정 우진

ethanjohnson592's activity

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

upvoted a paper 13 days ago

VibeVideoBench: Evaluating Multimodal Agents on Code-Driven Video Generation

Paper • 2610.35864 • Published 15 days ago • 21

upvoted a paper 15 days ago

DynaFlow: Learning Free-Form Multi-Agent Orchestration

Paper • 2610.34467 • Published 17 days ago • 39

upvoted a paper 20 days ago

StreamEval: Evaluating Interactive Streaming Video Generation Models

Paper • 2610.28402 • Published 22 days ago • 29

upvoted a paper 22 days ago

MJev-Spatial: System One Spatial Intelligence via Native Attention Matching

Paper • 2610.22276 • Published 27 days ago • 81

upvoted 9 papers 23 days ago

Has GPT-6-Astra Achieved Embodied Intelligence?

Paper • 2610.22471 • Published 27 days ago • 136

From Correctness to Utility: Gain-Based Prefix Evaluation for LLM Reasoning

Paper • 2606.07190 • Published Jun 5 • 14

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published Jun 4 • 37

OmniDirector: General Multi-Shot Camera Cloning without Cross-Paired Data

Paper • 2606.13432 • Published Jun 11 • 59

Search and Refine During Think: Autonomous Retrieval-Augmented Reasoning of LLMs

Paper • 2505.11277 • Published May 16, 2025 • 10

Learn What's Left, Not What's Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization

Paper • 2608.16072 • Published Aug 17 • 30

EnvHarness: Awakening Static Worlds for Agent Learning

Paper • 2608.19880 • Published Aug 20 • 109

Harness Handbook: Making Evolving Agent Harnesses Readable,Navigable, and Editable

Paper • 2607.13285 • Published Jul 14 • 114

Looped World Models

Paper • 2606.18208 • Published Jun 16 • 51

upvoted 7 papers 26 days ago

Lucida: Parse, Generate, and Place for Composable Real-to-Sim Scene Modeling

Paper • 2608.30821 • Published Aug 31 • 65

Beyond Pixels: From Video Priors to 4D Worlds

Paper • 2608.10744 • Published Aug 11 • 74

OmniEdu: Open Foundation Models for Learning and Teaching

Paper • 2609.23088 • Published Sep 19 • 55

OneStreamer: Unifying Perception, Memory, and Proactive Response in Streaming Video Interaction

Paper • 2610.01762 • Published Oct 1 • 72

RewardHarness: Self-Evolving Agentic Post-Training

Paper • 2605.08703 • Published May 9 • 9

Dr. Claw: An AI Scientist Workspace for Vibe Research

Paper • 2609.00365 • Published Aug 31 • 37

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

Paper • 2609.38721 • Published Sep 30 • 134