[CVPR 2024 Best paper award candidate] EGTR: Extracting Graph from Transformer for Scene Graph Generation

[CVPR 2024 Oral] InternVL Family: A Pioneering Open-Source Alternative to GPT-4V. 接近GPT-4V表现的可商用开源多模态对话模型

Code release for CVPR 2024 paper LEOD: Label-Efficient Object Detection for Event Cameras

[CVPR 2024 Highlight] OpenESS: Event-Based Semantic Scene Understanding with Open Vocabularies

Official implementation of Lookahead Exploration with Neural Radiance Representation for Continuous Vision-Language Navigation (CVPR'24 Highlight).

[CVPR'2024 Highlight] Official PyTorch implementation of the paper "VTimeLLM: Empower LLM to Grasp Video Moments".

[CVPR' 2024] Contrasting Intra-Modal and Ranking Cross-Modal Hard Negatives to Enhance Visio-Linguistic Fine-grained Understanding

Open-source framework for uncertainty and deep learning models in PyTorch 🌱

[CVPR 2024] Official PyTorch Implementation for Adam

[CVPR 2024 Oral] Rethinking Inductive Biases for Surface Normal Estimation

Codes and Data for ACL 2024 Paper "Faithful Logical Reasoning via Symbolic Chain-of-Thought".

Neo4j graph construction from unstructured data using LLMs

A knowledge graph RAG app using LangChain and Neo4j.

A voice-enabled chatbot application built using of 🦜️🔗 LangChain, text-to-speech, and speech-to-text models from 🤗 Hugging Face, and 🍱 BentoML.

Implementation of Slot Attention from GoogleAI

We introduced a new model designed for the Code generation task. Its test accuracy on the HumanEval base dataset surpasses that of GPT-4 Turbo (April 2024) and GPT-4o.

Large Action Model framework to develop AI Web Agents

Code for the paper 'Grokked Transformers are Implicit Reasoners: A Mechanistic Journey to the Edge of Generalization'

The first open source Large Action Model generalist Artificial Narrow Intelligence that controls completely human user interfaces by only using natural language. PyWinAssistant utilizes Visualizati…

33B Chinese LLM, DPO QLORA, 100K context, AirLLM 70B inference with single 4GB GPU

Official implementation for "Multimodal Chain-of-Thought Reasoning in Language Models" (stay tuned and more will be updated)

Emote Portrait Alive: Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions

STaRK: Benchmarking LLM Retrieval on Textual and Relational Knowledge Bases (https://stark.stanford.edu/)

🐚 OpenDevin: Code Less, Make More

Official implementation for the paper: "Code Generation with AlphaCodium: From Prompt Engineering to Flow Engineering""

Create Customized Software using Natural Language Idea (through LLM-powered Multi-Agent Collaboration)

Chat with NeRF enables users to interact with a NeRF model by typing in natural language.