AIBullisharXiv – CS AI · 8h ago6/10
🧠
Mull-Tokens: Modality-Agnostic Latent Thinking
Researchers introduce Mull-Tokens, a new approach enabling multimodal AI models to reason across text and image modalities using shared latent tokens without requiring specialized tools or handcrafted data. The method demonstrates 3-16% performance improvements on spatial reasoning benchmarks, offering a simpler alternative to existing multimodal reasoning systems.