A comprehensive survey on Internal Consistency and Self-Feedback in Large Language Models.

Dynamic 2D Gaussians: Geometrically accurate radiance fields for dynamic objects

A system for agentic LLM-powered data processing and ETL

Official code implementation of General OCR Theory: Towards OCR-2.0 via a Unified End-to-end Model

Implementation of paper 'Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models'

High accuracy RAG for answering questions from scientific documents with citations

GeoCalib: Learning Single-image Calibration with Geometric Optimization (ECCV 2024)

open-source multimodal large language model that can hear, talk while thinking. Featuring real-time end-to-end speech input and streaming audio output conversational capabilities.

A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.

Repository for Show-o, One Single Transformer to Unify Multimodal Understanding and Generation.

Clipora is a powerful toolkit for fine-tuning OpenCLIP models using Low Rank Adapters (LoRA).

MiniCPM-V 2.6: A GPT-4V Level MLLM for Single Image, Multi Image and Video on Your Phone

A tool to modify ONNX models in a visualization fashion, based on Netron and Flask.

A very simple news crawler with a funny name

Code for the paper "Visual Anagrams: Generating Multi-View Optical Illusions with Diffusion Models"

Code for *Eventfulness for Interactive Video Alignment*

Bring portraits to life!

Multi-lingual large voice generation model, providing inference, training and deployment full-stack ability.

Accepted as [NeurIPS 2024] Spotlight Presentation Paper

A tool to project equirectangular panorama into perspective images

code for "Diffusion Forcing: Next-token Prediction Meets Full-Sequence Diffusion"

A tool for compiling trained SKLearn models into other representations (such as SQL, Sympy or Excel formulas)

Local models support for Microsoft's graphrag using ollama (llama3, mistral, gemma2 phi3)- LLM & Embedding extraction

[NeurIPS 2024] Needle In A Multimodal Haystack (MM-NIAH): A comprehensive benchmark designed to systematically evaluate the capability of existing MLLMs to comprehend long multimodal documents.

[NeurIPS 2024] Depth Anything V2. A More Capable Foundation Model for Monocular Depth Estimation

Convert ONNX models to PyTorch.

Official Implementation of CVPR24 highligt paper: Matching Anything by Segmenting Anything

LLaVA-UHD: an LMM Perceiving Any Aspect Ratio and High-Resolution Images

Source code of paper "NVS-Solver: Video Diffusion Model as Zero-Shot Novel View Synthesizer"

[BMVC2021] The first image composition assessment dataset. Used in the paper "Image Composition Assessment with Saliency-augmented Multi-pattern Pooling". Useful for image composition assessment, i…