wongyukim

wongyukim's activity

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

upvoted a paper 1 day ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 4 days ago • 379

upvoted a paper 2 days ago

Molt: A Scalable PyTorch-Native Training Framework for Agentic Reinforcement Learning

Paper • 2607.21653 • Published 9 days ago • 30

upvoted 2 papers 3 days ago

Visual Contrastive Self-Distillation

Paper • 2607.21556 • Published 8 days ago • 50

Skill Self-Play: Pushing the Frontier of LLM Capability with Co-Evolving Skills

Paper • 2607.22529 • Published 7 days ago • 45

upvoted a paper 6 days ago

DataFlow-Harness: A Grounded Code-Agent Platform for Constructing Editable LLM Data Pipelines

Paper • 2607.16617 • Published 13 days ago • 137

upvoted 2 papers 8 days ago

EvolvingWorld: An Open-Schema Framework for Co-Evolving Role-Play Agents and World Model in Interactive Literary World

Paper • 2607.17250 • Published 12 days ago • 92

DeepSearch-World: Self-Distillation for Deep Search Agents in a Verifiable Environment

Paper • 2607.07820 • Published 23 days ago • 91

upvoted 2 papers 9 days ago

Recursive Harness Self-Improvement

Paper • 2607.15524 • Published 14 days ago • 24

On-Policy Delta Distillation

Paper • 2607.15161 • Published 15 days ago • 38

upvoted 2 papers 13 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

Paper • 2607.13705 • Published 16 days ago • 45

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

Paper • 2607.13285 • Published 17 days ago • 227

upvoted a paper 14 days ago

ABot-AgentOS: A General Robotic Agent OS with Lifelong Multi-modal Memory

Paper • 2607.10350 • Published 16 days ago • 85

upvoted a paper 15 days ago

LightMem-Ego: Your AI Memory for Everyday Life

Paper • 2607.11487 • Published 18 days ago • 47

upvoted 2 papers 17 days ago

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published 29 days ago • 65

Vidu S1: A Real-Time Interactive Video Generation Model

Paper • 2607.03118 • Published 28 days ago • 144

upvoted 3 papers 20 days ago

AgentLens: Production-Assessed Trajectory Reviews for Coding Agent Evaluation

Paper • 2607.06624 • Published 24 days ago • 8

RoboDojo: A Unified Sim-and-Real Benchmark for Comprehensive Evaluation of Generalist Robot Manipulation Policies

Paper • 2607.04434 • Published 24 days ago • 15

Dual Latent Memory in Vision-Language-Action Models for Robotic Manipulation

Paper • 2607.07608 • Published 23 days ago • 56

upvoted a paper 21 days ago

Rank-Then-Act: Reward-Free Control from Frame-Order Progress

Paper • 2607.01897 • Published 29 days ago • 7

upvoted a paper 22 days ago

Gemma 4 Technical Report

Paper • 2607.02770 • Published 29 days ago • 75