[CoRL 2025] Real-world RL. Official implementation of "Robot Trains Robot: Automatic Real-World Policy Adaptation and Learning for Humanoids"

Reference PyTorch implementation and models for DINOv3

[NeurIPS 2025] InternScenes: A Large-scale Interactive Indoor Scene Dataset with Realistic Layouts.

Official code for "No time to train! Training-Free Reference-Based Instance Segmentation"

[CVPR 2025 Best Paper Award] VGGT: Visual Geometry Grounded Transformer

Perceive Anything: Recognize, Explain, Caption, and Segment Anything in Images and Videos

This repository contains the official implementation of "FastVLM: Efficient Vision Encoding for Vision Language Models" - CVPR 2025

[CVPR 2025] Official PyTorch implementation of "EdgeTAM: On-Device Track Anything Model"

[TPAMI] JointFormer: A Unified Framework with Joint Modeling for Video Object Segmentation

Official implementation of "S⁴M: Boosting Semi-Supervised Instance Segmentation with SAM" (ICCV 2025)

A Python module for extracting colors from images. Get a palette of any picture!

[ICLR 2025] SAMRefiner: Taming Segment Anything Model for Universal Mask Refinement

Advances in Multimodal Adaptation and Generalization: From Traditional Approaches to Foundation Models

DeepSeek-VL2: Mixture-of-Experts Vision-Language Models for Advanced Multimodal Understanding

[Lumina Embodied AI] 具身智能技术指南 Embodied-AI-Guide

Some thoughts about writing scientific papers

Minimal implementation of clipped objective Proximal Policy Optimization (PPO) in PyTorch

学术期刊配色推荐器

Cool Papers - Immersive Paper Discovery

Unseen Object Instance Segmentation with MSMFormer. (ICRA 2024 and RSS 2023)

Codes of paper "Unseen Object Amodal Instance Segmentation via Hierarchical Occlusion Modeling", ICRA 2022

Official PyTorch implementation of "Paralinguistics-Aware Speech-Empowered LLMs for Natural Conversation" (NeurIPS 2024)

[IROS 2025] NIDS-Net: A unified framework for novel instance detection and segmentation

Recommend new arxiv papers of your interest daily according to your Zotero libarary.

Modified Discrete Mean Curvature Measure (MDMCM) embedding scripts for the ACRONYM and GraspNet-1 Billion datasets.

Generative Grasping CNN from "Closing the Loop for Robotic Grasping: A Real-time, Generative Grasp Synthesis Approach" (RSS 2018)

中国科研常用LaTeX模板集