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。
Automatic speech recognition (ASR) systems often perform less accurately for speakers of regional dialects, but less is known about how users respond to these limitations and how regional voices…
Modern machine learning models are often trained on large datasets assembled from many different sources, whose statistical properties can differ substantially. Understanding how this heterogeneity…
Vision-language-action (VLA) policies can learn to follow execution preferences, such as where to grasp an object or how to move around an obstacle, from demonstrations annotated with preference…
We describe the QMUL_AK submission to AISA-ArabicFC 2026. The system adapts the Arabic-English ALLaM-7B-Instruct model to function calling with low-rank adaptation (LoRA).
In micromanipulation, erroneous hand motion limits unaided manipulation accuracy, which can affect task performance and safety in critical applications like microsurgery. Handheld robots…
This paper presents a two-stage learning framework for versatile and agile humanoid locomotion that couples online reduced-order model (ROM) reference generation with whole-body tracking control. In…
Generative flows can admit different velocity fields that induce the same continuous marginal evolution but behave differently after numerical discretization. We study this finite-step…
Latent multi-agent systems reduce inference cost by keeping intermediate reasoning and inter-agent communication in continuous representations.\ Reusable skills, however, are commonly supplied as…
Radar systems can recover scene geometry and recognize predefined categories, but these outputs do not provide a persistent spatial representation for open-ended language queries. Such queries…
Key-value (KV) caching is a core mechanism in large language models, where intermediate key and value representations are stored to accelerate autoregressive decoding. As generation length increases,…
Large language model agents are increasingly used for scientific discovery. However, existing benchmarks mix law inference with programming, score data fitting instead of prediction on unseen inputs,…
Vision-Language-Action (VLA) models offer a promising paradigm for general-purpose household robotics. However, inference and data-collection strategies that have been deployed in smaller-scale…
Many open mixture-of-experts (MoE) language models train with Muon instead of AdamW. Most balance the load with a bias on each expert's routing score, adjusted after every step.
We propose a multimodal transformer framework for efficiently modeling long1 financial documents that combine structured tabular data with noisy, unstructured2 textual disclosures. The framework…
Utterance-level similarity ratings do not reveal where perceived accent differences occur in generated speech. We introduce a segmental evaluation protocol combining speaker and accent similarity…
Metis is a bet that better data, better training methods and new architectures can buy what a bigger parameter count cannot, at a fraction of the cost. Metis-1.6 is its latest step: two language…
On PushT, our fixed action updater (1,505 parameters) solves 8 of 16 scenes reserved from our configuration selection. The comparison planners perform as follows: Selected Adam (7 tasks solved, total…
International climate policy requires coordination among countries whose mitigation decisions impose local costs but generate global benefits. Classical game-theoretic and integrated assessment…
Large language models (LLMs) are widely used as automated judges, yet most alignment methods target aggregated human judgments and overlook variation among individual annotators. Existing approaches…
We study conformal prediction under covariate shift with a known covariate density ratio, seeking prediction sets with minimum expected length under the target distribution. For every calibration…
Scaling visual reinforcement learning (RL) with GPU-accelerated simulation is computationally expensive due to rendering and visual-policy inference costs. Consequently, two-stage teacher--student…
AI agents that share a secret convention can coordinate through messages that look innocent, so a monitor that reads only the messages can miss them. We propose a behavioural test: a partner that…
This work considers projection-free online learning algorithms with linear minimization oracles for handling the decision set. For Online Frank--Wolfe (OFW), regret upper bounds were already known…
Deep neural networks learn data-dependent features, a capacity widely credited for their empirical success. However, explicitly characterizing what features emerge -- and when they improve…