AI Model2024
A research codebase and model family for vision–language models that experiments with data‑centric post‑training strategies and long‑context multimodal reasoning. Includes model reports, released research weights (non‑commercial), grounding tools (LocateAnything) and integrations for inference/optimization.
AI Infra2024
Drives UI automation from screenshots alone: describe steps in natural language and a vision model acts on what it sees, no DOM selectors. One API spans web, Android, iOS, HarmonyOS and desktop; plugs into Playwright/Vitest or runs autonomously.
AI Image2024
Turns a UI screenshot into structured elements so a vision LLM can act without HTML or accessibility trees. A fine-tuned detector finds interactable icons; a caption model describes their function, lifting GPT-4V grounding on ScreenSpot and Mind2Web.
AI Infra2024
Runs local LLM, vision-language, ASR, OCR, and image-generation models across NPU, GPU, and CPU from one command. Differs from Ollama and llama.cpp with first-class Qualcomm Hexagon NPU support and day-0 coverage of new models like Qwen3-VL.
AI Image2024
Trains a 65M-parameter vision-language model from scratch in ~2 hours on one RTX 3090, about 3 RMB (~$0.40) of GPU rental. Connects a frozen SigLIP2 encoder to a small MiniMind LLM via a two-layer MLP projector; full PyTorch code for pretraining and SFT.
AI Image2024
Turns PDFs and images into clean Markdown with a 7B vision-language model, keeping tables, equations, handwriting, and multi-column reading order while removing headers and footers. Runs on one 12GB+ GPU at about 1/32 the cost of GPT-4o APIs.
AI Dataset2024
Provides point-accurate annotations of interactive parts in high-resolution indoor laser-scan point clouds, plus affordance labels, motion axes and natural-language task descriptions; includes aligned iPad RGB-D video slices with 2D projections for multimodal research.
AI Video2024
Reference architectures and microservices for building GPU-accelerated vision agents that enable natural-language video search, long-video summarization, visual Q&A, and alert verification. Integrates NVIDIA NIM models, embeddings, VLMs/LLMs, and agent workflows for deployable video-analytics stacks.
Embodied AI2025
Turns camera, audio, LIDAR and web inputs into robot motion, navigation and speech by routing them through pluggable LLMs and VLMs. Hardware-agnostic Go runtime configured via JSON5, with ROS2/Zenoh middleware for real robots and simulators.
AI Agent2025
Drives your computer from natural language: a vision-language model reads raw screenshots and works the mouse and keyboard like a person, controlling any GUI app without APIs or accessibility hooks. Local or remote operator modes on Windows and macOS.
AI Video2025
Retrieval-augmented generation framework for videos spanning hundreds of hours, runnable on a single RTX 3090. Builds multi-modal knowledge graphs over visual and audio content so you can query and chat across many long videos at once.