[CVPR 2025] DEIM: DETR with Improved Matching for Fast Convergence

YOLOE: Real-Time Seeing Anything

Code release for DynamicTanh (DyT)

No fortress, purely open ground. OpenManus is Coming.

[CVPR 2025] Fast3R: Towards 3D Reconstruction of 1000+ Images in One Forward Pass

具身智能入门指南 Embodied-AI-Guide

《动手学大模型Dive into LLMs》系列编程实践教程

Generalist YOLO: Towards Real-Time End-to-End Multi-Task Visual Language Models

Wan: Open and Advanced Large-Scale Video Generative Models

主要记录大语言大模型（LLMs） 算法（应用）工程师相关的知识及面试题

Solve Visual Understanding with Reinforced VLMs

DeepEP: an efficient expert-parallel communication library

YOLOv12: Attention-Centric Real-Time Object Detectors

xDiT: A Scalable Inference Engine for Diffusion Transformers (DiTs) with Massive Parallelism

A Flexible Framework for Experiencing Cutting-edge LLM Inference Optimizations

https://arxiv.org/abs/2302.11813

[IEEE TIP] TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenes

D-FINE: Redefine Regression Task of DETRs as Fine-grained Distribution Refinement [ICLR 2025 Spotlight]

Finetune Llama 3.3, DeepSeek-R1, Gemma 3 & Reasoning LLMs 2x faster with 70% less memory! 🦥

[T-PAMI] Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Driving

Official code repo for the O'Reilly Book - "Hands-On Large Language Models"

校招、秋招、春招、实习好项目，带你从零动手实现支持LLama2/3和Qwen2.5的大模型推理框架。

🔥🔥🔥 A collection of some awesome public CUDA, cuBLAS, cuDNN, CUTLASS, TensorRT, TensorRT-LLM, Triton, TVM, MLIR and High Performance Computing (HPC) projects.

[CVPR24] COTR: Compact Occupancy TRansformer for Vision-based 3D Occupancy Prediction

Qwen2.5-VL is the multimodal large language model series developed by Qwen team, Alibaba Cloud.

Frontier Multimodal Foundation Models for Image and Video Understanding

Awesome Chinese LLM: A curated list of Chinese Large Language Model 中文大语言模型数据集和模型资料汇总

整理开源的中文大语言模型，以规模较小、可私有化部署、训练成本较低的模型为主，包括底座模型，垂直领域微调及应用，数据集与教程等。