#Vlm

Showing 60 of 102 repositories tagged #vlm, ranked by stars

huggingface
huggingface
transformers

๐Ÿค— Transformers: the model-definition framework for state-of-the-art machine learning models in text, vision, audio, and multimodal models, for both inference and training.

Score
100
โ˜… 162.4k โ‘‚ 33.9k โ€”
Python
sgl-project
sgl-project
sglang

SGLang is a high-performance serving framework for large language models and multimodal models.

Score
88
โ˜… 30.1k โ‘‚ 7.1k +17/day
Python
RunanywhereAI
RunanywhereAI
runanywhere-sdks

Production ready toolkit to run AI locally

Score
100
โ˜… 10.3k โ‘‚ 365 +2/day
C++
roboflow
roboflow
notebooks

A collection of tutorials on state-of-the-art computer vision models and techniques. Explore everything from foundational architectures like ResNet to cutting-edge models like RF-DETR, YOLO11, SAM 3, and Qwen3-VL.

Score
100
โ˜… 9.5k โ‘‚ 1.5k +8/day
Jupyter Notebook
yzhao062
yzhao062
anomaly-detection-resources

Anomaly detection related books, papers, videos, and toolboxes. Last update late 2025 for LLM and VLM works!

Score
75
โ˜… 9.3k โ‘‚ 1.8k +6/day
Python
qualcomm
qualcomm
GenieX

Run frontier LLMs and VLMs locally on Qualcomm devices across NPU, GPU, and CPU with a few lines of code

Score
100
โ˜… 8.2k โ‘‚ 1.0k +9/day
Rust
PaddlePaddle
PaddlePaddle
ERNIE

The official repository for ERNIE 4.5 and ERNIEKit โ€“ its industrial-grade development toolkit based on PaddlePaddle.

Score
25
โ˜… 7.7k โ‘‚ 1.4k +1/day
Python
StarTrail-org
StarTrail-org
PixelRAG

The end of web parsing. The beginning of scalable pixel-native search. link: https://pixelrag.ai/

Score
62
โ˜… 6.2k โ‘‚ 498 +360/day
Python
om-ai-lab
om-ai-lab
VLM-R1

Solve Visual Understanding with Reinforced VLMs

Score
50
โ˜… 6.0k โ‘‚ 383 โ€”
Python
OpenBMB
OpenBMB
UltraRAG

A Low-Code MCP Framework for Building Complex and Innovative RAG Pipelines

Score
38
โ˜… 5.6k โ‘‚ 434 +4/day
Python
changyeyu
changyeyu
LLM-RL-Visualized

๐ŸŒŸ100+ ๅŽŸๅˆ› LLM / RL ๅŽŸ็†ๅ›พ๐Ÿ“š๏ผŒใ€Šๅคงๆจกๅž‹็ฎ—ๆณ•ใ€‹ไฝœ่€…ๅทจ็Œฎ๏ผ๐Ÿ’ฅ๏ผˆ100+ LLM/RL Algorithm Maps ๏ผ‰

Score
100
โ˜… 4.6k โ‘‚ 442 +19/day
Python
joanrod
joanrod
star-vector

StarVector is a foundation model for SVG generation that transforms vectorization into a code generation task. Using a vision-language modeling architecture, StarVector processes both visual and textual inputs to produce high-quality SVG code with remarkable precision.

Score
86
โ˜… 4.5k โ‘‚ 253 +3/day
Python
Hunyuan-PromptEnhancer
Hunyuan-PromptEnhancer
PromptEnhancer

[CVPR 2026] PromptEnhancer is a prompt-rewriting tool, refining prompts into clearer, structured versions for better image generation.

Score
98
โ˜… 3.7k โ‘‚ 324 +1/day
Python
MiniMax-AI
MiniMax-AI
MiniMax-01

The official repo of MiniMax-Text-01 and MiniMax-VL-01, large-language-model & vision-language-model based on Linear Attention

Score
66
โ˜… 3.4k โ‘‚ 330 โ€”
Python
QiuYannnn
QiuYannnn
Local-File-Organizer

An AI-powered file management tool that ensures privacy by organizing local texts, images. Using Llama3.2 3B and Llava v1.6 models with the Nexa SDK, it intuitively scans, restructures, and organizes files for quick, seamless access and easy retrieval.

Score
63
โ˜… 3.3k โ‘‚ 328 +4/day
Python
SkyworkAI
SkyworkAI
Skywork-R1V

Skywork-R1V is an advanced multimodal AI model series developed by Skywork AI, specializing in vision-language reasoning.

Score
85
โ˜… 3.2k โ‘‚ 281 +1/day
Python
modelscope
modelscope
evalscope

A streamlined and customizable framework for efficient large model (LLM, VLM, AIGC) evaluation and performance benchmarking.

Score
97
โ˜… 3.1k โ‘‚ 419 +9/day
Python
xlang-ai
xlang-ai
OSWorld

[NeurIPS 2024] OSWorld: Benchmarking Multimodal Agents for Open-Ended Tasks in Real Computer Environments

Score
100
โ˜… 3.0k โ‘‚ 494 +1/day
Python
SharpAI
SharpAI
DeepCamera

Open-Source AI Camera Skills Platform, AI NVR & CCTV Surveillance. Local VLM video analysis with Qwen, DeepSeek, SmolVLM, LLaVA, YOLO26. LLM-powered agentic security camera agent โ€” watches, understands, remembers & guards your home via Telegram, Discord or Slack. Pluggable AI skills. OpenAI, Google, Anthropic or local AI. Runs on Mac Mini & AI PC.

Score
95
โ˜… 2.9k โ‘‚ 456 +11/day
JavaScript
om-ai-lab
om-ai-lab
OmAgent

[EMNLP-2024] Build multimodal language agents for fast prototype and production

Score
55
โ˜… 2.7k โ‘‚ 291 โ€”
Python
BAAI-Agents
BAAI-Agents
Cradle

The Cradle framework is a first attempt at General Computer Control (GCC). Cradle supports agents to ace any computer task by enabling strong reasoning abilities, self-improvment, and skill curation, in a standardized general environment with minimal requirements.

Score
52
โ˜… 2.5k โ‘‚ 265 +4/day
Python
DanOps-1
DanOps-1
Gpt-Agreement-Payment

ChatGPT Plus/Team/Pro ่ฎข้˜…ๅ่ฎฎ็ซฏๅˆฐ็ซฏ้‡ๆ”พๅทฅๅ…ท้›† ยท hCaptcha ่ง†่ง‰ๆฑ‚่งฃๅ™จ ยท ๅๆฌบ่ฏˆๆœบๅˆถๅฎž่ฏ็ ”็ฉถ / End-to-end protocol replay toolkit for ChatGPT Plus/Team/Pro subscription with from-scratch hCaptcha solver and empirical anti-fraud research

Score
91
โ˜… 2.1k โ‘‚ 9 +6/day
Python
llmsresearch
llmsresearch
paperbanana

Open source implementation and extension of Google Researchโ€™s PaperBanana for automated academic figures, diagrams, and research visuals, expanded to new domains like slide generation.

Score
94
โ˜… 2.1k โ‘‚ 302 +5/day
Python
CryptoAILab
CryptoAILab
Awesome-LM-SSP

A reading list for large models safety, security, and privacy (including Awesome LLM Security, Safety, etc.).

Score
100
โ˜… 2.0k โ‘‚ 149 +5/day
coderonion
coderonion
awesome-yolo-object-detection

๐Ÿš€๐Ÿš€๐Ÿš€ A collection of some awesome public YOLO object detection series projects and the related object detection datasets.

Score
51
โ˜… 1.8k โ‘‚ 235 +2/day
NVIDIA-AI-Blueprints
NVIDIA-AI-Blueprints
video-search-and-summarization

The NVIDIA VSS Blueprint is a suite of reference architectures for building GPU-accelerated vision agents and AI-powered video analytics applications.

Score
92
โ˜… 1.7k โ‘‚ 345 +4/day
C++
software-mansion
software-mansion
react-native-executorch

Declarative way to run AI models in React Native on device, powered by ExecuTorch.

Score
90
โ˜… 1.6k โ‘‚ 84 +8/day
C++
lightseekorg
lightseekorg
tokenspeed

TokenSpeed is a speed-of-light LLM inference engine.

Score
89
โ˜… 1.6k โ‘‚ 189 +1/day
Python
yueliu1999
yueliu1999
Awesome-Jailbreak-on-LLMs

Awesome-Jailbreak-on-LLMs is a collection of state-of-the-art, novel, exciting jailbreak methods on LLMs. It contains papers, codes, datasets, evaluations, and analyses.

Score
0
โ˜… 1.5k โ‘‚ 118 +11/day
zapdos-labs
zapdos-labs
unblink

Camera monitoring with VLM

Score
80
โ˜… 1.4k โ‘‚ 170 +1/day
Go
Tencent
Tencent
AngelSlim

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

Score
88
โ˜… 1.4k โ‘‚ 156 +29/day
Python
BAAI-DCAI
BAAI-DCAI
Bunny

A family of lightweight multimodal models.

Score
43
โ˜… 1.1k โ‘‚ 76 โ€”
Python
candle-org
candle-org
mindnlp

MindSpore + ๐Ÿค—Huggingface: Run any Transformers/Diffusers model on MindSpore with seamless compatibility and acceleration.

Score
12
โ˜… 919 โ‘‚ 270 โ€”
Python
Skythinker616
Skythinker616
gpt-assistant-android

ใ€ๆ–ฐๅขžๆ™บ่ƒฝไฝ“ๆจกๅผใ€‘ๅฎ‰ๅ“็ซฏๅ…จๅœบๆ™ฏGPTๅŠฉๆ‰‹๏ผŒๅฏ็”จ้Ÿณ้‡้”ฎๅ”ค่ตทๅนถ่ฟ›่กŒ่ฏญ้Ÿณไบคๆต๏ผŒๆ”ฏๆŒ่”็ฝ‘ใ€ๆ‹็…งใ€ๆจกๆฟใ€้™„ไปถ่งฃๆžใ€ๆ™บ่ƒฝไฝ“ๆจกๅผ็ญ‰ | GPT assistant for Android, activated via volume keys for voice interaction, supporting features such as networking, taking photos, templates, parsing PDF and Office documents, and agent mode.

Score
80
โ˜… 886 โ‘‚ 124 โ€”
Java
zubair-irshad
zubair-irshad
Awesome-Robotics-3D

A curated list of 3D Vision papers relating to Robotics domain in the era of large models i.e. LLMs/VLMs, inspired by awesome-computer-vision, including papers, codes, and related websites

Score
65
โ˜… 815 โ‘‚ 42 โ€”
coderonion
coderonion
awesome-llm-and-aigc

๐Ÿš€๐Ÿš€๐Ÿš€A collection of some awesome public projects about Large Language Model(LLM), Vision Language Model(VLM), Vision Language Action(VLA), AI Generated Content(AIGC), the related Datasets and Applications.

Score
40
โ˜… 808 โ‘‚ 75 โ€”
OpenDataBox
OpenDataBox
awesome-data-llm

Official Repository of "LLM ร— DATA" Survey Paper

Score
82
โ˜… 802 โ‘‚ 70 +3/day
OpenVGLab
OpenVGLab
OmniLottie

[CVPR 2026๐Ÿ”ฅ] ๐Ÿง‘โ€๐ŸŽจ OmniLottie, an open-sourced multi-modal instructed vector animation generator that produces Lottie JSONs.

Score
74
โ˜… 721 โ‘‚ 37 +4/day
Python
MigoXLab
MigoXLab
dingo

Dingo: A Comprehensive AI Data, Model and Application Quality Evaluation Tool

Score
80
โ˜… 720 โ‘‚ 74 +1/day
Python
Purewhiter
Purewhiter
mobilegym

MobileGym: A Verifiable and Highly Parallel Simulation Platform for Mobile GUI Agent Research ยท ๆต่งˆๅ™จ้‡Œ่ฟ่กŒ็š„ๅฎ‰ๅ“ๆจกๆ‹Ÿๅ™จ ยท Browser-hosted Android Simulator ยท Verifiable Evaluation ยท Scalable Online RL Training

Score
60
โ˜… 712 โ‘‚ 111 +4/day
Python
NVIDIA-NeMo
NVIDIA-NeMo
Automodel

๐Ÿš€ Pytorch Distributed native training library for LLMs/VLMs with OOTB Hugging Face support

Score
83
โ˜… 693 โ‘‚ 208 +3/day
Python
taco-group
taco-group
SparkVSR

[ECCV 2026] SparkVSR: Interactive Video Super-Resolution via Sparse Keyframe Propagation

Score
78
โ˜… 684 โ‘‚ 73 +1/day
Python
TIGER-AI-Lab
TIGER-AI-Lab
VLM2Vec

This repo contains the code for "VLM2Vec" [ICLR 2025], "VLM2Vec-V2 [TMLR 2026]", and "MMEB-V3"

Score
77
โ˜… 663 โ‘‚ 60 โ€”
Python
niuzaisheng
niuzaisheng
ScreenAgent

ScreenAgent: A Computer Control Agent Driven by Visual Language Large Model (IJCAI-24)

Score
35
โ˜… 603 โ‘‚ 67 +1/day
Python
gokayfem
gokayfem
ComfyUI_VLM_nodes

Custom ComfyUI nodes for Vision Language Models, Large Language Models, Image to Music, Text to Music, Consistent and Random Creative Prompt Generation

Score
60
โ˜… 576 โ‘‚ 58 โ€”
Python
Flame-Code-VLM
Flame-Code-VLM
Flame-Code-VLM

Flame is an open-source multimodal AI system designed to translate UI design mockups into high-quality React code. It leverages vision-language modeling, automated data synthesis, and structured training workflows to bridge the gap between design and front-end development.

Score
100
โ˜… 560 โ‘‚ 48 โ€”
Python
vlm-run
vlm-run
vlmrun-hub

A hub for various industry-specific schemas to be used with VLMs.

Score
60
โ˜… 551 โ‘‚ 24 โ€”
Python
awwaiid
awwaiid
ghostwriter

Use the reMarkable2 as an interface to vision-LLMs (ChatGPT, Claude, Gemini). Ghost in the machine!

Score
68
โ˜… 536 โ‘‚ 30 +15/day
Rust
RobotecAI
RobotecAI
rai

RAI is a vendor agnostic agentic framework for Physical AI robotics, utilizing ROS 2 tools to perform complex actions, defined scenarios, free interface execution, log summaries, voice interaction and more.

Score
75
โ˜… 534 โ‘‚ 71 +1/day
Python
Fabric-Project
Fabric-Project
Fabric

Node Creative Coding / 3D / Image Processing tool inspired by Quartz Composer

Score
40
โ˜… 528 โ‘‚ 26 โ€”
Swift
Core-Mate
Core-Mate
OpenGUI

OpenGUI is an Android GUI agent framework for phone-use AI that can see, plan, and operate real mobile apps through the GUI.

Score
67
โ˜… 527 โ‘‚ 19 +127/day
Kotlin
hybridgroup
hybridgroup
yzma

Go with your own intelligence - Go applications that directly integrate llama.cpp for local inference using hardware acceleration.

Score
0
โ˜… 512 โ‘‚ 18 +1/day
Go
coderonion
coderonion
awesome-cuda-and-hpc

๐Ÿš€๐Ÿš€๐Ÿš€ This repository lists some awesome public CUDA, cuda-python, cuBLAS, cuDNN, CUTLASS, TensorRT, TensorRT-LLM, Triton, TVM, MLIR, PTX and High Performance Computing (HPC) projects.

Score
31
โ˜… 495 โ‘‚ 47 +2/day
redai-infra
redai-infra
Relax

An Asynchronous Reinforcement Learning Engine for Omni-Modal Post-Training at Scale

Score
72
โ˜… 464 โ‘‚ 58 +7/day
Python
worldbench
worldbench
awesome-vla-for-ad

๐ŸŒ Vision-Language-Action Models for Autonomous Driving: Past, Present, and Future

Score
71
โ˜… 439 โ‘‚ 39 +3/day
HTML
opendilab
opendilab
LightRFT

LightRFT: Light, Efficient, Omni-modal & Reward-model Driven Reinforcement Fine-Tuning Framework

Score
58
โ˜… 401 โ‘‚ 11 +9/day
Python
eggbrid2
eggbrid2
mobileClaw

Open Android AI agent runtime for phone control, app automation, VLM screen reading, skill routing, mini apps, and Mihomo VPN workflows.

Score
20
โ˜… 401 โ‘‚ 17 +3/day
Kotlin
Aident-AI
Aident-AI
open-cuak

Reliable Automation Agents at Scale

Score
0
โ˜… 391 โ‘‚ 32 โ€”
TypeScript
Hon-Wong
Hon-Wong
VoRA

[Fully open] [Encoder-free MLLM] Vision as LoRA

Score
26
โ˜… 387 โ‘‚ 30 โ€”
Python
Wakals
Wakals
CoVT

Official repo of "Chain-of-Visual-Thought: Teaching VLMs to See and Think Better with Continuous Visual Tokens"

Score
70
โ˜… 374 โ‘‚ 20 โ€”
Python
Related Topics
#llm#qwen#multimodal#ai#deepseek#reinforcement-learning#computer-vision#agent#llama#deep-learning#machine-learning#large-language-models

ยฉ 2026 GitRepoTrend ยท GitHub repositories by topic ยท Updated weekly