wongyukim

wongyukim's activity

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

upvoted a paper about 19 hours ago

SkillZip: Evaluation-Free Skill Compression for Self-Evolving Agents by Discovering Reusable Structure

Paper • 2608.11079 • Published 3 days ago • 13

upvoted 3 papers 2 days ago

Motif 3: Technical Report

Paper • 2608.09119 • Published 4 days ago • 43

Agent Memory Distillation: Empowering Small LLM Agents with Hierarchical Teacher Memory

Paper • 2608.07169 • Published 7 days ago • 47

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 5 days ago • 194

upvoted 2 papers 3 days ago

Douyin Multimodal Embedding Model Technical Report

Paper • 2608.02148 • Published 11 days ago • 14

Addressable Memory for Video World Models

Paper • 2608.07408 • Published 7 days ago • 12

upvoted a paper 4 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 8 days ago • 92

upvoted 7 papers 6 days ago

FinanceHarness: Autonomous Financial Deep Research Framework

Paper • 2607.27853 • Published 7 days ago • 11

FocusMem: Factorizing Content, Readout, and Trust in Latent GUI Memory

Paper • 2608.04530 • Published 9 days ago • 14

When Memory Lies: An Empirical Study of Spatial Memory Staleness in VLM Agents

Paper • 2608.04574 • Published 9 days ago • 16

K-EXAONE 2.0 Technical Report

Paper • 2608.04505 • Published 9 days ago • 25

Toward Skill-Native LLMs: Skill Entropy for Benchmarking and Training Long-Horizon Reasoning

Paper • 2608.05139 • Published 9 days ago • 27

OneDayAgent: Towards a Long-Horizon Harness for Autonomous Agents

Paper • 2608.05013 • Published 10 days ago • 35

Recursive Synthesis for Long-Horizon Terminal Tasks

Paper • 2608.05466 • Published 7 days ago • 239

upvoted 6 papers 8 days ago

SkillJack: Persistent Skill Backdoors in Self-Evolving Agents

Paper • 2608.03509 • Published 10 days ago • 23

Zero-Mem: Zero-Token Memory Operations for LLM Agents

Paper • 2607.29377 • Published 14 days ago • 11

MemSFT: Mitigating Alignment Tax with an External Parametric Memory

Paper • 2607.25614 • Published 17 days ago • 23

UEmbed: Unified Sparse and Dense Multimodal Embeddings

Paper • 2608.02583 • Published 11 days ago • 50

Progressive Agent Skill Generation via Reinforcement Learning

Paper • 2608.01678 • Published 11 days ago • 58

LongHorizon-Harness: Advancing Long-Horizon Agents for Real-World Tasks

Paper • 2608.01964 • Published 11 days ago • 169