How this analysis was created: This summary and feature list are AI-generated from collected project material and can contain mistakes. Stars, license and language are imported from GitHub. Inclusion does not mean that we have tested or audited this project. Check the source documentation for any feature you depend on. Learn more on our About page.
CVPR'24 RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback
ICML 2024 Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"
ICML 2025 Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal Large Language Models'.
In Stage 1, the Keyword Extraction Prompt instructs ChatGPT to generate verbs, nouns, and adjectives (highlighted in brown) from the original caption. In Stage 2, the Caption Generation Prompt guides ChatGPT to generate a rewritten caption. By iteratively applying this prompt, multiple rewritten…
Aligning LMMs with Factually Augmented RLHF
The main features of llava-rlhf/llava-rlhf are: Alignment and RLHF, Hallucination Mitigation, Mitigation Methods, RLHF Frameworks.
Projects with overlapping indexed features include: rlhf-v/rlhf-v — [CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback. damo-nlp-sg/vcd — [CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive… 1zhou-wang/memvr — [ICML 2025] Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for… anonymousanoy/fohe — In Stage 1, the Keyword Extraction Prompt instructs ChatGPT to generate verbs, nouns, and adjectives (highlighted in… bradyfu/woodpecker — ✨✨Woodpecker: Hallucination Correction for Multimodal Large Language Models. billchan226/halc — [ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding".