MM-LIMA: Less Is More for Alignment in Multi-Modal Datasets

Documenti analoghi

• First SFT, Second RL, Third UPT: Continual Improving Multi-Modal LLM Reasoning via Unsupervised Post-Training
  di: Wei, Lai, et al.
  Pubblicazione: (2025)
• Improved Iterative Refinement for Chart-to-Code Generation via Structured Instruction
  di: Xu, Chengzhi, et al.
  Pubblicazione: (2025)
• Advancing Multimodal Reasoning via Reinforcement Learning with Cold Start
  di: Wei, Lai, et al.
  Pubblicazione: (2025)
• More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
  di: Liu, Chengzhi, et al.
  Pubblicazione: (2025)
• MM-R5: MultiModal Reasoning-Enhanced ReRanker via Reinforcement Learning for Document Retrieval
  di: Xu, Mingjun, et al.
  Pubblicazione: (2025)