Achieving Gold-Medal-Level Olympiad Reasoning via Simple and Unified Scaling Paper • 2605.13301 • Published May 13 • 165
For-Value: Efficient Forward-Only Data Valuation for finetuning LLMs and VLMs Paper • 2508.10180 • Published Apr 25 • 19
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models Paper • 2512.02556 • Published Dec 2, 2025 • 270
Running Featured 1.38k FineWeb: decanting the web for the finest text data at scale 🍷 1.38k Explore and download the FineWeb web‑scale text dataset