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。
Recognizing task completion and failure enables robots to stop upon success and initiate recovery or replanning after failure. Existing methods augment Vision Language Action (VLA) policies with task…
Objective: Iontophoretic drug delivery has primarily relied on current modulation to regulate drug transport. Here, we investigate hydrogel geometry, microstructure, and local electric fields as…
Generating 360-degree panoramas requires both local perspective fidelity and global spherical continuity. Existing representations face a trade-off: equirectangular projection (ERP) enables seamless…
\emph{Continuous-space} attacks find prompts that trigger malicious behaviors, such as overthinking, in black-box LLMs by sampling or optimizing over a low-dimensional Gaussian latent space and…
Synthetic biparametric MRI (bpMRI) may help alleviate the limited availability of large and representative prostate MRI datasets for deep learning applications. In this work, we present a conditional…
Tactile sensing provides robots with contact information difficult to obtain from vision alone. Shear force is particularly important for understanding tangential contact, guiding corrective motions,…
World action models increasingly rely on pretrained video models assumed to capture physical dynamics for prediction, planning, and action generation. Existing evaluations assess plausibility, probe…
Diffusion large language models (dLLMs) enable flexible masked generation through bidirectional context modeling, but this capability also introduces a distinct jailbreak attack surface. We find that…
Many deployments require a model to move rapidly from a data-rich source to a related target observed only sparsely. This is especially consequential where target data are difficult to collect, as in…
Exoskeletons have shown great potential for augmenting human physical capabilities, yet generating reliable assistance remains challenging because human motion patterns and interaction requirements…
Low-light image enhancement (LLIE) aims to recover well-exposed and perceptually faithful images from severely degraded observations. Recent diffusion-based generative methods achieve strong…
We envision a general-purpose protein foundation model as a unified, interactive model of sequence, structure, and function, capable of understanding, generation, and cross-modal translation while…
Diffusion trajectory planners with domain-specific experts face a practical question in unseen regions: can they rely on selecting among existing experts, or must the planner itself adapt? We study…
Multimodal sentiment analysis (MSA) aims to infer sentiment by integrating linguistic, acoustic, and visual information. However, many fusion methods integrate modality-specific representations and…
Generative video compression (GVC) methods usually employ decoder-side diffusion models to denoise reconstructed signals based on generative priors. Besides, most of these methods perform denoising…
Robot demonstrations record what the robot saw and what it did. They do not specify how the 3D world changed in between.
Generative modeling for Computer-Aided Design (CAD) remains fundamentally challenged by the need to capture the intricate interplay between discrete topological connectivity and precise spatial…
Diffusion language models (DLMs) decode multiple tokens in parallel, so individually valid tokens can be incompatible together under a schema. Exact joint inference over a grammar graph enforces…
Neurosurgical navigation commonly presents magnetic resonance imaging (MRI) as 2D slices, making it difficult to relate the anatomy in those slices to the cortical surface observed through the…
Population graph learning supports brain disorder diagnosis by sharing information across subjects. Its effectiveness, however, depends on whether the relationships guiding this exchange are relevant…
Cyberbullying involves behavioral and contextual patterns beyond isolated abusive messages. However, existing approaches remain fragmented across content detection, semantic representation, and…
Few-step autoregressive video generation enables low-latency streaming, yet prevailing training pipelines separate causal adaptation from distribution matching. Recent representation-based…
Diffusion-based audio-visual generation methods typically perform joint denoising of audio and video latents throughout the entire sampling trajectory, repeatedly executing modality-specific…
Humanoid motion-tracking policies can reproduce diverse behaviors, yet connecting independently acquired motions into a continuous sequence remains challenging. Interpolation connects boundary poses…