#vision-language-model

Turn documents into AI-ready Markdown with visual understanding

Browser-based Android phone agent using WebADB/WebUSB and OpenAI-compatible vision models

PriorTR (ECCV 2026): training-free, prior-corrected visual token reduction for accelerating multimodal LLMs — image & video.

AI Robotics Demos 2026 - VLM Policies, MCP Skills & HTML Reports

On-demand vision for text-only DeepSeek Harness (DSH) sessions: images become markers, and a vision_describe tool sends only image + question to an OpenAI-compatible vision model

Agentic AI for biologically grounded morphological feature design from microscopy — designs, implements, and validates compact cell-profiling features. Includes a desktop Qt UI demo.

Local HTTP service for running AutoGLM phone-agent tasks against a connected Android device

Autonomous UI/game-testing agent: vision-language reasoning, browser control, action planning, failure recovery, and evaluation.