InfiniteVL: Synergizing Linear and Sparse Attention for Highly-Efficient, Unlimited-Input Vision-Language Models Paper โข 2512.08829 โข Published 19 days ago โข 18
Flow-GRPO: Training Flow Matching Models via Online RL Paper โข 2505.05470 โข Published May 8 โข 86
Can 1B LLM Surpass 405B LLM? Rethinking Compute-Optimal Test-Time Scaling Paper โข 2502.06703 โข Published Feb 10 โข 153
Euclid: Supercharging Multimodal LLMs with Synthetic High-Fidelity Visual Descriptions Paper โข 2412.08737 โข Published Dec 11, 2024 โข 54