MLINFO COLLECTION
樹脂、電池、触媒、合金などの配合・組成を、少ない実験回数で改善するためのAI/MI導線です。
We study nonconvex--strongly-convex bilevel optimization with finite-sum objectives and fully first-order oracles. We propose Sampled Implicit Corrections for Bilevel Optimization (SICBO), which…
We study differentially private black-box evaluation of arbitrary high-dimensional functions. Given a dataset $S$ and query access to a function $f$---whose sensitivity may be unknown or…
In this work, we develop a zeroth-order (ZO) method that estimates the gradient with minimal bias and variance. Instead of the random directions often used in the ZO literature, we consider central…
Empirical averages are fundamental statistical primitives. On nonlinear spaces, their generalization, the Fréchet mean, generally lacks a closed-form solution, and its computation requires solving an…
Standard Bayesian experimental design (BED) methods assume the experimenter alone will act on the data, choosing the best action given their own beliefs and goals. In practice, data are often acted…
Evaluating the causal effect of new features is a central goal for online platforms. While recent literature addresses limited testing traffic via centralized portfolio optimization, this perspective…
Every day, people continuously infer situational context and adjust the way they understand and remember the world. Context, signaled by the prefrontal cortex, is known to modulate working memory and…
Predictive coding (PC) is a local, energy-based alternative to backpropagation (BP) whose iterative inference dynamics make it attractive for implementation on analog hardware. However, standard…
Quantum-inspired evolutionary optimization (QIEO) represents design variables as a set of qubits and searches a continuous, multi-dimensional landscape through rotation of the qubit's amplitude pair.…
Neurons in the visual system are selective for specific spatial and temporal stimulus features, described by their \emph{receptive field}. Estimating one means a coefficient per pixel per time bin…
Human motion retargeting bridges the embodiment gap between humans and humanoid robots by converting human demonstrations into reference trajectories for whole-body control and loco-manipulation. For…
Forecasting future human motion requires jointly reasoning about an agent's global trajectory and 3D body pose, which are tightly coupled, particularly in team sports where multiple interacting…
Weight-only quantization keeps LLM activations in floating point and stores weights as low-bit integers, turning the dominant workload into floating-point-integer (FP-INT) general matrix…
Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements. Although recent approaches enable…
Dynamic representations based on 4D Gaussian Splatting (4DGS) have shown strong capabilities in reconstruction and rendering, yet current methods remain limited in supporting complex natural-language…
Sequential decision-making under partial observability is difficult because agents must explore to infer hidden, task-relevant information before acting effectively. Learning such…
Vision-language-action (VLA) models have shown promise in robotic manipulation, but imitation learning (IL) alone often struggles to master complex long-horizon skills. Reinforcement learning (RL)…
Harness optimization, which improves an agent's prompts, tools, and workflows, is an increasingly effective way to enhance agents built on frozen or closed-source LLMs. Leading approaches such as the…
Recovering metric world-space hand motion from egocentric video supports understanding human interactions and transferring them to embodied agents. Three challenges complicate this task: multi-stage…
Real-time whole-body humanoid teleoperation remains challenging due to the computational latency introduced by optimization-based retargeting pipelines and future-frame conditioning. Existing motion…
Movement primitives commonly represent robot mo- tions through basis functions indexed by time or phase. Inspired by spacetime representations employed in physics, we propose a spline-based…
During steady pouring, images and robot pose may remain nearly unchanged while transferred mass accumulates, making the return decision ambiguous for a whole-task vision-language-action (VLA) policy.…
The deployment of small and quantized language models in resource-constrained settings raises an important fairness question: when a compressed model produces fewer biased responses, does this…
Aligned large language models are trained to comply with benign requests while refusing harmful ones. However, recent work shows that this refusal behavior is fragile and can often be disrupted by…