ThinkAct

ThinkAct-Share's activity

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

cmhungsteve 

authored 2 papers 10 days ago

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

Paper • 2609.07941 • Published 12 days ago • 18

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

Paper • 2609.04201 • Published 16 days ago • 49

cmhungsteve 

submitted a paper to Daily Papers 10 days ago

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

Paper • 2609.07941 • Published 12 days ago • 18

cmhungsteve 

authored a paper 26 days ago

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

Paper • 2608.21031 • Published 29 days ago • 4

cmhungsteve 

submitted a paper to Daily Papers 26 days ago

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

Paper • 2608.21031 • Published 29 days ago • 4

cmhungsteve 

authored a paper 3 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 113

cmhungsteve 

submitted a paper to Daily Papers 3 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 113

cmhungsteve 

authored 3 papers 4 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 8 months ago

3AM: Segment Anything with Geometric Consistency in Videos

Paper • 2601.08831 • Published Jan 13 • 34

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

Paper • 2508.14041 • Published Aug 19, 2025 • 59

cmhungsteve 

authored a paper 8 months ago

3AM: Segment Anything with Geometric Consistency in Videos

Paper • 2601.08831 • Published Jan 13 • 34

FuEnYang 

authored a paper 8 months ago

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

Paper • 2601.09708 • Published Jan 14 • 55

cmhungsteve 

authored 2 papers 8 months ago

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

Paper • 2601.09708 • Published Jan 14 • 55

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

Paper • 2601.05242 • Published Jan 8 • 235

cmhungsteve 

authored a paper 9 months ago

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 9 months ago

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

Paper • 2512.17012 • Published Dec 18, 2025 • 49

cmhungsteve 

authored a paper 9 months ago

Zoom-Zero: Reinforced Coarse-to-Fine Video Understanding via Temporal Zoom-in

Paper • 2512.14273 • Published Dec 16, 2025 • 10

cmhungsteve 

authored a paper 10 months ago

BlurDM: A Blur Diffusion Model for Image Deblurring

Paper • 2512.03979 • Published Dec 3, 2025 • 5