research

arXiv:2604.28147v1 Announce Type: new Abstract: Surprisal theory links human processing effort to the predictability of an upcoming linguistic unit, but empirical work often leaves the notion of a uni

arXiv:2604.27599v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used for recommendation reranking, but their listwise predictions can depend on the order in which candi

arXiv:2604.27674v1 Announce Type: cross Abstract: The hubness problem, in which hub embeddings are close to many unrelated examples, occurs often in high-dimensional embedding spaces and may pose a pr

Companies are taking control of their own data to tailor AI for their needs. The challenge lies in balancing ownership with the safe, trusted flow of high‑quality data needed to power reliable insight

arXiv:2509.23439v2 Announce Type: replace-cross Abstract: We study optimal diagonal preconditioning using the classical worst-case kappa-condition number and the averaging-based omega-condition number

arXiv:2604.27637v1 Announce Type: new Abstract: Current Large Language Model (LLM) evaluation frameworks utilize the same static prompt template across all models under evaluation. This differs from t

arXiv:2604.27201v1 Announce Type: cross Abstract: Hybrid-thinking language models expose explicit think and no-think modes, but current designs do not separate them cleanly. Even in no-think mode, mod

arXiv:2512.23192v3 Announce Type: replace Abstract: While Transformers have demonstrated remarkable potential in modeling Partial Differential Equations (PDEs), modeling large-scale unstructured meshe

arXiv:2507.03478v2 Announce Type: replace-cross Abstract: Image quality assessment (IQA) is crucial in the evaluation stage of novel algorithms operating on images, including traditional and machine l

arXiv:2604.27721v1 Announce Type: cross Abstract: This paper presents a physically-informed fuzzy clustering of vertical sounding ionograms for automatically separating the ionogram into tracks suitab

arXiv:2508.21787v2 Announce Type: replace-cross Abstract: Best-of-n sampling improves the accuracy of large language models (LLMs) and large reasoning models (LRMs) by generating multiple candidate so

arXiv:2604.27313v1 Announce Type: cross Abstract: Operational weather prediction has long relied on physics-based numerical weather prediction (NWP), whose accuracy comes at the cost of substantial co

This IBM Research challenge problem likely involves analyzing mathematical properties of binary matrices (matrices containing only 0s and 1s), potentially exploring topics such as matrix operations, e

arXiv:2601.11908v2 Announce Type: replace Abstract: Large language models (LLMs) struggle with reasoning over long contexts where relevant information is sparsely distributed. Although plan-and-execut

arXiv:2502.14270v3 Announce Type: replace Abstract: Birth weight serves as a fundamental indicator of neonatal health, closely linked to both early medical interventions and long-term developmental ri

arXiv:2604.27892v1 Announce Type: cross Abstract: The rapidly expanding artificial intelligence (AI) industry has produced diverse yet powerful prediction tools, each with its own network architecture

arXiv:2503.01835v2 Announce Type: replace Abstract: Transformers have achieved remarkable success across multiple fields, yet their impact on 3D medical image segmentation remains limited with convolu

arXiv:2604.27379v1 Announce Type: new Abstract: Dialogue models are inherently reactive, responding to the current user turn without anticipating upcoming intents, which leads to redundant interaction

arXiv:2604.28055v1 Announce Type: cross Abstract: Individualized Alzheimer's disease (AD) progression prediction requires models that use irregular visits, account for censoring, avoid diagnostic leak

arXiv:2604.27533v1 Announce Type: new Abstract: Evaluating automatic speech recognition (ASR) systems is a classical but difficult and still open problem, which often boils down to focusing only on th

arXiv:2604.27234v1 Announce Type: new Abstract: Remaining Useful Life (RUL) estimation is a critical component of Prognostics and Health Management (PHM), enabling proactive maintenance scheduling and

arXiv:2604.28075v1 Announce Type: cross Abstract: Recent research has shown that filtering massive English web corpora into high-quality subsets significantly improves training efficiency. However, fo

arXiv:2604.28190v1 Announce Type: new Abstract: We show that Frechet Distance (FD), long considered impractical as a training objective, can in fact be effectively optimized in the representation spac

arXiv:2509.18308v3 Announce Type: replace Abstract: Pulmonary Embolism (PE) is a life-threatening condition for which accurate and timely detection is critical to patient care. However, our systematic

arXiv:2604.27553v1 Announce Type: new Abstract: When the visual style of text is considered, a wide variety can be observed in font, color, and size. However, when a word is read, its meaning is indep

arXiv:2604.27504v1 Announce Type: new Abstract: Recent generative models have shown strong performance in generating diverse 3D assets from 2D images, a fundamental research topic in computer vision a

arXiv:2604.27617v1 Announce Type: cross Abstract: With the widespread application of Unmanned Aerial Vehicles (UAVs) in bridge structural health monitoring, deep learning-based automatic crack detecti

arXiv:2604.28161v1 Announce Type: new Abstract: The robotic manipulation of Deformable Linear Objects (DLOs) is a fundamental challenge due to the high-dimensional, non-linear dynamics of flexible str

【Sakana AI エンジニア募集：正社員＆インターン】🐟 Sakana AIは去年から手掛けてきた金融領域に加えて、防衛・製造業でも次々とプロジェクトが立ち上がっています。 また、Sakana Chat, Sakana Marlin, Sakana Fuguなどを始めとしたプロダクトも続々と生まれてきており、最先端のAI技術で産業価値 を生み出すことを経験できる場が多数存在しています。 App

David Ha announced joining Sakana AI as an Applied Research Engineer, expressing his commitment to making valuable contributions to advancing AI development in Japan. This represents a significant hir

David Ha announced joining Sakana AI as a Product Manager, expressing commitment to bringing the company's technology to the world. The post indicates Ha's transition into a product management role at

arXiv:2604.27447v1 Announce Type: cross Abstract: Modern stochastic optimization pipelines increasingly rely on learned generative models to represent uncertainty, while downstream decisions are evalu

arXiv:2604.27738v1 Announce Type: cross Abstract: Autoregressive Neural Networks based on dense or convolutional layers have recently been shown to be a viable strategy for generating classical spin s

arXiv:2604.27508v1 Announce Type: new Abstract: Understanding human actions is critical for advancing behavior analysis in human-robot interaction. Particularly in tasks that demand quick and proactiv

arXiv:2604.27467v1 Announce Type: cross Abstract: Code sandboxes have emerged as a critical infrastructure for advancing the coding capabilities of large language models, providing verifiable feedback

arXiv:2604.27596v1 Announce Type: new Abstract: In open-world semi-supervised learning (OWSSL), a model learns from labeled data and unlabeled data containing both known and novel classes. In practica

arXiv:2604.27204v1 Announce Type: new Abstract: In the field of universal automatic phonetic transcription (APT), clean and diverse training transcriptions are required. However, such high-quality dat

arXiv:2604.27538v1 Announce Type: new Abstract: Automated plant recognition plays a crucial role in biodiversity monitoring and conservation, yet current approaches rely heavily on supervised learning

arXiv:2604.27169v1 Announce Type: new Abstract: We show that the geometric relations between semantic features in large language models' hidden states closely mirror human psychological associations.

arXiv:2604.28032v1 Announce Type: new Abstract: We study d-dimensional unbiased mean estimation in the single-message shuffle model, where each user sends a single privatized message and the analyzer

arXiv:2510.19110v2 Announce Type: replace-cross Abstract: Modern weather forecasting has increasingly transitioned from numerical weather prediction (NWP) to data-driven machine learning forecasting t

arXiv:2604.26985v1 Announce Type: cross Abstract: Masked diffusion models (MDMs) generate discrete sequences by iterative denoising under an absorbing masking process. In standard masked diffusion, if

arXiv:2604.27899v1 Announce Type: new Abstract: Understanding how human health changes over time, and why responses to interventions vary between individuals, remains a central challenge in medicine.

arXiv:2604.27583v1 Announce Type: cross Abstract: Motion retargeting from humans to human-like artificial agents is becoming increasingly important as humanoid robots grow more capable. However, most

arXiv:2604.28112v1 Announce Type: new Abstract: This work proposes novel splitting techniques for argumentation formalisms that incorporate supports between defeasible elements. We base our studies on

arXiv:2604.27964v1 Announce Type: new Abstract: Assumption-Based Argumentation (ABA) is a well-established formalism for modelling and reasoning over debates, with a wide range of applications. Howeve