perception

Cross-platform, customizable ML solutions for live and streaming media.

OpenEMMA, a permissively licensed open source "reproduction" of Waymo’s EMMA model.

Platform for Situated Intelligence

This repo contains evaluation code for the paper "BLINK: Multimodal Large Language Models Can See but Not Perceive". https://arxiv.org/abs/2404.12390 [ECCV 2024]

Your agent seeks what search can't find. A self-hosted perception MCP server that transcribes speech, reads behind logins, sees images and video frames, crosses languages, and remembers.

[ICRA26] OmniVLA: Physically-Grounded Multimodal VLA with Unified Multi-Sensor Perception for Robotic Manipulation

AOI: a model-agnostic perception layer giving computer-use agents adaptive video + audio perception with zero retraining, plus DynaCU-Bench (100 dynamic browser tasks). Paper + benchmark + code.