Min-Hung Chen

cmhungsteve's activity

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

authored a paper 6 days ago

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

Paper • 2608.21031 • Published 10 days ago • 4

upvoted a paper 6 days ago

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

Paper • 2608.21031 • Published 10 days ago • 4

submitted a paper to Daily Papers 6 days ago

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

Paper • 2608.21031 • Published 10 days ago • 4

upvoted a paper 10 days ago

Stealing Reasoning Traces from Proprietary LLM APIs

Paper • 2608.09867 • Published 21 days ago • 116

upvoted a collection 16 days ago

Qwen3.8

Collection

4 items • Updated 17 days ago • 458

upvoted 2 papers 2 months ago

One Model, Many Latencies: Universal Speech Enhancement for Diverse Real-Time Applications

Paper • 2606.25621 • Published Jun 24 • 22

Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients

Paper • 2606.18216 • Published Jun 16 • 65

upvoted a collection 3 months ago

Cosmos3

Collection

Omnimodal World Models for Physical AI • 6 items • Updated 3 days ago • 192

authored a paper 3 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 112

upvoted a paper 3 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 112

submitted a paper to Daily Papers 3 months ago

SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning

Paper • 2606.13673 • Published Jun 11 • 112

authored 3 papers 3 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

upvoted 3 papers 3 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

New activity in nvidia/4D-RGPT-8B 3 months ago

fix links

#1 opened 3 months ago by

cmhungsteve

liked a model 3 months ago

nvidia/4D-RGPT-8B

Video-Text-to-Text • Updated Jun 2 • 102 • 17

upvoted a paper 3 months ago

Why Far Looks Up: Probing Spatial Representation in Vision-Language Models

Paper • 2605.30161 • Published May 28 • 60