lhanchao777 / LVLM-Hallucinations-Survey
This is the first released survey paper on hallucinations of large vision-language models (LVLMs). To keep track of this field and continuously update our survey, we maintain this repository of relevant references.
β46Updated 3 months ago
Related projects β
Alternatives and complementary repositories for LVLM-Hallucinations-Survey
- [ICML 2024] Official implementation for "HALC: Object Hallucination Reduction via Adaptive Focal-Contrast Decoding"β68Updated 5 months ago
- π up-to-date & curated list of awesome LMM hallucinations papers, methods & resources.β144Updated 7 months ago
- mPLUG-HalOwl: Multimodal Hallucination Evaluation and Mitigatingβ79Updated 9 months ago
- [ICLR 2024] Analyzing and Mitigating Object Hallucination in Large Vision-Language Modelsβ133Updated 6 months ago
- The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''β178Updated 7 months ago
- HallE-Control: Controlling Object Hallucination in LMMsβ28Updated 6 months ago
- [CVPR 2024 Highlight] Mitigating Object Hallucinations in Large Vision-Language Models through Visual Contrastive Decodingβ204Updated last month
- Official implementation of paper 'Look Twice Before You Answer: Memory-Space Visual Retracing for Hallucination Mitigation in Multimodal β¦β27Updated last week
- Papers about Hallucination in Multi-Modal Large Language Models (MLLMs)β55Updated 2 months ago
- β36Updated 2 months ago
- Less is More: Mitigating Multimodal Hallucination from an EOS Decision Perspective (ACL 2024)β31Updated last week
- MMICL, a state-of-the-art VLM with the in context learning ability from ICL, PKUβ40Updated last year
- β23Updated 4 months ago
- PyTorch Implementation of "Divide, Conquer and Combine: A Training-Free Framework for High-Resolution Image Perception in Multimodal Largβ¦β15Updated last month
- MoCLE (First MLLM with MoE for instruction customization and generalization!) (https://arxiv.org/abs/2312.12379)β29Updated 7 months ago
- Beyond Hallucinations: Enhancing LVLMs through Hallucination-Aware Direct Preference Optimizationβ64Updated 9 months ago
- [Preprint] TRACE: Temporal Grounding Video LLM via Casual Event Modelingβ36Updated this week
- CHAIR metric is a rule-based metric for evaluating object hallucination in caption generation.β22Updated last year
- This is the official repo for Debiasing Large Visual Language Models, including a Post-Hoc debias method and Visual Debias Decoding stratβ¦β71Updated 7 months ago
- [EMNLP'23] The official GitHub page for ''Evaluating Object Hallucination in Large Vision-Language Models''β72Updated 7 months ago
- [EMNLP 2024 Findings] The official PyTorch implementation of EchoSight: Advancing Visual-Language Models with Wiki Knowledge.β34Updated 2 weeks ago
- [NeurIPS 2023]DDCoT: Duty-Distinct Chain-of-Thought Prompting for Multimodal Reasoning in Language Modelsβ32Updated 7 months ago
- [NeurIPS 2024] Calibrated Self-Rewarding Vision Language Modelsβ42Updated 4 months ago
- [ICLR 2023] This is the code repo for our ICLRβ23 paper "Universal Vision-Language Dense Retrieval: Learning A Unified Representation Spaβ¦β43Updated 4 months ago
- [EMNLP 2024] mDPO: Conditional Preference Optimization for Multimodal Large Language Models.β22Updated 3 weeks ago
- This repository contains the code for SFT, RLHF, and DPO, designed for vision-based LLMs, including the LLaVA models and the LLaMA-3.2-viβ¦β79Updated 3 weeks ago
- HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data (Accepted by CVPR 2024)β41Updated 3 months ago
- β11Updated this week
- VoCoT: Unleashing Visually Grounded Multi-Step Reasoning in Large Multi-Modal Modelsβ27Updated 3 months ago
- M-HalDetect Dataset Releaseβ19Updated last year