LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
Paper • 2604.02097 • Published • 32 •
4
Jiachun Jin
orres
AI & ML interests
None yet
Recent Activity
authored a paper about 1 month ago
Diffusion LLMs Can Do Faster-Than-AR Inference via Discrete Diffusion
Forcing authored a paper about 1 month ago
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders authored a paper about 1 month ago
LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified ModelOrganizations
commented a
paper about 1 month ago