gjb970312.

gjb970312's activity

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

upvoted a paper 1 day ago

CaPtain: A Pipeline for Post-Training Code-as-Policy Robot Agents

Paper • 2610.40799 • Published 6 days ago • 21

upvoted 2 papers 2 days ago

Look Only When Needed: Certificate-Guided Visual Routing for Efficient Diffusion VLMs

Paper • 2610.36671 • Published 8 days ago • 116

The Last AI Built by Humans: Toward Genuine Recursive Self-Improvement

Paper • 2609.11873 • Published Sep 10 • 38

upvoted a paper 4 days ago

A-RSI: Adaptive Task Refresh for Zero-Data Multimodal Self-Improvement

Paper • 2610.38568 • Published 7 days ago • 74

upvoted 2 papers 6 days ago

ChronoReplay: One Answer Interface Is Not Enough for Streaming Spatial Intelligence

Paper • 2610.34283 • Published 10 days ago • 25

Memory Tax: Dissecting the Net Value of Agent Memory

Paper • 2610.34073 • Published 10 days ago • 25

upvoted 3 papers 8 days ago

InteractiveWorld: A Verifiable Human-Centric Environment for Building Better Interactive MLLM Assistants

Paper • 2610.33966 • Published 10 days ago • 47

Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents

Paper • 2610.33568 • Published 11 days ago • 31

Reading, Writing, Sharing, and Interacting with the World through Video

Paper • 2610.31668 • Published 13 days ago • 42

upvoted 2 papers 11 days ago

OmniCompass: A Holistic Benchmark for Omni-Modal Video Grounding and Understanding

Paper • 2610.18829 • Published 22 days ago • 56

WeVisOne-VL: Unified Visual Perception from Objects to Pixels

Paper • 2610.31329 • Published 13 days ago • 45

upvoted 6 papers about 1 month ago

LoopVL: Recurrent Visual Intelligence

Paper • 2609.38426 • Published Sep 29 • 41

UniEvo-VL: An On-policy Self-Distillation Training Recipe for Multimodal Model Self-improvement

Paper • 2609.38721 • Published Sep 30 • 134

Raven: The Harness of Harnesses for Composable Agentic Intelligence

Paper • 2609.33439 • Published Sep 27 • 101

SAKI: Maximal-Coupling-Routed Teacher Supervision for On-Policy Distillation

Paper • 2609.36601 • Published Sep 29 • 24

YuE2: Unifying Symbolic and Audio Music Generation at Frontier Quality

Paper • 2609.33757 • Published Sep 27 • 157

RRSI: Regularized Recursive Self-Improvement of Agent Harnesses

Paper • 2609.24972 • Published Sep 21 • 164

upvoted 3 papers about 2 months ago

AI for Games in the Foundation Model Era

Paper • 2609.16679 • Published Sep 15 • 109

ZGCM-1: A Fully Open and Extremely Efficient Foundation Model for Math and Agentic Search

Paper • 2609.13356 • Published Sep 11 • 100

Breaking the Vision-Action Shortcut: Latent Interface Training for Generalizable Robotics Foundation Models

Paper • 2609.12641 • Published Sep 11 • 62