On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs

Documenti analoghi

• Echo Chamber: RL Post-training Amplifies Behaviors Learned in Pretraining
  di: Zhao, Rosie, et al.
  Pubblicazione: (2025)
• Game-RL: Synthesizing Multimodal Verifiable Game Data to Boost VLMs' General Reasoning
  di: Tong, Jingqi, et al.
  Pubblicazione: (2025)
• Thought-Like-Pro: Enhancing Reasoning of Large Language Models through Self-Driven Prolog-based Chain-of-Thought
  di: Tan, Xiaoyu, et al.
  Pubblicazione: (2024)
• An Investigation of Neuron Activation as a Unified Lens to Explain Chain-of-Thought Eliciting Arithmetic Reasoning of LLMs
  di: Rai, Daking, et al.
  Pubblicazione: (2024)
• D-COT: Disciplined Chain-of-Thought Learning for Efficient Reasoning in Small Language Models
  di: Ubukata, Shunsuke
  Pubblicazione: (2026)