arxiv:2609.33419
Min-Hung Chen
cmhungsteve
AI & ML interests
Multimodal AI, Spatial Intelligence, Video Understanding, Efficient Deep Learning, Transfer Learning, Transformer
Recent Activity
authored a paper 5 days ago
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining upvoted a paper 6 days ago
Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents commentedon a paper 7 days ago
SpatialClaw: Rethinking Action Interface for Agentic Spatial ReasoningOrganizations
models 0
None public yet
datasets 0
None public yet