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。
Adversarial training can improve some forms of correspondence between artificial and biological vision, but whether robust classifiers acquire human-aligned classification behavior remains unclear.…
Synthetic variants of known attacks, including feature-space adversarial perturbations, are sometimes used as stand-ins for unseen ("zero-day") attacks when evaluating machine-learning network…
We study federated model-free learning of a common linear quadratic regulator (LQR) gain under a limited uplink communication budget, with clients that share dynamics and costs but experience…
In this paper, we develop a projected instrumental variable framework that relaxes conventional assumptions for causal identification with instrumental variables. Building on the interpretation of…
Aerial visual localization over Level-of-Detail (LoD) 3D Maps has recently gained significant traction due to its global scalability, storage efficiency, and privacy-preserving nature. However,…
The Lane-Emden Equation is a class of nonlinear differential equations commonly used to model phenomena in astrophysics and mathematical physics, such as stellar structure and thermal behavior in…
Urban environmental monitoring is crucial for climate-adaptive cities, yet current approaches rely heavily on human inspection, overhead remote sensing, or limited terrestrial RGB imagery, thereby…
ALDER, a single-loop augmented-Lagrangian damped extragradient method, is proposed for smooth nonconvex--concave minimax problems with nonlinear coupled inequality constraints. Within an…
Speech-to-speech translation (S2ST) increasingly preserves what is said and how it sounds, but not necessarily when speech and silence occur. For dubbing and other temporally grounded applications,…
Software is increasingly developed by teams in which several people direct many coding agents from different vendors. Such teams must establish who may request what from whom, which messages start…
Understanding how animals move between behaviors is a central question in neuroethology, yet most segmentation methods first partition time into discrete states, leaving transitions as the unmodeled…
We study probabilistic forecasting of dynamical systems such as fluids and waves from coarse observations. Since the unseen fine scales influence the dynamics, the same coarse initial state can…
Medical vision-language models (VLMs) show promise for clinical image understanding, but their computational and memory requirements hinder deployment on resource-constrained clinical hardware.…
Reference-based style personalization should reproduce the appearance of a style reference while preserving the subject specified by a content prompt. In visual autoregressive models, dominant…
Two groups of pedestrians face avoidable risk on the city sidewalk: people living with visual impairment, who reach an obstacle before anything warns them, and people walking with divided attention,…
Hidden Markov models (HMMs) offer an important capability to interpret fitted latent states and transitions. When emission distributions nearly coincide, a small observation-density error does not…
Deep learning-based object detection models are highly dependent on the quality of annotated training data. However, large-scale datasets often contain inevitable label noise, with bounding box…
When a language model decides refund or claim requests under written policies, the system can show it similar past cases. Each past case has two parts: its facts and the decision recorded for it.
Independent mobility is a foundational requirement for the autonomy of blind and low-vision (BLV) individuals, yet the assistive technologies that support it have historically evolved slowly. This…
Graph foundation models aim to serve unseen graphs across tasks, feature spaces, and label sets. Most current models learn how to represent a new graph by pre-training on other graphs.
Subliminal learning allows AI models to inherit hidden preferences from seemingly unrelated training data, such as number sequences. Safety audits may evaluate models at standard 16-bit precision,…
Large language models (LLMs) are increasingly used to simulate human behavior, but which descriptions of people improve prediction when experimental designs change remains unclear. We develop a…
Generative view synthesis aims to synthesize novel-view videos from reference observations along user-defined camera trajectories. Maintaining global scene consistency throughout this process remains…
We introduce GateTrim, an adaptive-rank post-training quantization method for large language models that learns matrix-specific ranks through gate optimization and threshold-based rank selection.…