快速提取音视频内容，整理成一份结构化的markdown笔记

Ola: Pushing the Frontiers of Omni-Modal Language Model

Grounded SAM 2: Ground and Track Anything in Videos with Grounding DINO, Florence-2 and SAM 2

Fully open reproduction of DeepSeek-R1

Tarsier -- a family of large-scale video-language models, which is designed to generate high-quality video descriptions , together with good capability of general video understanding.

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

PyTorch code and models for the DINOv2 self-supervised learning method.

A minimal codebase for finetuning large multimodal models, supporting llava-1.5/1.6, llava-interleave, llava-next-video, llava-onevision, llama-3.2-vision, qwen-vl, qwen2-vl, phi3-v etc.

TransNet V2: Shot Boundary Detection Neural Network

[NeurIPS'23 Oral] Visual Instruction Tuning (LLaVA) built towards GPT-4V level capabilities and beyond.

Official inference repo for FLUX.1 models

An official implementation for "CLIP4Clip: An Empirical Study of CLIP for End to End Video Clip Retrieval"

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

Use PEFT or Full-parameter to finetune 450+ LLMs (Qwen2.5, InternLM3, GLM4, Llama3.3, Mistral, Yi1.5, Baichuan2, DeepSeek-R1, ...) and 150+ MLLMs (Qwen2.5-VL, Qwen2-Audio, Llama3.2-Vision, Llava, I…

LLaVA-CoT, a visual language model capable of spontaneous, systematic reasoning

Inpaint anything using Segment Anything and inpainting models.

🔥🔥🔥Latest Papers, Codes and Datasets on Vid-LLMs.

Collection of AWESOME vision-language models for vision tasks

a state-of-the-art-level open visual language model | 多模态预训练模型

将微信读书划线同步到Notion

The easiest way to serve AI apps and models - Build Model Inference APIs, Job queues, LLM apps, Multi-model pipelines, and more!

PyTorch implementation of MAE https//arxiv.org/abs/2111.06377

We use MixedWM38, the mixed-type wafer defect pattern dataset for wafer defect pattern regcognition with visual transformers.

Bag of Visual Feature with Hamming Enbedding, Reranking

Unofficial PyTorch implementation of "Meta Pseudo Labels"

Code for "MultiGrain: a unified image embedding for classes and instances"

📈 目前最大的工业缺陷检测数据库及论文集 Constantly summarizing open source dataset and critical papers in the field of surface defect research which are of great importance.

使用 NextJS + Notion API 实现的，支持多种部署方案的静态博客，无需服务器、零门槛搭建网站，为Notion和所有创作者设计。 (A static blog built with NextJS and Notion API, supporting multiple deployment options. No server required, zero threshold t…