multimodal

Code and models for the paper "2D3MF: Deepfake Detection using Multi Modal Middle Fusion"

Your intelligent ally for effortless information retrieval and seamless browsing across documents and the web.

RT-Pose: A 4D Radar Tensor-based 3D Human Pose Estimation and Localization Benchmark (ECCV 2024)

AI NourishBot is an AI-powered nutrition assistant that leverages advanced vision models and natural language processing to detect ingredients from food images, filter ingredients based on dietary restrictions, estimate calories, provide detailed nutrient analysis, and generate recipe suggestions.

A bug-free and improved implementation of LLaVA-UHD, based on the code from the official repo

[NAACL 2025] Towards Rationality in Language and Multimodal Agents: A Survey

Multimodal Chatbot with Amazon Bedrock Knowledge Bases Integration

Private, on-device AI desktop app — GGUF (llama.cpp) & MLX, with Qwen3.8's native reasoning-effort ladder wired in as a real control. Local coding agent, RAG knowledge base, Deep Research, vision and voice. 100% offline, no account, no telemetry. Windows & macOS.

Multimodal datasets.

[ACL 2021] Learning Relation Alignment for Calibrated Cross-modal Retrieval

Uni-ViGU: Towards Unified Video Generation and Understanding via A Diffusion-Based Video Generator

ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding

Rerun viewer with Gradio

ICLR 2026 | ChemEval: 4-level, 13-dimension, 62-task text/multimodal chemistry benchmark for evaluating LLMs and MLLMs.

Code for LifelongMemory: Leveraging LLMs for Answering Queries in Long-form Egocentric Videos

VOXRAD is a voice transcription application for radiologists leveraging locally deployed ASR and LLM models.

[MLHC 2025] ECG-Byte: A Tokenizer for End-to-End Generative Electrocardiogram Language Modeling

Panacea is a framework for building collaborative, intelligent multi agent AI systems. The framework provides a robust infrastructure for creating and managing multiple AI agents, and enables developers and organizations to build, deploy, and optimize AI agents that work well in dynamic, complex environments.

A multimodal RAG dashboard and interactive 3D Knowledge Graph. Process documents locally with Ollama or via Cloud APIs, powered by LightRAG, RAG-Anything and Neo4j.

AI company, product, and tool collection.