ThinkAct

ThinkAct-Share's activity

• All
• Models
• Datasets
• Spaces
• Buckets
• Papers
• Collections
• Community
• Posts
• Articles

cmhungsteve 

authored a paper 19 days ago

World Editing: Intervening on Executable Worlds at Increasing Depth

Paper • 2610.02331 • Published 26 days ago • 31

cmhungsteve 

authored a paper 24 days ago

TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining

Paper • 2609.33419 • Published 30 days ago • 19

cmhungsteve 

authored 2 papers about 2 months ago

ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding

Paper • 2609.07941 • Published Sep 7 • 18

Scal3R: Learning Efficient Multi-Relative Pose Query for Scalable Online 3D Reconstruction

Paper • 2609.04201 • Published Sep 3 • 50

cmhungsteve 

submitted a paper to Daily Papers about 2 months ago

ReactVAU: A Slow-Fast Decoupled Framework for Streaming Video Anomaly Understanding

Paper • 2609.07941 • Published Sep 7 • 18

cmhungsteve 

authored a paper 2 months ago

PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration

Paper • 2608.21031 • Published Aug 21 • 4

cmhungsteve 

submitted a paper to Daily Papers 2 months ago

PhysCaP: Grounding Code-as-Policy Agent with Physics-Informed Exploration

Paper • 2608.21031 • Published Aug 21 • 4

cmhungsteve 

authored a paper 5 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 115

cmhungsteve 

submitted a paper to Daily Papers 5 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 115

cmhungsteve 

authored 3 papers 5 months ago

FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding

Paper • 2605.19846 • Published May 20 • 3

DVSM: Decoder-only View Synthesis Model Done Right

Paper • 2605.29891 • Published May 28 • 2

Physics in 2-Steps: Locking Motion Priors Before Visual Refinement Erases Them

Paper • 2606.06361 • Published Jun 4 • 16

FuEnYang 

authored 2 papers 9 months ago

3AM: Segment Anything with Geometric Consistency in Videos

Paper • 2601.08831 • Published Jan 13 • 33

LongSplat: Robust Unposed 3D Gaussian Splatting for Casual Long Videos

Paper • 2508.14041 • Published Aug 19, 2025 • 60

cmhungsteve 

authored a paper 9 months ago

3AM: Segment Anything with Geometric Consistency in Videos

Paper • 2601.08831 • Published Jan 13 • 33

FuEnYang 

authored a paper 9 months ago

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

Paper • 2601.09708 • Published Jan 14 • 55

cmhungsteve 

authored a paper 9 months ago

Fast-ThinkAct: Efficient Vision-Language-Action Reasoning via Verbalizable Latent Planning

Paper • 2601.09708 • Published Jan 14 • 55

cmhungsteve 

authored 2 papers 10 months ago

GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization

Paper • 2601.05242 • Published Jan 8 • 236

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

Paper • 2512.17012 • Published Dec 18, 2025 • 49

cmhungsteve 

submitted a paper to Daily Papers 10 months ago

4D-RGPT: Toward Region-level 4D Understanding via Perceptual Distillation

Paper • 2512.17012 • Published Dec 18, 2025 • 49