Researchers introduce RealWonder, a real-time video generation system that simulates physical consequences of 3D actions by using physics simulation as an intermediate representation. The system generates 480x832 resolution videos at 13.2 FPS from a single image, handling rigid objects, deformable bodies, fluids, and granular materials.
Researchers introduced MeanFlowSE, a generative speech enhancement model that eliminates the computational bottleneck of multistep inference by learning average velocity over finite intervals rather than instantaneous velocity fields. The single-step approach achieves comparable quality to multistep baselines on VoiceBank-DEMAND while requiring substantially lower computational cost and no knowledge distillation.
A new arXiv study systematically characterizes memorization behavior in diffusion language models (DLMs) and finds they exhibit substantially lower memorization-based leakage of personally identifiable information compared to autoregressive language models. The research establishes a theoretical framework showing that sampling resolution directly correlates with exact training data extraction.
A new paper identifies token rounding as the primary bottleneck limiting continuous diffusion language models (DLMs) and proposes CoDAR, a two-stage framework that combines continuous embedding-space diffusion with a contextual autoregressive decoder. Experiments on LM1B and OpenWebText show CoDAR achieves competitive performance with discrete diffusion approaches while offering tunable fluency-diversity trade-offs.
Researchers have identified token rounding as a primary bottleneck limiting continuous diffusion language models (DLMs) and propose CoDAR, a two-stage framework that maintains continuous embedding-space diffusion while using an autoregressive Transformer decoder for contextualized token discretization. Experiments on LM1B and OpenWebText show CoDAR achieves competitive performance with discrete diffusion approaches.
Researchers have proposed DiSE, a self-evaluation method designed to assess output quality in diffusion language models (dLLMs) by computing token regeneration probabilities. The technique enables efficient confidence quantification for models that generate text bidirectionally rather than sequentially, addressing a key limitation in quality assessment.
Researchers propose LaDiR, a framework that replaces traditional autoregressive decoding with latent diffusion models to improve LLM reasoning. The approach encodes reasoning steps into compressed latent representations and uses bidirectional attention to refine solutions iteratively, enabling parallel exploration of diverse reasoning paths.
Segmind has released SegMoE, a mixture-of-experts (MoE) diffusion model designed to accelerate image generation while reducing computational overhead. The model applies MoE techniques traditionally used in large language models to the diffusion model architecture, enabling selective expert activation during inference.