wongyukim

wongyukim's activity

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

upvoted 3 papers about 2 hours ago

An Empirical Study of Harness Design for Coding Agents

Paper • 2609.20804 • Published 4 days ago • 72

DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression

Paper • 2609.19969 • Published 4 days ago • 138

JEPA-Anything: Learning Predictive Models across Different Worlds

Paper • 2609.20800 • Published 4 days ago • 58

upvoted 2 papers 4 days ago

Modality-Autoregressive World-Action Models

Paper • 2609.17524 • Published 6 days ago • 11

Continual Learning Mechanisms Compose for Long-Horizon Memorization

Paper • 2609.06986 • Published 14 days ago • 367

upvoted 2 papers 5 days ago

Agent as Policy for Robotic Manipulation

Paper • 2609.12541 • Published 10 days ago • 17

PhysBrain 1.5: From Vision-Language Models to Physical Foundation Models

Paper • 2609.14973 • Published 7 days ago • 171

upvoted 2 papers 6 days ago

COBRA-Skills: Contextual Bandit-Guided Evolution for Agent Skill Optimization

Paper • 2609.11682 • Published 11 days ago • 44

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

Paper • 2609.12641 • Published 10 days ago • 70

upvoted 2 papers 7 days ago

Generative Late-Interaction Embeddings For Visual Document Retrieval

Paper • 2609.11808 • Published 11 days ago • 27

Memory as Plans: World-Action Modeling with Memory-Grounded Planning

Paper • 2609.11561 • Published 11 days ago • 40

upvoted 3 papers 10 days ago

Scaling Automatic Research Agents via World Models

Paper • 2608.12564 • Published 23 days ago • 470

Group Adaptive Clipping Policy Optimization

Paper • 2609.00444 • Published 21 days ago • 10

NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness

Paper • 2609.08183 • Published 13 days ago • 172

upvoted 6 papers 11 days ago

Measuring Language Transfer in Robot Policies: Adding Greek to a Cosmos3 Vision-Language-Action Policy

Paper • 2609.07470 • Published 14 days ago • 23

RoboSPA: Can VLA Models Go Beyond Simple Scenes and Short-Horizon Tasks?

Paper • 2609.05324 • Published 17 days ago • 28

Procedural Graphs: Self-Evolving Execution Structures for LLM Agents

Paper • 2609.09153 • Published 13 days ago • 40

GE-Act 2.0: Pretraining and Scaling a World-Action Model for Robotic Manipulation

Paper • 2609.05588 • Published 17 days ago • 56

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

Paper • 2609.08798 • Published 13 days ago • 78

OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining

Paper • 2609.07398 • Published 14 days ago • 76