The code to visualize colon-bench data and run evaluations of MLLMs on the benchmark.

[WACV 2026] FG-TRACER: Tracing Information Flow in Multimodal Large Language Models in Free-Form Generation

[NeurIPS 2025 Spotlight] InterMT: Multi-Turn Interleaved Preference Alignment with Human Feedback

State-of-the-art training-free MLLMs acceleration methods implementation

This repository implements a Multimodal Retrieval-Augmented Generation (RAG) pipeline for video data.

Mitigating Hallucination Potential in User Prompts Through AI-Guided Iterative Refinement

✨✨Latest Advances on Multimodal Large Language Models

[ICCVW 2025 (Oral)] Robust-LLaVA: On the Effectiveness of Large-Scale Robust Image Encoders for Multi-modal Large Language Models

This repo contains a companion app to the mllm-shap package developed during thesis at WUT. For details see mllm-shap documentation:

[ACL 2025] The code repository for "Mitigating Visual Forgetting via Take-along Visual Conditioning for Multi-modal Long CoT Reasoning" in PyTorch.

[CVPR 2026] Where MLLMs Attend and What They Rely On: Explaining Autoregressive Token Generation

an MLLM-based trust voice reasoning and retrieval system

MR-Pruner: Training-free Multi-resolution Visual Token Pruning for Multi-modal Large Language Models

This repository provides a hierarchical taxonomy of key paperson computer vision methods, surpassing flat lists with fine-grained subcategories that delineate emerging hotspots

From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation

This is the official repository for the paper titled "Unlocking Visual Tool Reasoning in Language Models via Perception Programs" accepted to CVPR 2026.

Explore the fundamentals of MLLMs and emblematic models. This repository covers practical techniques for preprocessing, prompt engineering, and building multimodal pipelines using LangChain and LangGraph, alongside future trends and challenges in AI.

Official repository of paper titled "FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysis".