[NeurIPS 2024] CV-VAE: A Compatible Video VAE for Latent Generative Video Models

An elegant PyTorch deep reinforcement learning library.

本人的科研经验

Collect some World Models for Autonomous Driving papers.

Latent Motion Token as the Bridging Language for Robot Manipulation

A simple testbed for robotics manipulation policies

This is the official implementation of our ICML 2024 paper "MultiMax: Sparse and Multi-Modal Attention Learning""

[NeurIPS'24 Oral] HydraLoRA: An Asymmetric LoRA Architecture for Efficient Fine-Tuning

Advanced AI Explainability for computer vision. Support for CNNs, Vision Transformers, Classification, Object detection, Segmentation, Image similarity and more.

[NeurIPS 2024] Code for the paper "Diffusion of Thoughts: Chain-of-Thought Reasoning in Diffusion Language Models"

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

Official release of InternLM2.5 base and chat models. 1M context support

AnchorAttention: Improved attention for LLMs long-context training

[NeurIPS 2024] Efficient Multi-modal Models via Stage-wise Visual Context Compression

This is the official implementation of our paper "Video-RAG: Visually-aligned Retrieval-Augmented Long Video Comprehension"

The official repository for ManiSkill-ViTac2025

LAPA: Latent Action Pretraining from Videos

Official code for "QueST: Self-Supervised Skill Abstractions for Continuous Control" [NeurIPS 2024]

A comprehensive list of papers about Robot Manipulation, including papers, codes, and related websites.

用来记录一些碎片知识等，防止遗忘

[NeurIPS 2024 D&B] Point Cloud Matters: Rethinking the Impact of Different Observation Spaces on Robot Learning

RoboTwin: Dual-Arm Robot Benchmark with Generative Digital Twins

Autoregressive Policy for Robot Learning

Heterogeneous Pre-trained Transformer (HPT) as Scalable Policy Learner.

Awesome world models for manipulation

world modeling challenge for humanoid robots

The repository provides code for running inference with the SegmentAnything Model (SAM), links for downloading the trained model checkpoints, and example notebooks that show how to use the model.