TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
Paper • 2609.33419 • Published • 19
AI & ML interests
None defined yet.
Recent Activity
View all activity
Team members 24 private
cmhungsteve
authored a
paper 4 days ago
cmhungsteve
authored 2
papers 27 days ago
cmhungsteve
submitted a
paper to Daily Papers 27 days ago
cmhungsteve
authored a
paper about 1 month ago
cmhungsteve
submitted a
paper to Daily Papers about 1 month ago
hamacojr
authored a
paper 4 months ago
cmhungsteve
authored a
paper 4 months ago
cmhungsteve
submitted a
paper to Daily Papers 4 months ago
cmhungsteve
authored 3
papers 4 months ago
FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding
Paper • 2605.19846 • Published • 3
DVSM: Decoder-only View Synthesis Model Done Right
Paper • 2605.29891 • Published • 2
Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them
Paper • 2606.06361 • Published • 16
Zhiding
authored 8
papers 4 months ago
Neural Eulerian Scene Flow Fields
Paper • 2410.02031 • Published
Eagle 2: Building Post-Training Data Strategies from Scratch for Frontier Vision-Language Models
Paper • 2501.14818 • Published • 10
QLIP: Text-Aligned Visual Tokenization Unifies Auto-Regressive Multimodal Understanding and Generation
Paper • 2502.05178 • Published • 10
GR00T N1: An Open Foundation Model for Generalist Humanoid Robots
Paper • 2503.14734 • Published • 9
Nemotron-H: A Family of Accurate and Efficient Hybrid Mamba-Transformer Models
Paper • 2504.03624 • Published • 20
OpenVision 3: A Family of Unified Visual Encoder for Both Understanding and Generation
Paper • 2601.15369 • Published • 22
Fully Attentional Networks with Self-emerging Token Labeling
Paper • 2401.03844 • Published
Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
Paper • 2505.23766 • Published