MMODELYST
People/Jiaming Han
PPL

Jiaming Han

Papers (3)
LC-ERD: Mining Latent Logic for Self-Evolving Reasoning via Consistency-Regulated Reward DecompositionBitLM: Unlocking Multi-Token Language Generation with Bitwise Continuous DiffusionAuto-Rubric as Reward: From Implicit Preferences to Explicit Multimodal Generative Criteria