Code for inference in decoder-only LLMs. The code is based on transformers.

This is the repo for ACL 2024 Finding paper - Unveiling the Spectrum of Data Contamination in Language Model: A Survey from Detection to Remediation

trending projects & awesome papers about data-centric llm studies.

The official implementation of the paper "What Matters in Transformers? Not All Attention is Needed".

Safety-J: Evaluating Safety with Critique

Survey Paper of foundation models for robotics

SAPIEN Manipulation Skill Framework, a GPU parallelized robotics simulator and benchmark

Fast and memory-efficient exact attention

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

Evaluating and reproducing real-world robot manipulation policies (e.g., RT-1, RT-1-X, Octo, and OpenVLA) in simulation under common setups (e.g., Google Robot, WidowX+Bridge)

Embodied Chain of Thought: A robotic policy that reason to solve the task.

List of language agents based on paper "Cognitive Architectures for Language Agents"

[Embodied-AI-Survey-2024] Paper list and projects for Embodied AI

A large-scale benchmark and learning environment.

An open-source platform for Visual AI.

Official Task Suite Implementation of ICML'23 Paper "VIMA: General Robot Manipulation with Multimodal Prompts"

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Octo is a transformer-based robot policy trained on a diverse mix of 800k robot trajectories.

LLaRA: Large Language and Robotics Assistant

Anole: An Open, Autoregressive and Native Multimodal Models for Interleaved Image-Text Generation

Suite of human-collected datasets and a multi-task continuous control benchmark for open vocabulary visuolinguomotor learning.

CALVIN - A benchmark for Language-Conditioned Policy Learning for Long-Horizon Robot Manipulation Tasks

Code for RoboFlamingo

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curatio…

Repository for Meta Chameleon, a mixed-modal early-fusion foundation model from FAIR.

OpenVLA: An open-source vision-language-action model for robotic manipulation.

The repository of the project "Fine-tuning Large Language Models with Sequential Instructions", code base comes from open-instruct and LAVIS