From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix Paper • 2609.01572 • Published 9 days ago • 35
Running 44 T-Search: an open agentic retriever 🔎 44 Open agentic retriever for hard multi-step search
Trust-Region Behavior Blending for On-Policy Distillation Paper • 2605.31159 • Published May 29 • 69
Kandinsky 5.0: A Family of Foundation Models for Image and Video Generation Paper • 2511.14993 • Published Nov 19, 2025 • 236
Analyze Feature Flow to Enhance Interpretation and Steering in Language Models Paper • 2502.03032 • Published Feb 5, 2025 • 59
The Differences Between Direct Alignment Algorithms are a Blur Paper • 2502.01237 • Published Feb 3, 2025 • 113