understanding

[ICLR 2026] Official repo of paper "Reconstruction Alignment Improves Unified Multimodal Models". Unlocking the Massive Zero-shot Potential in Unified Multimodal Models through Self-supervised Learning.

Cerul — video memory infrastructure for AI products. SDKs, CLI, MCP, and developer integrations.

VideoEval-Pro: Robust and Realistic Long Video Understanding Evaluation [TMLR26]