On-Policy Distillation Teaches New Skills but Not New Knowledge
Paper • 2610.09639 • Published • 7
wongyukim
wongyukim
AI & ML interests
None yet
Recent Activity
upvoted a paper about 11 hours ago
On-Policy Distillation Teaches New Skills but Not New Knowledge upvoted a paper about 11 hours ago
AgentGarten: Code Worlds for Evolving Agents upvoted a paper 3 days ago
RoboJEPA: Scaling Robotic Latent World ModelsOrganizations
upvoted 2
papers about 11 hours ago
upvoted 5
papers 3 days ago
RoboJEPA: Scaling Robotic Latent World Models
Paper • 2610.10515 • Published • 5
Learning Multimodal Embeddings with Evidence-Aligned Readout
Paper • 2609.33659 • Published • 11
DecepEval: A Benchmark for Evaluating Deception in LLM Agents
Paper • 2610.07967 • Published • 81
UniWAM: Unified World-Action Model
Paper • 2610.02054 • Published • 67
Long-WAM: Scaling the Context of World-Action Models
Paper • 2610.10528 • Published • 107
upvoted 4
papers 4 days ago
Harness-Aware Distillation for Small Language Model Agents
Paper • 2610.02858 • Published • 16
Taming VLAs under Robot Execution Errors: Self-Compensation and Stress Testing
Paper • 2609.37334 • Published • 45
DiVeR: Decision-Critical Verifier Learning for VLA Test-Time Scaling
Paper • 2610.04933 • Published • 17
EVISKILL: Grounding Skill Evolution in Replayable Evidence
Paper • 2610.05030 • Published • 53
upvoted 3
papers 5 days ago
HLA-WM: Hybrid Linear Attention for Long-Horizon Video World Models
Paper • 2610.05739 • Published • 21
RealtimeWAM: One-Step Asynchronous World Action Models
Paper • 2610.06617 • Published • 24
LLM-as-Jev: LLMs Are Already Jev-Style Decision Models -- When and How to Fine-Tune Them
Paper • 2610.02076 • Published • 14
upvoted 6
papers 6 days ago
WM-VLM: Probing Internal World Models for Interleaved Visual-Textual Reasoning
Paper • 2609.34826 • Published • 12
World Embedding Benchmark
Paper • 2610.03632 • Published • 56
Spatial Memory Intelligence: Endowing World Models with Understanding-Driven Long-Term Memory
Paper • 2610.02521 • Published • 60
VeriHarness: Scaling Agentic Verification for Long-Horizon Tasks
Paper • 2610.00972 • Published • 62
Native Action-Prior Learning from Videos for World Action Models
Paper • 2610.03391 • Published • 88
World Action Modeling with Progressive Visual Planning
Paper • 2610.02508 • Published • 98