Edward Williams

Orbit-Noah's activity

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

upvoted a paper 17 days ago

The Trinity:Capability-Driven Recursive Self-Improvement for Multimodal Agents

Paper • 2610.36077 • Published 20 days ago • 160

upvoted a paper 21 days ago

Verus-Insight: Towards Explainable Artifact Detection in AI-Generated Videos

Paper • 2610.30866 • Published 24 days ago • 15

upvoted 4 papers about 1 month ago

Player-1: Learning to Play from Synthetic Experience

Paper • 2610.20584 • Published Oct 14 • 59

Thinking Inertia: LLMs Keep Thinking When Told Not To

Paper • 2610.11765 • Published Oct 8 • 127

Rethinking Long-Video Efficiency: A Joint Allocation Perspective on Frames, Pixels, and Front-End Latency

Paper • 2610.04318 • Published Oct 3 • 12

Predictive Credit: Measuring What Scientific Explanations Add to Experimental Forecasts

Paper • 2610.00314 • Published Sep 29 • 9

upvoted 3 papers about 2 months ago

When2Think: Learning When and How Much to Reason

Paper • 2609.19671 • Published Sep 28 • 21

Rethinking Critic Learning in PPO: Understanding and Mitigating Value Flattening

Paper • 2609.18708 • Published Sep 16 • 56

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published Sep 7 • 49

upvoted 5 papers 2 months ago

Atria Dawn: The Dawn of Agentic Superintelligence

Paper • 2609.15818 • Published Sep 14 • 248

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published Aug 29 • 76

Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation

Paper • 2609.08798 • Published Sep 8 • 69

Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding

Paper • 2609.04131 • Published Sep 3 • 21

Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills

Paper • 2609.02749 • Published Sep 2 • 149

upvoted 6 papers 3 months ago

OpenART: Scaling Agent Red Teaming via Open-Ended Environment Evolution

Paper • 2608.00677 • Published Aug 1 • 26

A^2E : An End-to-End Agent Auditing Engine

Paper • 2608.07346 • Published Aug 10 • 11

HarnessOpt-Bench: Evaluating LLMs at Harness Optimization

Paper • 2608.06301 • Published Aug 6 • 16

K-EXAONE 2.0 Technical Report

Paper • 2608.04505 • Published Aug 5 • 24

CADENA: Stepwise CAD Reverse Engineering

Paper • 2608.00799 • Published Aug 1 • 39

From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement

Paper • 2607.23802 • Published Jul 26 • 79