Paddle Multimodal Integration and eXploration, supporting mainstream multi-modal tasks, including end-to-end large-scale multi-modal pretrain models and diffusion model toolbox. Equipped with high performance and flexibility.

Explore LLM model deployment based on AXera's AI chips, It provides OpenAI‑compatible APIs and supports AX620E, AX650 and AX637 series chips.

A minimalistic demo for image inference and video understanding using OpenCV with some popular open-source VLMs

A workshop for collections of multi-modal LLM examples, samples, reference architecture and demos on Amazon SageMaker.

Streamlit App Combining Vision, Language, and Audio AI Models

Multimodal Agentic GenAI Workflow – Seamlessly blends retrieval and generation for intelligent storytelling

QBBot: A human-like AI UI/UX Inspector using Local VLM (InternVL2) and LLMs to autonomously audit web flows, detect visual bugs, and generate professional QA reports.

Fine-tuning Vision-Language Models for autonomous driving VQA: custom i.i.d. DriveLM-nuScenes split, ~132k pseudo-labels generated by Qwen3 from nuScenes sensor priors (3D bounding boxes, LiDAR depth, tracking trajectories), and InternVL2-2B LoRA fine-tuning reaching a DriveLM score of 0.589. Master's thesis, CTU Prague 2026.

基于 vLLM 部署 InternVL2-8B 多模态大模型,提供 curl/OpenAI SDK/requests 三种调用示例