MLINFO COLLECTION
製品画像、顕微鏡画像、表面欠陥を対象に、分類・検出・セグメンテーションを選ぶための導線です。
Radar systems can recover scene geometry and recognize predefined categories, but these outputs do not provide a persistent spatial representation for open-ended language queries. Such queries…
Vision-language models are shifting from offline passive understanding toward online proactive interaction. However, prevailing methods largely rely on explicit requests while miss the implicit user…
As streaming video generation advances, enabling real-time interaction with generated video is becoming increasingly important. We introduce StreamEval, a unified benchmark for interactive streaming…
We propose Nemotron-Labs-Diffusion-Uni (NLD-Uni), a unified discrete diffusion large language model (DLLM) for visual understanding and generation tasks. Compared with prior unified diffusion models,…
Video stylization typically transforms entire scenes, while local artistic editing requires precise region--style association, spatial control, and temporal consistency. We introduce LociArt, a…
Generating videos of a specific subject from a few reference images remains challenging when the camera reveals surfaces that are not visible in the input. Early subject-to-video (S2V) methods…
The growth of time-series datasets and foundation models has made dataset comparison a central part of time-series workflows. Assessing source-target transfer before model adaptation requires…
Metadata-conditioned generation is often framed as a data-to-text task in which additional input fields should improve grounding. Museum description generation challenges this assumption because…
Saliency and scanpath models are developed almost exclusively on natural photographs, yet paintings are composed by artists to guide the viewer's eye and differ from photographs in texture, colour…
Voice style conversion (VSC) aims to transform a source utterance to match the timbre, accent, and emotion of a target voice while preserving linguistic content. StyleStream 1.0 introduced the first…
We consider the problem of online linear classification, where a stream of unlabeled samples is available, and annotation is costly. We investigate the optimal query policy, that prescribes whether…
Often, \emph{eg} in healthcare and predictive maintenance, what matters is which of several competing causes will strike first, and with what probability: survival analysis with competing risks.…
We introduce Timestral, a family of four time series foundation models for probabilistic forecasting, with 5M, 28M, 123M, and 209M parameters. Timestral sets a new state of the art on GIFT-Eval,…
High-resolution video matting requires preserving fine details, such as hair strands and soft transparency, while maintaining consistency across frames. Memory-based methods achieve strong matting…
Reasoning-augmented vision-language-action (VLA) driving models can perceive and reason about safety-critical hazards yet fail to translate that evidence into safe actions. We characterize this…
We compare the relation between sentiment noise in the Twitter feed and losses for stocks of domestic and foreign firms. The mean quarterly domestic-foreign difference in the slope of next-quarter…
Healthcare providers lose substantial revenue to systematic payer underpayments and claim denials, yet identifying the recurring, correctable patterns behind them remains largely manual and does not…
Agent learning is shifting from learning from human data toward learning through interaction with the world. However, scaling such learning directly in real-world computer systems is challenging and…
Human egocentric experience offers a rich foundation for learning how the world is organized and how it changes through interaction. Realizing this potential at scale requires turning growing volumes…
High-quality image editing requires precise modification of target regions while preserving the content of unrelated regions. Existing editing models produce flattened outputs that limit precise…
Neural Architecture Search (NAS) has proved to be a strong alternative to manual network design, but applying it to 3D medical image segmentation is limited by two well-known costs, large annotation…
Visual generation requires both high-level semantic knowledge and fine-grained pixel details. We propose a learning paradigm that assigns these roles to autoregressive pretraining for knowledge…
Learning velocity fields directly in pixel space is difficult and slow. We show that coarse second-order image statistics can ease this task: frozen Wiener estimates improve velocity learning, with…
Agent harnesses enable large language models to act through tools, observe the results, and iteratively work toward a task goal. Verification checks and revises agents' work to improve output quality.