multimodal

Open-source Android AI using LiteRT-LM with hardware acceleration, cloud providers, memory, and voice.

Interactively browse multimodal tabular data

Language Quantized AutoEncoders

Multimodal fusion for heterogeneous biomedical data. NeurIPS 2024.

[ICCV 2025] The official code of the paper "Deciphering Cross-Modal Alignment in Large Vision-Language Models with Modality Integration Rate".

[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging

Multimodal Dataset and Benchmark for Multi-domain and Cross-domain Recommendation System

中文医学多模态大模型 Large Chinese Language-and-Vision Assistant for BioMedicine

Awesome Multimodal Agent

[LREC] MMChat: Multi-Modal Chat Dataset on Social Media

The open-source universal adapter for LLMs. Turn messy real-world data into clean, agent-ready context.

Efficient LLM inference on Slurm clusters.

Open-source, self-hosted multi-agent AI infrastructure for teams and apps with support for cloud and local models, tool integrations, workflows, and automation across business systems including Slack, ERPNext, Discord & Gmail.

[CVPR 2026 Highlight] WorldMM: Dynamic Multimodal Memory Agent for Long Video Reasoning

Data and code for paper "M3Exam: A Multilingual, Multimodal, Multilevel Benchmark for Examining Large Language Models"

Personal private Chatbot powered by Amazon Bedrock LLMs with a data analytics feature that provides isolated servereless compute on for data analysis. Chatbot features web-based intuitive user interface that can be accessed from any device (laptops, phones, etc.), handles multi-modal document upload and chat and maintains privacy of conversations.

[EMNLP 2025] Official implementation of "SensorLLM: Aligning Large Language Models with Motion Sensors for Human Activity Recognition"

[EMNLP'21] Visual News: Benchmark and Challenges in News Image Captioning

[Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics]: VisuoThink: Empowering LVLM Reasoning with Multimodal Tree Search

Implementation of MaMMUT, a simple vision-encoder text-decoder architecture for multimodal tasks from Google, in Pytorch