Janus-Pro: Decoupled Encoders for Unified Multimodal Models
Unified multimodal models have an unavoidable tension. Understanding wants semantic features — SigLIP or DINOv2 output vectors rich with concept-level information. Generation wants reconstruction-friendly codes — VQ tokens that compose back into crisp pixels. The two goals are not compatible in a single encoder. Janus (DeepSeek, October 2024) and Janus-Pro (DeepSeek, January 2025) argue the fix is to stop trying: decouple the two encoders. Share the transformer body between tasks, but route understanding through SigLIP and generation through a VQ tokenizer. At 7B, Janus-Pro beats DALL-E 3 on GenEval while matching LLaVA on MMMU. This lesson reads why two encoders work where one fails.
This lesson isn’t interactive yet.
It is part of the curriculum and will get the same treatment as Phase 1 — a visual cover, hands-on labs, derivations with numeric checks and a quiz. Until then, the original lesson is the best place to read it:
Part of Phase 12 — Multimodal AI. Use the previous / next cards below to keep browsing the phase.