RationalRewards: Reasoning Rewards Scale Visual Generation Both Training and Test Time Paper • 2604.11626 • Published 4 days ago • 95
Pseudo-Unification: Entropy Probing Reveals Divergent Information Patterns in Unified Multimodal Models Paper • 2604.10949 • Published 4 days ago • 38
Rethinking Generalization in Reasoning SFT: A Conditional Analysis on Optimization, Data, and Model Capability Paper • 2604.06628 • Published 9 days ago • 310
An Efficient Heterogeneous Co-Design for Fine-Tuning on a Single GPU Paper • 2603.16428 • Published about 1 month ago • 51
NearID: Identity Representation Learning via Near-identity Distractors Paper • 2604.01973 • Published 15 days ago • 31
Reconstruction-Guided Slot Curriculum: Addressing Object Over-Fragmentation in Video Object-Centric Learning Paper • 2603.22758 • Published 24 days ago • 3
Out of Sight but Not Out of Mind: Hybrid Memory for Dynamic Video World Models Paper • 2603.25716 • Published 21 days ago • 154
VESPO: Variational Sequence-Level Soft Policy Optimization for Stable Off-Policy LLM Training Paper • 2602.10693 • Published Feb 11 • 220
From Blind Spots to Gains: Diagnostic-Driven Iterative Training for Large Multimodal Models Paper • 2602.22859 • Published Feb 26 • 151