Stars
DiffusionOPD: A Unified Perspective of On-Policy Distillation in Diffusion Models
Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.6, DeepSeek-V4, GLM-5.1, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Gemma4, Llava, …
Official implementation of Tuna-2: Pixel Embeddings Beat Vision Encoders for Unified Understanding and Generation
Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe
StreamingVLM: Real-Time Understanding for Infinite Video Streams
《动手学大模型Dive into LLMs》系列编程实践教程
[ICLR 2026 Oral] FlashVID: Efficient Video Large Language Models via Training-free Tree-based Spatiotemporal Token Merging
[CVPR2025] BOLT: Boost Large Vision-Language Model Without Training for Long-form Video Understanding
Qlib is an AI-oriented Quant investment platform that aims to use AI tech to empower Quant Research, from exploring ideas to implementing productions. Qlib supports diverse ML modeling paradigms, i…
Towards Efficient Multimodal Large Language Models: A Survey on Token Compression
[CVPR 2025] Adaptive Keyframe Sampling for Long Video Understanding
One-for-All Multimodal Evaluation Toolkit Across Text, Image, Video, and Audio Tasks
[CVPR 2026] Divide, then Ground: Adapting Frame Selection to Query Types for Long-Form Video Understanding
[ICCV 2025] Implementation of the paper "Q-Frame: Query-aware Frame Selection and Multi-Resolution Adaptation for Video-LLMs"
Course projects and notes of undergraduate courses in NJUAI
Research and development (R&D) is crucial for the enhancement of industrial productivity, especially in the AI era, where the core aspects of R&D are mainly focused on data and models. We are commi…
Technical challenge for Creativa 77. Contains a brige ROS node, built in C++, that subscribes to the turtleX/Pose topic of turtlesim and republishes that info in a geometry_msgs/Pose2D type topic. …
基于SpringBoot + Vue的仓库管理系统、库存管理、进销存同、批次追溯管理、入库出库、安全库存预警 物品管理，申请记录，库房管理，入库记录，出库记录，采购计划，报表统计，耗材类别，出入库物品明细 制定申请物品->管理员审批制定采购计划->采购员采购->入库->出库
项目使用的是SSH框架，业务流程为：采购订单申请—>订单审核—>采购运输—>入库。 模块主要分为：基础维护模块（员工模块，商品模块，供应商模块，仓库模块，菜单模块，订单模块）、采购业务、审核业务、运输业务、入库业务 实现的功能：业务主线流程（采购订单申请—>订单审核—>采购运输—>入库）实现 权限系统的实现
这是一份入门AI/LLM大模型的逐步指南，包含教程和演示代码，带你从API走进本地大模型部署和微调，代码文件会提供Kaggle或Colab在线版本，即便没有显卡也可以进行学习。项目中还开设了一个小型的代码游乐场🎡，你可以尝试在里面实验一些有意思的AI脚本。同时，包含李宏毅 (HUNG-YI LEE）2024生成式人工智能导论课程的完整中文镜像作业。
NIFTI ROS Android App is a tablet app developed for the purpose of controlling and communicating with robot on the move. Right now, this app can receive and display laser scan data, map and video s…
面向开发者的 LLM 入门教程，吴恩达大模型系列课程中文版
ICCV2021/2019/2017 论文/代码/解读/直播合集，极市团队整理