MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization Paper • 2510.08540 • Published 24 days ago • 108 • 4
OmniAlign-V: Towards Enhanced Alignment of MLLMs with Human Preference Paper • 2502.18411 • Published Feb 25 • 74 • 2
MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning Paper • 2406.17770 • Published Jun 25, 2024 • 19 • 1