied navigation
(1)
vision language action
(1)
language instruction
(1)
simulation platform
(1)
part grounding
(1)
action program
(1)
end effector trajectory
(1)
Papers
GraspVLA: a Grasping Foundation Model Pre-trained on Billion-scale Synthetic Action Data
CORL 2025
Uni-NaVid: A Video-based Vision-Language-Action Model for Unifying Embodied Navigation Tasks
RSS 2025
RoboVerse: A Unified Platform, Benchmark and Dataset for Scalable and Generalizable Robot Learning
RSS 2025
D$^3$RoMa: Disparity Diffusion-based Depth Sensing for Material-Agnostic Robotic Manipulation
CORL 2024
SAGE: Bridging Semantic and Actionable Parts for GEneralizable Articulated-Object Manipulation under Language Instructions
RSS 2024