Search: “research”

arXiv:2605.12813v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong performance across many tasks but remain vulnerable to hallucinations, motivating the need for realistic a

arXiv:2605.12578v1 Announce Type: cross Abstract: The integration of terahertz communications and ultra-massive multiple-input multiple-output (UM-MIMO) systems in 6G networks is motivated by their ab

arXiv:2510.14244v2 Announce Type: replace-cross Abstract: Domain adaptation methods aim to bridge the gap between datasets by enabling knowledge transfer across domains, reducing the need for addition

arXiv:2605.13031v1 Announce Type: cross Abstract: This paper addresses the problem of estimating the relative pose (position and orientation) and velocity of a vehicle with respect to a moving target,

arXiv:2411.15913v4 Announce Type: replace-cross Abstract: Music style transfer blends source structure with reference style to enable personalized music creation. However, existing zero-shot methods o

arXiv:2605.13129v1 Announce Type: cross Abstract: Recent 3D generative models can synthesize high-quality assets, but their outputs are typically static: they lack the skeletal rigs, joint hierarchies

arXiv:2603.20527v3 Announce Type: replace Abstract: Preconditioned adaptive methods have gained significant attention for training deep neural networks, as they capture rich curvature information of t

arXiv:2605.13730v1 Announce Type: cross Abstract: Transthoracic echocardiography (TTE) is the first-line imaging modality for diagnosing bicuspid aortic valve (BAV), yet diagnostic performance varies

【採用情報】Sakana AIで「Public Sector Specialist」を募集🐟 https://sakana.ai/careers/#public-sector-specialist Sakana AIの最先端技術を官公庁と連携し社会実装していくための ドキュメンテーション戦略の立案・実行を担っていただきます。 👉 このようなご経験をお持ちの方を募集 ・政府機関での予算要求・政策立案

arXiv:2509.23800v3 Announce Type: replace-cross Abstract: Modern generative AI models, such as diffusion and flow matching models, can sample from rich data distributions. However, many applications,

arXiv:2605.13681v1 Announce Type: new Abstract: Flow Language Models (FLMs) are a recently introduced class of language models which adapt continuous flow matching for one-hot encoded token sequences.

arXiv:2310.07844v2 Announce Type: replace Abstract: We propose a novel angular velocity estimation method to increase the robustness of Simultaneous Localization And Mapping (SLAM) algorithms against

arXiv:2605.13684v1 Announce Type: new Abstract: We study the optimal scale at which real-valued function classes exhibit uniform convergence and learnability. Our main result establishes a scale-sensi

arXiv:2605.12715v1 Announce Type: new Abstract: As language models scale, the amount of data they require grows -- yet many target data sources, such as low-resource languages or specialized domains,

arXiv:2605.13667v1 Announce Type: new Abstract: Scene graph generation provides a compact structured representation for visual perception, but accurate and fast graph prediction from images and videos

arXiv:2509.21543v3 Announce Type: replace Abstract: Large Language Models (LLMs) have shown strong promise for robotic task planning, particularly through the automatic generation of symbolic planning

arXiv:2605.12945v1 Announce Type: new Abstract: Shortcut features are often invoked to explain out-of-distribution (OOD) failure, but training correlation, learned shortcut use, and test-time failure

arXiv:2605.12748v1 Announce Type: cross Abstract: Large language models (LLMs) can fluently generate student-like responses, making them attractive as simulated students for training and evaluating AI

arXiv:2510.11303v2 Announce Type: replace Abstract: Sketch-based 3D reconstruction remains a challenging task due to the abstract and sparse nature of sketch inputs, which often lack sufficient semant

arXiv:2605.13079v1 Announce Type: cross Abstract: Muon orthogonalizes the momentum buffer before each update, replacing its singular values with ones via Newton-Schulz iterations. This simple change l

arXiv:2605.13181v1 Announce Type: cross Abstract: Precipitation nowcasting remains challenging due to the highly localized, rapidly evolving, and heterogeneous nature of atmospheric dynamics. Although

arXiv:2605.13127v1 Announce Type: cross Abstract: Determinantal point processes (DPPs) have emerged as a kernelized alternative to vanilla independent sampling for generating efficient minibatches, co

arXiv:2605.12890v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) has made machine-generated text increasingly difficult to distinguish from human-written text. W

arXiv:2605.13426v1 Announce Type: new Abstract: Strategic classification studies learning settings in which individuals can modify their features, at a cost, in order to influence the classifier's dec

arXiv:2605.13153v1 Announce Type: new Abstract: Temporal Knowledge Graph Reasoning (TKGR) aims at inferring missing (especially future) events from historical data. Current evaluation in TKGR uniforml

arXiv:2605.13333v1 Announce Type: cross Abstract: Text-driven motion diffusion models are capable of generating realistic human motions, but text alone often struggles to express fine-level nuances of

arXiv:2602.23013v3 Announce Type: replace Abstract: Detecting visual anomalies in industrial inspection often requires training with only a few normal images per category. Recent few-shot methods achi

arXiv:2605.13312v1 Announce Type: new Abstract: We present Supervised Deep Multimodal Matrix Factorization (SD3MF), an interpretable framework for integrative brain network analysis that generalizes S

arXiv:2605.13386v1 Announce Type: new Abstract: Generative models are often conditioned on a small set of examples via cross-attention. Under the Gaussian optimal-transport path, we show that the exac

arXiv:2601.17326v2 Announce Type: replace Abstract: Retinal prostheses restore limited visual perception, but low spatial resolution and temporal persistence make reading difficult. In sequential lett

arXiv:2506.12075v2 Announce Type: replace-cross Abstract: High school English Literature teachers often encounter barriers to assembling diverse, thematically aligned text sets due to limited planning

arXiv:2605.13384v1 Announce Type: new Abstract: Most models of machine teaching and learning assume the learner makes no errors in its internal deductive inference. However, humans and large language

The Art of the Steal: 1. IRS catches Trump cheating on his taxes. 2. Trump sues IRS for catching him cheating on his taxes. 3. DOJ helps Trump get $10 billion from the IRS because they caught him chea

arXiv:2510.04698v3 Announce Type: replace-cross Abstract: Humans systematically misrepresent probability in a stereotyped inverse-S pattern. It has been documented for decades, but its origin remains

arXiv:2605.13399v1 Announce Type: new Abstract: We construct a new kind of encoder, leveraging the expressive power of diffusion models. In a traditional variational autoencoder, the encoder and decod

arXiv:2605.12928v1 Announce Type: new Abstract: Modern language models have historically relied on two dominant design choices: subword tokenization and autoregressive (AR) ordering. These design deci

arXiv:2605.12940v1 Announce Type: cross Abstract: Probabilistic Circuits (PCs) are deep generative models that support exact and efficient probabilistic inference. Yet in autoregressive language model

The JAX package is now around the same level, 20M monthly downloads. Which is incredibly fast growth, because 5 years ago I recall it being below 2M or so. It went from niche to mainstream in the past

The Keras package recently crossed 21M monthly downloads on PyPI, an all-time high (the daily ATH is around 900k). I still remember when it first crossed 10M monthly downloads about 5 years ago and I

arXiv:2605.12908v1 Announce Type: cross Abstract: Weak-to-strong (W2S) generalization, in which a strong model is fine-tuned on outputs of a weaker, task-specialized model, has been proposed as an app

The quantity of code that devs ship has roughly 10xed. But net developer productivity (value created by unit of time) is only up by a bit, if at all. Part of it is that the additional code is solving

arXiv:2605.13252v1 Announce Type: cross Abstract: We study multiple change point localization under bandit feedback. An unknown piecewise-constant function on a compact interval can be queried sequent

arXiv:2304.12906v4 Announce Type: replace Abstract: Implicit generative modeling (IGM) aims to produce samples of synthetic data matching the characteristics of a target data distribution. Recent work

This one blew my mind back in the day! From 'Learning Invariant Features through Topographic Filter Maps' (2009) by @koraykv, @MarcRanzato, @rob_fergus and @ylecun Relics from the prehistoric era of A

This reminds me of computerization. The amount of 'work' people could execute on computers increased by a huge factor, but their productivity did not. The amount of work 'needed' to arrive at the same

arXiv:2605.13678v1 Announce Type: new Abstract: Recent studies on long-term time series forecasting have shown that simple linear models and MLP-based predictors can achieve strong performance without