MLINFO COLLECTION
工程条件、原料ロット、検査値から品質指標や不良リスクを予測するための技術です。
Quantitative research is an iterative loop: a researcher proposes a market hypothesis, implements it as an executable signal, tests it on historical data, and decides what to keep. Existing…
Perimeter triage faces a latency/semantics trade-off: signature engines are fast and format-safe but blind to unseen attacks, while generative models are semantic but slow and produce unparseable…
Gaussian process upper confidence bound (GP-UCB) has been widely studied, though its known regret upper bound is suboptimal. To obtain near-optimal regret upper bounds, existing studies mainly focus…
Smart-city applications often combine scarce labeled data with abundant unlabeled observations. Semi-supervised learning (SSL) exploits both labeled and unlabeled data to improve classification under…
Offline reinforcement learning is fundamentally limited by the coverage of the available data, while collecting additional trajectories through online exploration may be costly, unsafe, or…
Bayesian neural networks (BNNs) offer a principled framework for quantifying epistemic uncertainty. However, standard weight-space priors yield complex, high-dimensional neural network posteriors…
As robots and intelligent systems increasingly interact with humans, they must anticipate long sequences of future actions from only brief observations. While purely neural models typically require…
The marginals of a continuous diffusion model can be reproduced by a deterministic ordinary differential equation (ODE), known as the probability flow ODE, which provides a foundation for accelerated…
Legal Question Answering (QA) over statutory texts is a challenging task in Natural Language Processing (NLP), especially in low-resource settings with complex legal systems. It requires answers that…
Safety alignment for Large Language Models is heavily focused on English with limited multilingual representation, particularly damaging low-resource language performance. Related open training…
We study high-dimensional integration on bounded convex domains. Given a non-negative integrand $r$, the goal is to estimate $Z=\int_{D}r(x)\,\mathrm dx$ on $D\subset\mathbb R^d$.
We present LucidLyra, a framework that makes generatively reconstructed 3D scenes directly queryable for semantics and instances in a feed-forward manner from video latents. While generative 3D…
Large language model (LLM) agents are proposed for clinical prediction but are untested in pediatrics, where cohorts are small and outcomes are uncommon. Using records from 2,489 youth with type 2…
In-context imitation learning (ICIL) adapts robot policies through test-time demonstrations, but long multimodal trajectories constrain how many examples fit in context. We ask what a compressed…
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…
High-quality articulated assets are essential for embodied perception, simulation, and manipulation, yet constructing them at scale remains difficult. Manual annotation and procedural modeling…
Looping in transformer models reuses weights by repeatedly applying the same transformer, or parts of it, making the model deeper without increasing its parameter count. Whether looping is useful…
Large language models (LLMs) are increasingly capable, yet they produce wrong answers indistinguishable from correct ones. In question answering (QA), such an error propagates unnoticed into…
Synthetic data are widely used for training modern AI systems. However, their statistical understanding remains limited.
Multimodal large language models (MLLMs) are now used as zero-shot judges of image quality, but their color judgments are rarely tested with colorimetric ground truth. We present a five-task…
Fine-grained action annotations can support skill reuse and compositional generalization in robot policies. However, robot datasets typically provide task-level instructions without subtask…
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…
Recent advances in Time Series Foundation Models (TSFMs) increasingly rely on axial attention mechanisms, but despite their empirical success, the theoretical properties of axial attention remain…