LASP-2: Rethinking Sequence Parallelism for Linear Attention and Its Hybrid Paper • 2502.07563 • Published 12 days ago • 23
UltraIF: Advancing Instruction Following from the Wild Paper • 2502.04153 • Published 17 days ago • 21
UltraIF: Advancing Instruction Following from the Wild Paper • 2502.04153 • Published 17 days ago • 21
view article Article Process Reinforcement through Implicit Rewards By ganqu and 1 other • Jan 3 • 24
RLAIF-V: Aligning MLLMs through Open-Source AI Feedback for Super GPT-4V Trustworthiness Paper • 2405.17220 • Published May 27, 2024 • 1
UltraMedical: Building Specialized Generalists in Biomedicine Paper • 2406.03949 • Published Jun 6, 2024