LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
Paper • 2604.02097 • Published • 30
None defined yet.
Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
LoPA: Scaling dLLM Inference via Lookahead Parallel Decoding