MLINFO COLLECTION
日次更新の新着・公開記事を新しい順に掲載しています。
We show that outlier eigenvectors of the Bethe Hessian achieve weak recovery in the stochastic block model down to the Kesten-Stigum threshold, for every fixed common expected degree $d>1$. This…
Physicians read electrocardiograms (ECGs) from waveform shape and timing, yet accurate deep-learning classifiers rarely show which waveform regions drive their predictions. We introduce LYNX-ECG, a…
Cultural value alignment requires not only model optimization but also a well-specified target grounded in real-human evidence. Yet how such targets should be grounded in human data remains largely…
Continual learning is the study of how a model accumulates knowledge from data received over time, rather than all at once. In practice, this is typically achieved by dividing a dataset into tasks…
Average segmentation accuracy and model count do not reveal whether models fail on the same cases. We present CoFailMed, an audit of correlated failures in pretrained-encoder pools for medical…
Multi-head attention in Vision Transformers (ViTs) allows independent attention patterns across heads, but without explicit regularization, heads may learn redundant patterns rather than…
Taxonomy construction is essential for knowledge-intensive NLP yet remains costly: clustering-based methods (i) need careful per-corpus tuning and yield unstable hierarchies, while LLM-based…
Healthcare increasingly relies on connected medical devices, clinical information systems, cloud services, and distributed-care technologies, creating cybersecurity risks across clinical workflows.…
Highway work zones are critical edge cases for autonomous vehicles (AVs), combining atypical geometries and jurisdiction-specific regulations that existing benchmarks fail to capture: real-world…
Reasoning distillation is widely used to transfer the reasoning capabilities of large language models to smaller students through teacher-generated supervision. In the black-box setting, however,…
Recent years have seen multiple impressive results in visual-inertial odometry (VIO) techniques, by which accurate state estimation can be achieved via the extended Kalman filter (EKF) or nonlinear…
Reliable histopathology segmentation requires models that rely on pathology-relevant structures rather than spurious background correlations. In this work, we argue that improving architectures alone…
A central challenge in multimodal in-context learning (MICL) arises from tasks that are ill-defined without context and require uncovering the underlying rules from demonstrations. Existing methods…
This paper leverages the higher-order kinematic derivatives of serial robots to achieve efficient, aspect-preserving real-time inverse kinematics. First, a family of higher-order solvers is derived,…
Task Vectors (TVs) provide a compact way to steer large language models, but they are typically treated as atomized directions merely extracted from hidden states, leaving their internal functional…
Bangla symptom-based disease prediction is commonly evaluated on a small, imbalanced structured benchmark containing many profiles that differ by only one or two symptoms. We test whether train-only…
Whether a language model was trained on a document matters for copyright, privacy, and benchmark contamination. Yet most membership-inference (MI) evaluations on language models collect members and…
Multitemporal synthetic aperture radar (SAR) imagery provides continuous, cloud-free observations of crop phenology for agricultural monitoring in cloudy and rainy regions, yet high-accuracy…
Architectural spaces are increasingly gaining robotic capabilities. Architectural robots such as robotic partitions, ceilings, furniture, facades, and other spatial components can autonomously move…
Looped language models can strengthen reasoning through repeated computation with shared weights, increasing execution depth without adding independent parameters. However, each additional pass…
Underwater imagery records rich ecological information and supports applications such as science communication, fishery monitoring, ecological conservation, and oceanographic research. Beyond general…
The needle-in-a-haystack (NIAH) benchmark was introduced as a test for measuring a model's ability to find small relevant facts within a very large body of input text. However, existing NIAH…
Flexible robot links challenge the rigid-body assumption, making joint measurements alone insufficient for accurate manipulation. This paper introduces a flexibility-aware manipulation framework that…
Large language models (LLMs) have recently been adopted for Grammatical Error Correction (GEC), achieving strong performance via both full fine-tuning and prompt-based approaches. As probabilistic…