[ICCVW 2025] LLaVA-MORE: A Comparative Study of LLMs and Visual Backbones for Enhanced Visual Instruction Tuning
[ICLR 2026] Official implementation of the paper "Map the Flow: Revealing Hidden Pathways of Information in VideoLLMs"
[IEEE T-BIOM] FaceXBench: Evaluating Multimodal LLMs on Face Understanding
The Official Code Repo for EgoOrientBench [CVPR25]
The official repo of our work "Pensieve: Retrospect-then-Compare mitigates Visual Hallucination"
Vision-Zephyr: a multimodal LLM for Visual Commonsense Reasoning—CLIP-ViT + Zephyr-7B with visual prompting; code, training scripts, and VCR evaluation.
Official repository of paper titled "FPBench: A Comprehensive Benchmark of Multimodal Large Language Models for Fingerprint Analysis".
Multimodal LLMs see sentiment better through description than by direct classification. 95.8% F1 on PerceptSent, beating CNN and Transformer baselines by up to 15 points. 72 checkpoints and every results published on the Hugging Face.
This is a code repository for a Master's Thesis in Machine Learning with the title: "Machine Teaching for Explainable AI in Industry: A Novel Approach with Time Series Classifiers"
Dataset annotations and evaluation code for our sensational image detection dataset, Sens-VisualNews, released as part of our paper "Sens-VisualNews: A Benchmark Dataset for Sensational Image Detection"
Can Multimodal LLMs ‘See’ Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos
[NeurIPS 2026] EDMA: Entropy-Driven Multimodal Answering
To associate your repository with the multimodal-llms topic, visit your repo's landing page and select "manage topics."