emigmo

LLMs-from-scratch

Implementing a ChatGPT-like LLM in PyTorch from scratch, step by step

MinerU

A one-stop, open-source, high-quality data extraction tool, supports PDF/webpage/e-book extraction.一站式开源高质量数据提取工具，支持PDF/网页/多格式电子书提取。

sglang

SGLang is a fast serving framework for large language models and vision language models.

alphageometry

Monkey

【CVPR 2024 Highlight】Monkey (LMM): Image Resolution and Text Label Are Important Things for Large Multi-modal Models

Memary

The Open Source Memory Layer For Autonomous Agents

open-instruct

esm

openvla

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

ADAS

Automated Design of Agentic Systems

VITA

✨✨VITA: Towards Open-Source Interactive Omni Multimodal LLM

open_x_embodiment

Awesome-Robotics-3D

A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

SPPO

The official implementation of Self-Play Preference Optimization (SPPO)

rStar

3D-VLA

[ICML 2024] 3D-VLA: A 3D Vision-Language-Action Generative World Model

OPERA

[CVPR 2024 Highlight] OPERA: Alleviating Hallucination in Multi-Modal Large Language Models via Over-Trust Penalty and Retrospection-Allocation

VIINA

VIINA: Violent Incident Information from News Articles on the 2022 Russian Invasion of Ukraine

OmniCorpus

OmniCorpus: A Unified Multimodal Corpus of 10 Billion-Level Images Interleaved with Text

Super_MARIO

embodied-agents

Seamlessly integrate state-of-the-art transformer models into robotics stacks

crossformer

MCTS-DPO

This is the repository that contains the source code for the Self-Evaluation Guided MCTS for online DPO.

droid

Distributed Robot Interaction Dataset.

llm_debate

Code release for "Debating with More Persuasive LLMs Leads to More Truthful Answers"

PAI

[ECCV 2024] Paying More Attention to Image: A Training-Free Method for Alleviating Hallucination in LVLMs

Video-of-Thought

Codes for ICML 2024 paper: "Video-of-Thought: Step-by-Step Video Reasoning from Perception to Cognition"

Source-Bias

Code for "Neural Retrievers are Biased Towards LLM-Generated Content"

nesca-pytorch

PyTorch Implementation for the paper "Let Me Help You! Neuro-Symbolic Short-Context Action Anticipation" accepted to RA-L'24.

Dr_DPO

Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference Optimization