wongyukim

wongyukim's activity

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

upvoted 3 papers 1 day ago

Harness the Memory: A Holistic Evaluation of Memory Substrates in Memory Agents

Paper • 2608.15008 • Published 6 days ago • 14

FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive Execution

Paper • 2608.16157 • Published 4 days ago • 69

Demystifying Agent Skills: Why They Work-Until They Don't

Paper • 2608.14036 • Published 7 days ago • 155

upvoted a paper 2 days ago

HarnessEval-W: Agentifying the Evaluation of Visual Worlds

Paper • 2608.16859 • Published 4 days ago • 119

upvoted 3 papers 3 days ago

MobileMem: Learning from a Year of Mobile Experiences

Paper • 2608.13606 • Published 10 days ago • 23

Self-Supervised Visual On-Policy Distillation

Paper • 2608.14144 • Published 7 days ago • 162

Can We Defend Against AI-Generated Video Attacks on Real-World Crisis Events? A Systematic Evaluation of Detectors, Generators and Social Dissemination

Paper • 2608.14391 • Published 7 days ago • 274

upvoted 6 papers 4 days ago

SKILLER: Language-Level Reinforcement Learning for Reusable Skill Extraction in Small Language Models

Paper • 2608.10538 • Published 10 days ago • 15

LycheeMemory V2: Efficient Long-Term Memory for LLM Agents via Semantic Segment-Level Consolidation

Paper • 2608.12990 • Published 8 days ago • 14

Maglev: Sliding Recurrent Memory

Paper • 2608.02870 • Published 16 days ago • 14

AutoDesign: Meta-Harness Optimization for Long-Horizon Agentic Design

Paper • 2608.13560 • Published 8 days ago • 52

Spatial Memory Agent: Experience-Grounded Procedure Memory for Spatial Intelligence

Paper • 2608.12743 • Published 8 days ago • 42

DarwinX: Evolving Agent Harnesses Through Natural Selection

Paper • 2608.07545 • Published 21 days ago • 107

upvoted a paper 8 days ago

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

Paper • 2608.11079 • Published 10 days ago • 17

upvoted 3 papers 9 days ago

Motif 3: Technical Report

Paper • 2608.09119 • Published 11 days ago • 46

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

Paper • 2608.07169 • Published 14 days ago • 50

On-Policy Self-Distillation without Any Supervision

Paper • 2608.06296 • Published 12 days ago • 215

upvoted 2 papers 10 days ago

Douyin Multimodal Embedding Model Technical Report

Paper • 2608.02148 • Published 18 days ago • 14

Addressable Memory for Video World Models

Paper • 2608.07408 • Published 14 days ago • 15

upvoted a paper 11 days ago

AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning

Paper • 2608.05987 • Published 15 days ago • 97