laion/1.7b-MixtureVitae-300BT-v1-decontaminated-16k-DPO-Tulu3-decontaminated-masked Text Generation • 2B • Updated 10 days ago • 27 • 1
LongStraw: Long-Context RL Beyond 2M Tokens under a Fixed GPU Budget Paper • 2607.14952 • Published 13 days ago • 203
Do All Visual Tokens Matter Equally? Object-Evidence Preserving Token Merging for Vision-Language Retrieval Paper • 2607.04605 • Published 23 days ago • 24
OmniOpt: Taxonomy, Geometry, and Benchmarking of Modern Optimizers Paper • 2607.04033 • Published 25 days ago • 76
Logit-Contribution Scoring Identifies Non-Literal Retrieval Heads Paper • 2607.01002 • Published 28 days ago • 19
MemLearner: Learning to Query Context memory for Video World Models Paper • 2606.31734 • Published 29 days ago • 28
Crafter: A Multi-Agent Harness for Editable Scientific Figure Generation from Diverse Inputs Paper • 2605.30611 • Published May 28 • 252
VibeThinker-3B: Exploring the Frontier of Verifiable Reasoning in Small Language Models Paper • 2606.16140 • Published Jun 15 • 124
Efficient Agentic Reinforcement Learning with On-Policy Intrinsic Knowledge Boundary Enhancement Paper • 2605.26952 • Published May 26 • 16