Петров Наталья

harperrobinson

AI & ML interests

Paper replication and lightweight experiments. Mostly focused on experiments.

Recent Activity

liked a model 4 days ago

EdwardoSunny/ttt-discover-v3-qwen3-8b-ac2-step32

liked a model 7 days ago

Jackrong/Qwen3.5-27B-Claude-4.6-Opus-Reasoning-Distilled

upvoted a paper 9 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

View all activity

Organizations

None yet

upvoted a paper 9 days ago

The Mirage of Optimizing Training Policies: Monotonic Inference Policies as the Real Objective for LLM Reinforcement Learning

Paper • 2606.29526 • Published 17 days ago • 163

upvoted a paper 22 days ago

Skill-MAS: Evolving Meta-Skill for Automatic Multi-Agent Systems

Paper • 2606.18837 • Published 28 days ago • 57

upvoted a paper 24 days ago

Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs

Paper • 2605.30611 • Published May 28 • 250

upvoted a paper 25 days ago

Looped World Models

Paper • 2606.18208 • Published 29 days ago • 480

upvoted 6 papers about 1 month ago

ABot-Earth 0.5: Generative 3D Earth Model

Paper • 2606.09967 • Published Jun 8 • 486

WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces

Paper • 2606.09426 • Published Jun 8 • 105

Retrospective Harness Optimization: Improving LLM Agents via Self-Preference over Trajectory Rollouts

Paper • 2606.05922 • Published Jun 4 • 70

Kwai Keye-VL-2.0 Technical Report

Paper • 2606.10651 • Published Jun 9 • 192

Agent Skills Should Go Beyond Text: The Case for Visual Skills

Paper • 2606.01414 • Published May 31 • 10

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

Paper • 2605.30888 • Published May 29 • 10