wongyukim

wongyukim's activity

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

upvoted 6 papers 3 days ago

Memory for Large Language Models

Paper • 2607.25380 • Published 6 days ago • 9

MemHarness: Memory Is Reconstructed, Not Replayed

Paper • 2607.28272 • Published 4 days ago • 14

Memory Decoder at Scale: A Pretrained, Parametric Long-Term Memory

Paper • 2607.27919 • Published 4 days ago • 51

Filesystem-Based Memory for LLM Agents: Organization, Evolution, and Sustainability

Paper • 2607.26637 • Published 5 days ago • 9

SkillRise: Agentic Reinforcement Learning for Cross-Task Skill Evolution

Paper • 2607.26784 • Published 5 days ago • 25

Metis: Memory Foundation Model

Paper • 2607.26760 • Published 5 days ago • 260

upvoted a paper 5 days ago

Kimi K3: Open Frontier Intelligence

Paper • 2607.24653 • Published 7 days ago • 441

upvoted a paper 6 days ago

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

Paper • 2607.21653 • Published 12 days ago • 32

upvoted 2 papers 7 days ago

Visual Contrastive Self-Distillation

Paper • 2607.21556 • Published 11 days ago • 51

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

Paper • 2607.22529 • Published 10 days ago • 47

upvoted a paper 10 days ago

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

Paper • 2607.16617 • Published 16 days ago • 140

upvoted 2 papers 12 days ago

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

Paper • 2607.17250 • Published 15 days ago • 92

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

Paper • 2607.07820 • Published 26 days ago • 91

upvoted 2 papers 13 days ago

Recursive Harness Self-Improvement

Paper • 2607.15524 • Published 17 days ago • 25

On-Policy Delta Distillation

Paper • 2607.15161 • Published 18 days ago • 38

upvoted 2 papers 16 days ago

AgentCompass: A Unified Evaluation Infrastructure for Agent Capabilities

Paper • 2607.13705 • Published 19 days ago • 45

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

Paper • 2607.13285 • Published 20 days ago • 232

upvoted a paper 18 days ago

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

Paper • 2607.10350 • Published 19 days ago • 85

upvoted a paper 19 days ago

LightMem-Ego: Your AI Memory for Everyday Life

Paper • 2607.11487 • Published 21 days ago • 47

upvoted a paper 21 days ago

Video-Oasis: Rethinking Evaluation of Video Understanding

Paper • 2603.29616 • Published Jul 2 • 65