A generative world for general-purpose robotics & embodied AI learning.

Liquid: Language Models are Scalable Multi-modal Generators

[CVPR'24] RLHF-V: Towards Trustworthy MLLMs via Behavior Alignment from Fine-grained Correctional Human Feedback

MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale

(NeurIPS 2024) Learning to Visual Question Answering, Asking and Assessment

Infinity ∞ : Scaling Bitwise AutoRegressive Modeling for High-Resolution Image Synthesis

(ECCV 2024) Empowering Multimodal Large Language Model as a Powerful Data Generator

Official repo for "VisionZip: Longer is Better but Not Necessary in Vision Language Models"

A taxonomy of industrial anomaly detection methods and datasets (updating).

LLMs build upon Evol Insturct: WizardLM, WizardCoder, WizardMath

Accelerating the development of large multimodal models (LMMs) with one-click evaluation module - lmms-eval.

【EMNLP 2024🔥】Video-LLaVA: Learning United Visual Representation by Alignment Before Projection

Train transformer language models with reinforcement learning.

LLaMA 2 implemented from scratch in PyTorch

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

[ECCV 2024] Bridging Different Language Models and Generative Vision Models for Text-to-Image Generation

[Arxiv] Towards Generic Anomaly Detection and Understanding: Large-scale Visual-linguistic Model (GPT-4V) Takes the Lead.

[CVPR 2023] Unofficial re-implementation of "WinCLIP: Zero-/Few-Shot Anomaly Classification and Segmentation".

[IEEE TII 2023] Collaborative Discrepancy Optimization for Reliable Image Anomaly Localization

Official implementation of "Segment Any Anomaly without Training via Hybrid Prompt Regularization (SAA+)".

[ECCV2024] The Official Implementation for ''AdaCLIP: Adapting CLIP with Hybrid Learnable Prompts for Zero-Shot Anomaly Detection''

Refine high-quality datasets and visual AI models

[CVPR'24 Oral] Official repository of Point Transformer V3 (PTv3)

ReKep: Spatio-Temporal Reasoning of Relational Keypoint Constraints for Robotic Manipulation

Using SparseInst as a Detector for Video Instance Segmentation

ICCV'2023 | CTVIS: Consistent Training for Online Video Instance Segmentation

DROID Policy Learning and Evaluation

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