MLINFO COLLECTION
RAG、埋め込み、検索評価、要約を使って文書検索や社内QAを作るための技術です。
Real-to-Sim-to-Real (Real2Sim2Real) enables structured world representations for planning, interpretability, and safe execution. Most existing approaches rely on passive perception, which creates…
Humanoid dexterous hands are a core component of embodied intelligence, enabling robots to translate high-level intent into rich and adaptive physical interaction. However, existing designs remain…
Nonparametric inference often requires characterizing an unknown function, such as a cumulative distribution function (CDF), across its entire domain rather than a specific point. We develop…
Shapley-value-based explanations are widely used for feature attribution in machine learning. However, in computer vision, a feature may reduce the target-class score when added to the complete…
In stochastic multi-objective bandits, Pareto optimal arms may represent different trade-offs among objectives. Balanced sampling across them is important in practical settings such as online…
In token-priced language model services, users can see the prompts they submit and the answers they receive, but may also pay for internal reasoning and candidate answers that are not shown in the…
We study the asymptotic behaviour of the solutions to the unconstrained generalized variational inference problem regularized by an $α$-divergence. Under mild conditions, the minimizer is explicit up…
Problem definition: Subscription box services often ask customers for ratings before choosing what to send. Responses are scarce, and longer questionnaires and finer scales lower completion.
Organisms must constantly weigh exploiting the resources they know against exploring for better ones. When foragers compete, the best behavior for each forager also depends on what its competitors do.
Clinical scalp electroencephalography (EEG) offers a noninvasive window into neural dynamics of neuropsychiatric disorders. However, discriminative deep models often lack anatomically indexed…
Self-evolving vision-language models train on questions they generate from unlabeled images. Since these questions have no gold answers, prior methods label them by majority vote over sampled answers…
As constellations of satellite grow in size, and become more costly, they are increasingly funded by multiple stakeholders who expect access to the constellation's resources that is commensurate with…
In applications such as air-quality monitoring, inexpensive sensor readings can help predict pollutant concentrations measured by a separate reference instrument. We study how to adapt conformal…
Gradient equilibrium (GEQ) is a recent framework in online learning that requires the time-averaged gradients along the learner's trajectory to vanish. We study GEQ when the learner is constrained…
Retrieval Augmented Generation (RAG) grounds large language models in external knowledge. Modern pipelines combine embedding, chunking, retrieval, reranking, query augmentation, context compression,…
In real-world clinical settings, dental X-ray segmentation using deep learning methods suffers from reliability issues. Even when the segmentation quality is bad, deep learning models show high…
Foundation models are typically trained in stages: pretraining, midtraining, supervised fine-tuning (SFT), and reinforcement learning (RL), with changes in both data and learning algorithms. We show…
Language models handle text well, and rule engines give conclusions with proofs. Systems that combine the two are usually described by example, and the same coupling turns up under different names in…
Systems such as The AI Scientist have shown that AI agents can carry out and write up research, but in those demonstrations humans chose the research area and selected the outputs to show. We study…
Unlimited OCR ushers the era of long-horizon parsing, substantially mitigating the growth of working memory as document lengthens. However, as document length scales to hundreds of pages, the visual…
What is the round complexity of Hessian-similar optimization when each round can contact at most $s$ of $m$ clients? Prior rates permit a free master or full participation and do not characterize…
Modern gradient boosting algorithms are based on Newton's method, which excels empirically but lacks global convergence guarantees. While recent work on Gradient-Regularized Newton (GRN) boosting…
World Action Models (WAMs) have emerged as a promising approach to learning generalist robot policies using rich spatiotemporal priors from pre-trained video diffusion models. A recent line of WAMs…
Blind random search is a simple global optimization method that only requires the value of the loss function, without needing gradient information or an explicit loss model. However, its classical…