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。
In this paper, we investigate why vision-language models (VLMs) produce errors by decomposing them into two sources: visual-representation failures, in which the visual evidence required for the…
Barycenter models, based on stochastic and deterministic optimal transport bridges between probability measures, have proven to be useful for supervised and unsupervised learning for (probability)…
Traditional robotic navigation systems separate mapping, planning, and low-level control through cascaded modules, introducing computational overhead and accumulated latency. End-to-end reinforcement…
The evidence, $\mathcal{Z} = p(x | \mathcal{M})$, of a data-generating model $\mathcal{M}$ is a powerful tool in Bayesian frameworks: it enables model inference, model misspecification tests, and…
Learning causal structure from data requires assumptions about mechanisms, noises, observation schemes, and interventions. Historically, causal discovery has relied primarily on conditional…
We study the inverse problem of recovering unknown parameters governing the dynamics and rewards of Mean Field Games (MFGs) from partial observations of population trajectories, made stochastic by…
We study the optimal design of a self-financing event, a problem that requires balancing the recruitment of costly, positive-value participants with revenue-generating agents who may impose negative…
In-context reinforcement learning (ICRL) exploits the impressive in-context learning ability of large language models to zero-shot generalize to new, unseen tasks at inference time without any…
RLVR improves language-model reasoning, but commonly relies on independent stochastic rollouts for exploration, which can repeatedly sample similar failed strategies. Prior work has seen success with…
While large-scale human motion capture datasets provide a rich source of demonstrations for humanoid robot learning, retargeting the diverse motions to different humanoid robots remains a nontrivial…
General-purpose multimodal models have shown promise as direct robot action policies, yet whether they grasp the physics underlying real-world interactions and can apply that understanding to guide…
A planner using a learned world model can improve its predicted outcome while choosing a worse action. We study when expected free energy (EFE) can help decide how much computation to spend on a plan.
Connected and Autonomous Vehicles (CAVs) face significant challenges in roundabout navigation due to dense traffic interactions and unpredictable agent behaviors, necessitating high levels of…
Spatial and spatiotemporal point process models are widely used to analyze event data across many scientific disciplines, but likelihood-based Bayesian inference is often computationally prohibitive…
Stochastic optimization with high-fidelity nonlinear models is often computationally prohibitive because each objective evaluation requires sampling-based uncertainty quantification inside an outer…
A new adaptive restart rule for Genetic Algorithms (GAs) is considered. The rule is based on the Schnabel Census method, originally developed for statistical estimation of a size of animal population.
In the best-arm identification problem, an algorithm adaptively selects arms to find the arm of the largest mean reward. Successive Rejects (SR) is a simple fixed-budget best-arm identification…
Many modern learning systems are used not to select a single best action, but to sample diverse high-quality outputs. Examples include entropy-regularized reinforcement learning, RLHF, and…
Neural Posterior Estimation (NPE) fits an amortized conditional density estimator to a simulated training set of complete-data realizations. NPE's training objective, log-likelihood, favors posterior…
We examine the value of information in extensive-form decision problems: the largest multiplicative gain that a decision maker can obtain from an information refinement, taken over all payoff…
Alignment of large language models typically relies on pairwise preference feedback, though ranked feedback can capture more comprehensive information across multiple responses within a single…
We study the complexity of computing approximate first-order Nash equilibria in min-max optimization problems with one dimensional min and max players and product constraints. For black-box access to…
We study a class of strategic hypothesis testing problems in which a principal aims to allocate resources among competing agents who possess data or data-generating mechanisms that may be relevant to…
The randomized primal-dual framework of Devanur, Jain, and Kleinberg (SODA 2013) splits each unit matching gain between endpoint dual variables according to the matched offline rank. The gain-sharing…