Latent Chain-of-Thought for Visual Reasoning

Chain-of-thought (CoT) reasoning is critical for improving the interpretability and reliability of Large Vision-Language Models (LVLMs). However, existing training algorithms such as SFT, PPO, and GRPO may not generalize well across unseen reasoning tasks and heavily rely on a biased reward model. To address this challenge, we reformulate reasoning in LVLMs as posterior inference and propose a scalable training algorithm based on amortized variational inference. By leveraging diversity-seeking reinforcement learning algorithms, we introduce a novel sparse reward function for token-level learning signals that encourage diverse, high-likelihood latent CoT, overcoming deterministic sampling limitations and avoiding reward hacking. Additionally, we implement a Bayesian inference-scaling strategy that replaces costly Best-of-N and Beam Search with a marginal likelihood to efficiently rank optimal rationales and answers. We empirically demonstrate that the proposed method enhances the state-of-the-art LVLMs on four reasoning benchmarks, in terms of effectiveness, generalization, and interpretability.

Authors

• Guohao Sun
• Hang Hua University of Rochester
• Jian Wang
• Jiebo Luo University of Rochester
• Sohail Dianat
• MAJID RABBANI
• Raghuveer Rao
• Zhiqiang Tao Rochester Institute of Technology

Keywords

No keywords are indexed for this paper.