Eagle Family: Exploring Model Designs, Data Recipes and Training Strategies for Frontier-Class Multimodal LLMs

[EMNLP 2024 Industry Track] This is the official PyTorch implementation of "LLMC: Benchmarking Large Language Model Quantization with a Versatile Compression Toolkit".

[Fully open] [Encoder-free MLLM] Vision as LoRA

[NeurIPS 2024] This repo contains evaluation code for the paper "Are We on the Right Way for Evaluating Large Vision-Language Models"

The official code implementation of paper "Combining Similarity and Importance for Video Token Reduction on Large Visual Language Models"

CLIP-MoE: Mixture of Experts for CLIP

[AAAI 2025] HiRED strategically drops visual tokens in the image encoding stage to improve inference efficiency for High-Resolution Vision-Language Models (e.g., LLaVA-Next) under a fixed token budget.

A benchmark dataset and simple code examples for measuring the perception and reasoning of multi-sensor Vision Language models.

[CVPR'25] Antidote: A Unified Framework for Mitigating LVLM Hallucinations in Counterfactual Presupposition and Object Perception

Code for ICLR 2025 Paper: Visual Description Grounding Reduces Hallucinations and Boosts Reasoning in LVLMs

Code for USENIX Security 2024 paper: Moderating Illicit Online Image Promotion for Unsafe User Generated Content Games Using Large Vision-Language Models.

VisGraphVar: A Benchmark Generator for Assessing Variability in Graph Analysis Using Large Vision-Language Models

Novel approach that leverages LVLMs to efficiently generate high-quality synthetic VQA-NLE datasets.

A powerful Streamlit application that allows users to analyze and interact with YouTube video content through natural language questions.