Yury Panikov

panikov's activity

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

upvoted 4 papers about 2 hours ago

LatentSkill: From In-Context Textual Skills to In-Weight Latent Skills for LLM Agents

Paper • 2606.06087 • Published 7 days ago • 56

On the Geometry of On-Policy Distillation

Paper • 2606.07082 • Published 6 days ago • 62

SWE-Explore: Benchmarking How Coding Agents Explore Repositories

Paper • 2606.07297 • Published 6 days ago • 105

Agents' Last Exam

Paper • 2606.05405 • Published 8 days ago • 158

upvoted 11 papers 4 days ago

The Flip Side of RLHF: On-Policy Feedback for Reward Model Self-Supervised Improvement

Paper • 2605.30888 • Published 13 days ago • 10

Count Anything

Paper • 2605.30846 • Published 13 days ago • 11

Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?

Paper • 2605.30557 • Published 14 days ago • 12

DecMem: Towards Minute-Long Consistent World Generation with Decoupled Memory

Paper • 2605.31336 • Published 13 days ago • 12

HL-OutPaint: Coarse-to-Fine Video Outpainting for High-Resolution Long-Range Videos

Paper • 2605.17543 • Published 23 days ago • 13

From Prompt Injection to Persistent Control: Defending Agentic Harness Against Trojan Backdoors

Paper • 2605.31042 • Published 13 days ago • 18

Linearizing Vision Transformer with Test-Time Training

Paper • 2605.02772 • Published 14 days ago • 20

Recovering Policy-Induced Errors: Benchmarking and Trajectory Synthesis for Robust GUI Agents

Paper • 2605.29447 • Published 14 days ago • 20

Harness Updating Is Not Harness Benefit: Disentangling Evolution Capabilities in Self-Evolving LLM Agents

Paper • 2605.30621 • Published 14 days ago • 22

PEEK: Picking Essential frames via Efficient Knowledge distillation

Paper • 2605.31029 • Published 13 days ago • 20

LongDS-Bench: On the Failure of Long-Horizon Agentic Data Analysis

Paper • 2605.30434 • Published 14 days ago • 21

upvoted 5 papers 8 days ago

Exploring Autonomous Agentic Data Engineering for Model Specialization

Paper • 2605.30407 • Published 14 days ago • 23

SAAS: Self-Aware Reinforcement Learning for Over-Search Mitigation in Agentic Search

Paper • 2605.29796 • Published 14 days ago • 25

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation

Paper • 2605.26844 • Published 16 days ago • 26

SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks

Paper • 2605.31433 • Published 13 days ago • 28

dMoE: dLLMs with Learnable Block Experts

Paper • 2605.30876 • Published 13 days ago • 36