MLINFO COLLECTION
材料候補探索、分子生成、実験条件探索、ベイズ最適化に関係する技術です。
Large language model (LLM) agents for personal health read wearable data and recommend, but do not learn about the individual in a way that can be audited or falsified. We present EpiCoach, an…
Agents powered by large language models (LLMs) have demonstrated remarkable progress in solving complex reasoning tasks. However, LLM agents often falter on long-horizon tasks due to cognitive…
Low-bit quantization enables efficient deployment of large language models by reducing memory footprint and computational cost. Achieving high accuracy at low precision requires selecting…
Small-molecule identification from tandem mass spectrometry (MS/MS) may require complementary measurements. Herein, we propose a structure-informed deep Q-network (SI-DQN) that uses existing MS/MS…
We revisit advantage estimation in Group Relative Policy Optimization (GRPO) and observe that any token-level advantage admits a two-stage factorization: a \emph{sample-level baselining} step that…
While mining parallel sentences from web pages has proven effective for low-resource machine translation, the majority of the world's languages have little to no web presence. What they do have,…
Epistemic game theory explains an agent's strategic behavior via the beliefs it holds about others and how these beliefs are updated as the interactions unfold. Modern LLM-based agents, however,…
Rubric-based rewards provide fine-grained, interpretable supervision for open-ended reinforcement learning, where holistic scalar rewards struggle to capture multidimensional response quality. Static…
Automatic operator design (AOD) has increasingly adopted large language models (LLMs) to generate problem-specific search and variation operators for multi-objective combinatorial optimization…
Vegetation plays a central role in cities, serving functional roles such as balancing shade and sky exposure, shaping the microclimate, carbon sequestration, and providing acoustic screening.…
Privacy accounting bounds the cumulative privacy cost of Differentially Private Stochastic Gradient Descent but does not determine how to allocate a fixed budget across iterations. We formulate the…
Diffusion transformers (DiTs) have become the dominant architecture for high-fidelity image synthesis, yet they suffer from slow training convergence and high computational cost. Two recent lines of…
Novel view synthesis (NVS) in degraded scenes aims to reconstruct 3D scenes from multi-view observations affected by various degradations, and to generate clear and photorealistic images at unseen…
Generating interactive 3D assets from a single image requires realistic appearance, fidelity to the depicted object, and plausible physical behavior. Yet detailed geometry alone does not determine…
Clients observing different parts of a prediction task may learn locally equivalent models with incompatible behavior outside their observed support. We study whether redundant models permit local…
Targeted protein degradation (TPD) represents a fundamental shift in drug discovery, moving beyond traditional target inhibition toward the event-driven removal of disease-causing proteins. A…
In the context of multi-stage trajectory planning for robotic percutaneous liver interventions, identifying a kinematically feasible entry point remains a critical computational bottleneck. Existing…
Probabilistic meshless methods solve partial differential equations (PDEs) by placing a Gaussian process prior on the solution and conditioning it on the PDE at a finite set of collocation nodes. The…
Over-refusal is a critical side effect of safety alignment in large language models (LLMs), causing harmless but superficially risky queries to be mistakenly rejected. Despite the effectiveness of…
Visual grounding is crucial for robots to understand language instructions with visual observations. This paper addresses the problem of visual grounding uncertainties, where a robot uses a black-box…
Modern machine learning models are often overparameterized, i.e., have more parameters than training data. This typically implies that the loss function admits multiple minimizers so that training…
Molecular discovery requires navigating vast combinatorial search spaces while balancing competing biological objectives. AI agents can automate expert-defined molecular design protocols, but…
In engineering, applications of artificial intelligence have so far been largely limited to surrogate models and optimization tasks. Large language models changed this, as they can write software…
Deep search agents extend language models by interleaving reasoning with external retrieval. However, effective search-agent training requires addressing two challenges beyond final-answer…