inference-time, RLHF/STaR, ResT - LMM

TLDR: Token-Level Detective Reward Model forLarge Vision Language Models 논문리뷰

jinuklee 2024. 10. 12. 18:17

https://arxiv.org/pdf/2410.04734

'inference-time, RLHF > STaR, ResT - LMM' 카테고리의 다른 글

RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback  (0) 2024.10.13
Enhancing visual-language modality alignment in large vision language models via self-improvement 논문리뷰  (0) 2024.10.13
FGAIF: Aligning Large Vision-Language Modelswith Fine-grained AI Feedback 논문리뷰  (1) 2024.10.12
GLOV: GUIDED LARGE LANGUAGE MODELS AS IMPLICIT OPTIMIZERS FOR VISION LANGUAGE MODELS 논문리뷰  (0) 2024.10.12
LMM의 DPO : Aligning Modalities in Vision Large Language Models via Preference Fine-tuning 논문리뷰  (0) 2024.10.09

'inference-time, RLHF/STaR, ResT - LMM'의 다른글

  • 현재글TLDR: Token-Level Detective Reward Model forLarge Vision Language Models 논문리뷰

관련글

티스토리툴바