MLINFO COLLECTION
画像・動画生成、条件付き生成、編集、3D生成に関係する拡散モデルの論文と実装です。
Vision-Language-Action (VLA) models have demonstrated promising capabilities in robotic manipulation by integrating visual perception, language understanding, and action generation. Recent advances…
Recent advances in video world models have enabled the generation of increasingly realistic and interactive virtual environments, opening new possibilities for player-customizable gameplay. Agentic…
Bimanual dexterous manipulation requires continuous coordination of wrist motion, finger contact, and object motion. Human videos provide rich manipulation experience.
Video generation is shifting from end-to-end synthesis toward agentic generation, where planning, tool use, and feedback enable coherent, controllable multi-shot videos. In parallel, video world…
An outstanding creative advertising image should both attract attention and communicate a product's positioning. How to choose a persuasive conceptual bridge before rendering begins is challenging…
Event cameras capture visual brightness changes under challenging lighting conditions. However, traditional event-based image reconstruction targets grayscale intensity and produces images without…
The pursuit of fair and equitable AI in human-centric tasks is critically hindered by the inherent biases and privacy risks of real-world datasets, which offer imbalanced representations of identity…
Diffusion models are powerful priors for accelerated MRI reconstruction, but most current methods are posterior samplers, which return a random draw from the posterior. A reproducible and…
Guidance methods are essential tools for steering the generation process in diffusion models, improving the generalizability of stochastic robotic controllers and enabling high-quality controlled…
Understanding the internal routing of visual concepts is crucial for the safe and controllable adaptation of generative models. While concept localization has been widely studied in diffusion models,…
Real-time magnetic resonance imaging of the vocal tract makes speech articulation directly observable, but the trade-off between temporal resolution and signal quality introduces substantial noise…
Diffusion transformers (DiTs) have become the dominant architecture for high-fidelity image synthesis, yet they suffer from slow training convergence and high computational cost. Two recent lines of…
Distribution Matching Distillation (DMD) distills multi-step diffusion models into few-step generators by minimizing reverse KL divergence. Despite its strong performance, DMD guides samples by local…
KV cache quantization is well studied for autoregressive language models, where cached prefix states are exact under causal attention and quantization is mainly a cache reconstruction problem.…
Unlike autoregressive large language models (AR-LLMs), diffusion LLMs (dLLMs) generate text by iteratively denoising many tokens in parallel, offering a promising path to efficient inference.…
Virtual try-on has achieved remarkable progress in recent years, yet most existing methods are designed for a specific scenario, such as cloth-to-person or person-to-person try-on, and often require…
Interactive video world models aim to follow user actions while maintaining scene consistency over extended interactions. History-based methods reuse generated latents to preserve scene content, but…
Unified multimodal models (UMMs) jointly support visual understanding and image generation, yet information flow between these two capabilities remains largely asymmetric: understanding…
A score-based diffusion model is trained on the two-dimensional classical Heisenberg model, the lattice representation of the $O(3)$ nonlinear sigma model. Neural networks are trained on three…
One-step distillation turns pretrained diffusion models into fast generators, but strong results often require substantial training machinery and compute. Pure adversarial distillation offers a…
We propose MorphSIG, a training-free framework that reformulates subject-driven image generation (SIG) as pseudo-video feature transport. MorphSIG contains two core modules: Progressive Decoupled…
Traditional neural solvers for solving vehicle routing problems (VRPs) often suffer from limited solution diversity, motivating the development of Generative Flow Network (GFlowNet)-based models.…
Compositional motion transfer requires a model to extract motions from multiple reference videos, and apply each motion to a user-specified object in one target scene. Existing methods normally…
Unified Multimodal Models (UMMs) enable powerful multi-image synthesis but incur substantial computation from long visual contexts. While token pruning offers a direct route to accelerating…