arxiv:2412.01292
PeihaoChen
PeihaoChen
AI & ML interests
Embodied AI, Multi-Modal Understanding
Recent Activity
authored
a paper
about 1 month ago
LSceneLLM: Enhancing Large 3D Scene Understanding Using Adaptive Visual
Preferences
upvoted
a
paper
3 months ago
VidEgoThink: Assessing Egocentric Video Understanding Capabilities for
Embodied AI
upvoted
a
paper
10 months ago
3D-VLA: A 3D Vision-Language-Action Generative World Model
Organizations
None yet
models
None public yet
datasets
None public yet