Mike "Iron" Kowalski

ironmike123's activity

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

upvoted 2 papers 6 days ago

On-Policy Parameter Update Direction Underlies Generalization in LLM Post-Training

Paper • 2609.36659 • Published Sep 29 • 77

RealCompanion: Benchmarking Human Understanding from Reasoning over Longitudinal Real-World Conversations

Paper • 2610.01780 • Published Oct 1 • 41

upvoted 4 papers about 1 month ago

Can Agents Design Libraries for Agents?

Paper • 2609.36730 • Published Sep 29 • 11

ROSS: Relearning from Self-Generated Rollouts through Selective Supervision

Paper • 2609.35954 • Published Sep 28 • 39

Beyond the Timeline: Augmenting Long-Video Memory with Grounded Entity Biographies

Paper • 2609.38155 • Published Sep 29 • 92

Scaling Properties of Same-Family On-Policy Distillation

Paper • 2609.32722 • Published Sep 26 • 159