← Search

Joerg Liebelt

1 accepted papers

2026

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

ICML 2026poster

Reinforcement learning (RL) fine-tuning is now widely used to improve LLM reasoning, and recent work has begun extending it to vision-language models (VLMs). While RL-tuned VLMs can improve visual reasoning benchmark performance, they can still suffer from weak visual grounding, hallucinations, and …

Cited by 4SourceScholar