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。
Fairness benchmarks for large language models (LLMs) are overwhelmingly English-born and American in their social categories; translated versions carry those categories into societies where they do…
Dynamic semantic maps have become an important intermediate representation for many computer vision applications. Efficient lossless compression of such maps is essential for reducing storage and…
Modern data analysis pipelines increasingly rely on large datasets assembled through retrieval, scraping, automated filtering, and post-hoc curation, where the observed sample is often a contaminated…
Voice-interactive large language models process both what a speaker says and how they say it, yet the two channels do not always agree. We ask whether that disagreement degrades speech emotion…
We study first-order regret guarantees for adversarial bandits with a fixed, known directed feedback graph. For strongly observable graphs, [ACBDK15] establishes a minimax regret of…
Training a large language model is compute-bound, and current recipes divide the work between optimizers by hand: orthogonalized momentum for attention and MLP matrices, Adam-style updates for the…
Continuous diffusion language models (CDLMs) and speculative drafters offer efficient language generation but are typically evaluated differently: CDLMs generate independently through iterative…
Teams that cannot communicate seem stuck with what each member sees. We show that their opponent can tell them the rest.
Existing whole-body PSMA PET/CT prostate metastasis segmentation methods generally rely on images alone, without explicitly incorporating where metastases tend to occur. We investigate whether a…
Egocentric videos offer an abundant source of hand-scene interactions for embodied learning, which requires recovering hands, camera, and scene consistently in a shared 3D world. Existing methods…
Imitation learning policies are intended to make robotic manipulation robust to variations in object pose, appearance, and environment that challenge pre-programmed motion. However, real-world…
The reasoning capabilities of vision-language models (VLMs) can be limited by incomplete or inaccurate visual observations in the general domain. In unmanned aerial vehicle (UAV) scenes, small…
Across coding, web, and tool-use tasks, language-model agents are now routinely trained with the same recipe: supervised fine-tuning (SFT) to learn the interface, then multi-turn reinforcement…
Humans and animals have a unique capacity to generalize and learn in novel circumstances, including "0-shot" inference (ZI) and continual learning (CL) -- two powerful cognitive abilities. Despite…
Recursive self-improvement (RSI) enables large language models to advance their capabilities through successive updates, but these updates can also introduce new risks and weaken existing safeguards.…
Achieving the broad task generalization of embodied models in physical environments remains a central challenge in robot learning. We study this challenge in World Action Models (WAMs) through two…
Effective computer-use agents (CUAs) should seamlessly combine visual GUI interaction with code and terminal execution within a single policy. We present Mage-VL-Cowork, a 4B hybrid CUA trained from…
Retrieval-Augmented Generation (RAG) is vulnerable to knowledge poisoning, where adversaries manipulate retrieved evidence to influence model outputs. Existing defenses are primarily evaluated using…
Continual adaptation requires deciding not only how to update a model, but whether to commit an update without exceeding a declared budget for changes to protected behavior. We introduce Certified…
A capable voice assistant must do more than recognize words; it must understand requests, reason over context, sustain conversations, and act through tools. We present Apriel Voice 27B Preview, an…
We study adaptive UAV sampling for radio environment map (REM) construction from non-Gaussian IoT observations. Integrated nested Laplace approximation(INLA) updates a Matérn GMRF posterior, with…
Learning a shared subspace in multitask learning is an important statistical problem, yet exact rates remain poorly understood in many of the formal settings considered in the literature. To address…
Data attribution methods for Language Models (LMs) are typically evaluated using downstream tasks like fact retrieval. However, existing evaluations vary multiple dataset properties simultaneously,…
An estimator can be accurate and stable on typical data, yet sensitive to a few possible records. Differentially private mechanisms commonly scale their noise to the worst-case influence of a single…