research

arXiv:2605.27336v1 Announce Type: new Abstract: Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sa

arXiv:2605.26886v1 Announce Type: cross Abstract: Learning-augmented algorithms have received significant attention in recent years, particularly in the context of online optimization. Motivated by th

arXiv:2510.10774v3 Announce Type: replace-cross Abstract: Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-

arXiv:2605.26821v1 Announce Type: cross Abstract: The Lund plane offers a physics-motivated, hierarchical representation of QCD radiation within jets, while transformer-based taggers have reached stat

arXiv:2605.26802v1 Announce Type: new Abstract: Generating high-fidelity synthetic tabular data under formal differential privacy guarantees remains an open challenge. Methods that provide strong theo

Petraeus: Putin is the personification of evil. He wants to reassemble as much of the former Soviet Union or Russian Empire as he can, and he does not believe Ukraine has a right to exist as an indepe

Physics-informed neural networks (PINNs) are machine learning models that incorporate physical laws and equations as constraints during training to solve differential equations. This post likely discu

arXiv:2605.26689v1 Announce Type: cross Abstract: Modern referring image segmentation pipelines couple a vision-language model (VLM) for grounding with a promptable segmenter such as the Segment Anyth

arXiv:2505.02974v3 Announce Type: replace Abstract: Machine learning-based surrogate models have emerged as a powerful tool to accelerate simulation-driven scientific workflows, but their adoption is

arXiv:2605.26400v1 Announce Type: cross Abstract: We propose a framework for evaluating structured generative search summaries that are placed atop organic web search results. A structured summary, ge

arXiv:2605.27304v1 Announce Type: new Abstract: Automated monitoring of animal welfare has largely targeted negative indicators, leaving positive welfare behaviours such as play underexplored. To addr

arXiv:2605.27101v1 Announce Type: cross Abstract: A key capability for video understanding is reliably linking subjects to events across time, yet whether Video Large Language Models (VideoLLMs) actua

arXiv:2605.26133v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become the predominant paradigm in NLP, advancing both research and industry. As model sizes and pretraining data gr

Google Research presents a zero-trust approach to private analytics that combines cryptographic and hardware protection mechanisms to reduce trust in any single entity. The solution uses a cryptograph

arXiv:2605.26998v1 Announce Type: new Abstract: Inverse reinforcement learning (IRL) recovers reward functions from observed behavior, yet traditional methods assume a single stationary reward that ca

arXiv:2605.27316v1 Announce Type: new Abstract: Probabilistic smoothing is a standard tool for global optimization, but existing methods rely on Gaussian kernels and specific transforms, often resulti

arXiv:2605.26431v1 Announce Type: new Abstract: Structural probes train on Universal Dependencies (UD), which does not encode formal-syntactic abstractions such as phase boundaries or phase-internal c

arXiv:2605.26255v1 Announce Type: cross Abstract: Early prediction of respiratory failure is critical for timely clinical intervention in intensive care units. Existing electronic health record (EHR)-

Proteins are the machinery of life. Scientists have cataloged billions of protein sequences—but their biology is still mostly unknown. Today we're releasing a world model of protein biology: a scienti

arXiv:2605.26801v1 Announce Type: new Abstract: Psychological constructs are often measured in separate instruments, datasets, and research traditions, which makes direct comparison difficult. This pa

arXiv:2507.16116v2 Announce Type: replace Abstract: The rapid advancement of video diffusion models has been hindered by fundamental limitations in temporal modeling, particularly the rigid synchroniz

arXiv:2605.27318v1 Announce Type: new Abstract: Video spatial reasoning requires accumulating viewpoint-dependent evidence over time while retaining information useful to the question being asked. Exi

arXiv:2605.26339v1 Announce Type: cross Abstract: Scalar post-training quantizers discard pairwise coordinate structure within weight rows. We introduce QAM-W (Quadrature Amplitude Modulation for Weig

arXiv:2511.14683v2 Announce Type: replace Abstract: Heaps' or Herdan's law characterizes the word-type vs. word-token relation by a power-law function, which is concave in linear-linear scale but a st

arXiv:2605.26770v1 Announce Type: new Abstract: Prior work shows that Large Language Models (LLMs) can transform Explainable AI (XAI) outputs into Natural Language Explanations (NLEs) that score highl

arXiv:2003.05746v4 Announce Type: replace-cross Abstract: In this paper, we explore the issue of inconsistency handling over prioritized knowledge bases (KBs), which consist of an ontology, a set of f

arXiv:2605.26519v1 Announce Type: new Abstract: Recent feed-forward geometry foundation models have demonstrated impressive generalization by recovering depth and poses in a single forward pass. Howev

arXiv:2605.26328v1 Announce Type: new Abstract: Radars are an ideal complement to cameras: both are inexpensive, solid-state sensors, with cameras offering fine angular resolution, while radars provid

arXiv:2602.03517v2 Announce Type: replace Abstract: Many decision-making problems require ranking individuals by their treatment effects rather than estimating the exact effect magnitudes. Examples in

arXiv:2605.26127v1 Announce Type: cross Abstract: Purpose: Real-time (RT) bSSFP MRI enables fast free-breathing cardiovascular imaging but requires 10-16 slices for functional assessment, resulting in

arXiv:2605.26854v1 Announce Type: new Abstract: The scalable solution of large sparse linear systems is a bottleneck in scientific computing and graph analysis. While algebraic multigrid (AMG) offers

arXiv:2605.26513v1 Announce Type: new Abstract: Mean Deviation (MD) is a critical metric for assessing visual field loss in ophthalmology. While previous work has focused solely on predicting MD from

arXiv:2605.26525v1 Announce Type: cross Abstract: Minute-scale cinematic video generation is a central challenge for generative video models. Existing paradigms address only fragments of this challeng

arXiv:2605.26969v1 Announce Type: cross Abstract: User modeling aims to use language models (LMs) to mimic an individual's behavior from a corpus of past context-action pairs (e.g., conversation turns

arXiv:2512.01572v3 Announce Type: replace-cross Abstract: Extreme sensor sparsity makes full-field reconstruction a fundamentally ill-posed problem in scientific sensing,where the goal is to infer phy

arXiv:2605.26535v1 Announce Type: cross Abstract: Generative models have emerged as a powerful paradigm for solving physics systems and modeling complex spatiotemporal dynamics. However, achieving hig

arXiv:1909.08210v4 Announce Type: replace Abstract: A restricted Boltzmann machine (RBM) is a two-layer neural network with shared weights and has been extensively studied for dimensionality reduction

arXiv:2605.26327v1 Announce Type: new Abstract: Shampoo-based methods, such as KL-Shampoo and SOAP, have demonstrated strong performance in training neural networks and rely on QR decomposition. Becau

arXiv:2605.26177v1 Announce Type: cross Abstract: Code agents are currently having skillful performance on repository-level software engineering benchmarks, but it remains unclear whether success on e

arXiv:2605.26661v1 Announce Type: cross Abstract: Out-of-distribution (OOD) detection has emerged as a popular technique to enhance the reliability of machine learning models by identifying unexpected

arXiv:2605.26921v1 Announce Type: new Abstract: The study of representations is widespread across fields, including neuroscience, psychology, and artificial intelligence. While representations are oft

arXiv:2605.26241v1 Announce Type: new Abstract: Success in generative modeling across language, image, and video demonstrates that large, well-curated datasets are the key driver for building capable

arXiv:2605.26702v1 Announce Type: cross Abstract: Reliable watermarking of panoramic imagery is fundamentally challenged by arbitrary 3D rotations. As panoramas are defined on the sphere, they natural

arXiv:2504.02993v2 Announce Type: replace-cross Abstract: In this paper, we aim to mitigate congestion in traffic management systems by guiding travelers along system-optimal (SO) routes. However, we

Sakana AIのオフィスが入居する麻布台ヒルズなどを運営する森ビルのウェブメディア「HILLS LIFE DAILY」に、Sakana AIリサーチサイエンティストのカラーヌワット・タリンへのインタビュー記事が掲載されました。 麻布台ヒルズのデジタルサイネージで上映中の浮世絵風画像生成プロジェクトを起点に、 日本文化を理解するAIモデルの可能性について語っています。約12,000枚の浮世絵でフ

arXiv:2605.27006v1 Announce Type: new Abstract: Sampling from learned high-dimensional distributions is a foundational computational problem. We introduce U-turn chains: Markov chains obtained by iter