-
GAIR
- Shanghai
-
13:14
(UTC +08:00) - https://rzfan525.github.io/
- @Vfrz525_
- https://www.zhihu.com/people/vfrz
- https://scholar.google.com/citations?user=mhot7AUAAAAJ&hl=en
Stars
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".
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)
DelinQu / SimplerEnv-OpenVLA
Forked from simpler-env/SimplerEnvEvaluating 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)
MichalZawalski / embodied-CoT
Forked from openvla/openvlaEmbodied 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.
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.
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
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 / openvla
Forked from TRI-ML/prismatic-vlmsOpenVLA: 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