Image de couverture de livre

Understanding and Mitigating Toxicity in Image-Text Pretraining Datasets: A Case Study on LLaVA

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Kanjula, Karthik Reddy, Guthikonda, Surya, Alam, Nahid, Islam, Shayekh Bin
Format:	Preprint
Publié:	2025
Sujets:	Computer Vision and Pattern Recognition
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

Spatial Reasoning is Not a Free Lunch: A Controlled Study on LLaVA
par: Alam, Nahid, et autres
Publié: (2026)

TG-LLaVA: Text Guided LLaVA via Learnable Latent Embeddings
par: Yan, Dawei, et autres
Publié: (2024)

LLaVA-MoD: Making LLaVA Tiny via MoE Knowledge Distillation
par: Shu, Fangxun, et autres
Publié: (2024)

Enhance Image-to-Image Generation with LLaVA-generated Prompts
par: Ding, Zhicheng, et autres
Publié: (2024)

Sa2VA: Marrying SAM2 with LLaVA for Dense Grounded Understanding of Images and Videos
par: Yuan, Haobo, et autres
Publié: (2025)

LLaVA-RE: Binary Image-Text Relevancy Evaluation with Multimodal Large Language Model
par: Sun, Tao, et autres
Publié: (2025)

OMG-LLaVA: Bridging Image-level, Object-level, Pixel-level Reasoning and Understanding
par: Zhang, Tao, et autres
Publié: (2024)

Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models
par: Malik, Hashmat Shadab, et autres
Publié: (2025)

Video-LLaVA: Learning United Visual Representation by Alignment Before Projection
par: Lin, Bin, et autres
Publié: (2023)

LLaVA-MLB: Mitigating and Leveraging Attention Bias for Training-Free Video LLMs
par: Shen, Leqi, et autres
Publié: (2025)

TC-LLaVA: Rethinking the Transfer from Image to Video Understanding with Temporal Considerations
par: Gao, Mingze, et autres
Publié: (2024)

Cosmos-LLaVA: Chatting with the Visual Cosmos-LLaVA: Görselle Sohbet Etmek
par: Zeer, Ahmed, et autres
Publié: (2024)

Behind Maya: Building a Multilingual Vision Language Model
par: Alam, Nahid, et autres
Publié: (2025)

Maya: An Instruction Finetuned Multilingual Multimodal Model
par: Alam, Nahid, et autres
Publié: (2024)

LLaVA-c: Continual Improved Visual Instruction Tuning
par: Liu, Wenzhuo, et autres
Publié: (2025)

MoE-LLaVA: Mixture of Experts for Large Vision-Language Models
par: Lin, Bin, et autres
Publié: (2024)

Safe-LLaVA: A Privacy-Preserving Vision-Language Dataset and Benchmark for Biometric Safety
par: Kim, Younggun, et autres
Publié: (2025)

PLLaVA : Parameter-free LLaVA Extension from Images to Videos for Video Dense Captioning
par: Xu, Lin, et autres
Publié: (2024)

LLaVA-Critic: Learning to Evaluate Multimodal Models
par: Xiong, Tianyi, et autres
Publié: (2024)

ViP-LLaVA: Making Large Multimodal Models Understand Arbitrary Visual Prompts
par: Cai, Mu, et autres
Publié: (2023)

R-LLaVA: Improving Med-VQA Understanding through Visual Region of Interest
par: Chen, Xupeng, et autres
Publié: (2024)

LLaVA-Octopus: Unlocking Instruction-Driven Adaptive Projector Fusion for Video Understanding
par: Sun, Boyuan, et autres
Publié: (2025)

LLaVA-SLT: Visual Language Tuning for Sign Language Translation
par: Liang, Han, et autres
Publié: (2024)

LLaVA-LE: Large Language-and-Vision Assistant for Lunar Exploration
par: Inal, Gokce, et autres
Publié: (2026)

MG-LLaVA: Towards Multi-Granularity Visual Instruction Tuning
par: Zhao, Xiangyu, et autres
Publié: (2024)

Why do LLaVA Vision-Language Models Reply to Images in English?
par: Hinck, Musashi, et autres
Publié: (2024)

LLaVA-OneVision-2: Towards Next-Generation Perceptual Intelligence
par: An, Xiang, et autres
Publié: (2026)

LLaVA-4D: Embedding SpatioTemporal Prompt into LMMs for 4D Scene Understanding
par: Zhou, Hanyu, et autres
Publié: (2025)

LLaVA-ST: A Multimodal Large Language Model for Fine-Grained Spatial-Temporal Understanding
par: Li, Hongyu, et autres
Publié: (2025)

LLaVA-Pose: Enhancing Human Pose and Action Understanding via Keypoint-Integrated Instruction Tuning
par: Zhang, Dewen, et autres
Publié: (2025)

LLaVA-Video: Video Instruction Tuning With Synthetic Data
par: Zhang, Yuanhan, et autres
Publié: (2024)

Surgical-LLaVA: Toward Surgical Scenario Understanding via Large Language and Vision Models
par: Jin, Juseong, et autres
Publié: (2024)

NOVO: Bridging LLaVA and SAM with Visual-only Prompts for Reasoning Segmentation
par: Yoon, Kyung-Yoon, et autres
Publié: (2025)

When LLaVA Meets Objects: Token Composition for Vision-Language-Models
par: Jahagirdar, Soumya, et autres
Publié: (2026)

LLaVA-SP: Enhancing Visual Representation with Visual Spatial Tokens for MLLMs
par: Lou, Haoran, et autres
Publié: (2025)

Beyond LLaVA-HD: Diving into High-Resolution Large Multimodal Models
par: Zhang, Yi-Fan, et autres
Publié: (2024)

LLaVA-MR: Large Language-and-Vision Assistant for Video Moment Retrieval
par: Lu, Weiheng, et autres
Publié: (2024)

ATP-LLaVA: Adaptive Token Pruning for Large Vision Language Models
par: Ye, Xubing, et autres
Publié: (2024)

LLaVA-KD: A Framework of Distilling Multimodal Large Language Models
par: Cai, Yuxuan, et autres
Publié: (2024)

LLaVA-FA: Learning Fourier Approximation for Compressing Large Multimodal Models
par: Zheng, Pengcheng, et autres
Publié: (2026)