MEND: RL For Flow Models via Proximal Velocity Matching Paper • 2610.05954 • Published 6 days ago • 3
Allspark: Weak to Strong Transfer via Alternating Chain of Thought Paper • 2609.32913 • Published 15 days ago • 4
Where Does Social Reasoning Come From? Capability Provenance in Language Models Paper • 2606.19625 • Published Jun 17
20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone Paper • 2605.11405 • Published May 13
ÜberWeb: Insights from Multilingual Curation for a 20-Trillion-Token Dataset Paper • 2602.15210 • Published Feb 25 • 1
The Finetuner's Fallacy: When to Pretrain with Your Finetuning Data Paper • 2603.16177 • Published Mar 21
DatBench: Discriminative, Faithful, and Efficient VLM Evaluations Paper • 2601.02316 • Published Jan 5 • 10
BeyondWeb: Lessons from Scaling Synthetic Data for Trillion-scale Pretraining Paper • 2508.10975 • Published Aug 14, 2025 • 60
Recite, Reconstruct, Recollect: Memorization in LMs as a Multifaceted Phenomenon Paper • 2406.17746 • Published Jun 25, 2024
CalVerT: Augmenting Agents with Calibrated Verifier Telemetry Improves Action and Learning in Knowledge-Intensive Tasks Paper • 2606.21777 • Published Jun 19 • 5
No Hidden Prompts Needed! You Can Game AI Peer Review with Presentation-Only Revisions Paper • 2606.13044 • Published Jun 11 • 11