MLINFO COLLECTION
工程条件、原料ロット、測定値から、品質指標や不良リスクを予測するための実装ガイドです。
Deploying language agents in real applications demands more than the right answer: an agent must execute a multi-step business process correctly, follow domain-specific rules, and interact with a…
Tabular foundation models (TFMs) now outperform gradient-boosted trees in classification and regression. Yet in survival analysis, which predicts when an event occurs from censored data, often on…
In Hebbian learning from examples, a Hopfield network retrieves archetypes seen only through noisy examples. We study it in the exponential Hopfield model: one softmax attention step with the…
Tabular foundation models based on prior-data fitted networks (PFNs) predict on a new data set in a single forward pass, but they cannot report which inputs their predictions depend on. We propose…
In this paper, we present a lightweight algorithm for modelling tabular data containing both continuous and discrete variables. The method uses empirical marginal distributions and a selected…
Process-induced warpage, ceramic stress and solder strain limit the reliability of insulated-gate bipolar transistor (IGBT) modules on direct-bonded copper (DBC) substrates. Surrogate-assisted design…
Language agents increasingly act through external tools and interactive environments, making the interface between the model and its executable capabilities part of the decision process. Model…
Can LLM agents carry a hard real-world problem from raw data to a system that holds its own against people? We study this in Hearthstone Battlegrounds, an eight-player auto-battler with stochastic…
Recent test-time training (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scientific discovery tasks.…
Language models are frequently aligned to human preferences via imperfect evaluators whose errors can be exploited during optimization. We train policies to search for comparisons on which an…
Spatial public goods models show that prescribed movement toward richer locations can generate spatial patterns. We ask how such patterns emerge when agents learn where to move and how learning rates…
High-capacity neural network models have achieved state-of-the-art performance across diverse classification tasks, yet they frequently operate as black-box models, lacking the transparency necessary…
As frontier language models grow increasingly capable and autonomous, independent third-party evaluations are critical for characterizing their systemic safety risks. While closed-source releases are…
Repeated attempts at interactive tasks uncover facts, useful operations, and failures that can inform subsequent execution. We introduce ReGE, a framework for turning this recorded experience into…
Data science agents can automate end-to-end machine learning workflows, yet they remain far from competitive on human leaderboards. Agents make process errors such as insufficient exploration,…
A benchmark is not merely a collection of test questions; it naturally induces an empirical measure over difficulty. In this work, we develop this measure-based view of benchmark evaluation.
Spatial reasoning requires more than access to geometric tools: a reasoner must decide when direct observation is sufficient and when to reconstruct, measure, or change reference frames. We present…
We present Épi, an autonomous research agent that sustains investigations across model sessions and evolves its methods through accumulated experience. Épi combines persistent research history,…
Expert human readers process large inputs (e.g., code repositories and long documents) by skimming to closely read only what matters. On the other hand, language models process all input tokens…
Drafting an answer allows a reasoning model to reconsider each decision in the context of the others. Yet repeated diffusion denoising does not ensure that individually plausible token updates form a…
Digital art generation has undergone a massive paradigm shift, moving from static image synthesis to dynamic video generation that can mimic the human painting process. While existing models can…
Video Reasoning Segmentation (VRS) requires a model to identify an implicitly described target and predict its pixel-level mask trajectory, while resolving the spatial relations and temporal events…
Chemical chain-of-thought can contain hallucinated structural and property claims. We thereby introduce MolLean, a process-verifiable language that grounds chemical reasoning in an explicit molecular…
Agent Skills improve LLM agents by making task knowledge reusable across sessions. Learning transferable Skills requires evidence about a procedure and its conditions of use, which a successful task…