LongR: Unleashing Long-Context Reasoning via Reinforcement Learning with Dense Utility Rewards Paper • 2602.05758 • Published 23 days ago • 11
GroundingPI: A Grounding Foundation Model towards Physical Intelligence with Visual Primitives Paper • 2609.39601 • Published Sep 30 • 95
GroundAnything: Reconciling Parallel Decoding with Precise Visual Grounding at Flash Speed Paper • 2609.39600 • Published Sep 30 • 34
SymDPO: Boosting In-Context Learning of Large Multimodal Models with Symbol Demonstration Direct Preference Optimization Paper • 2411.11909 • Published Nov 17, 2024 • 21
