Knowledge catalogue
arXiv:2605.25868v1 Announce Type: cross Abstract: The speed and accuracy of an artificial teammate fundamentally alter the failure states of Human-AI integration. While high-speed AI interventions ris
arXiv:2605.24718v1 Announce Type: new Abstract: Tokenizer fertility the number of tokens per word imposes a hidden cost on non-English NLP. We measure fertility for ten foundation models across 25 Eur
arXiv:2605.25134v1 Announce Type: cross Abstract: Sparse optimization is a fundamental challenge in various practical applications. A popular approach to sparse optimization is ell_p regularization. H
arXiv:2605.25208v1 Announce Type: new Abstract: Emotion-Cause Pair Extraction (ECPE) was introduced to explain why an emotion occurs, but this goal is now often reduced to binary pair/non-pair predict
arXiv:2605.24489v1 Announce Type: new Abstract: Enzyme-reaction retrieval is a fundamental problem in computational biology, underpinning enzyme characterization, reaction mechanism elucidation, and t
TinkerAPI, developed by TML, is a post-training infrastructure tool that Soumith Chintala recommends as an essential component for new AI companies during their startup phase. The tool appears to addr
arXiv:2605.25046v1 Announce Type: cross Abstract: YOLO-series and DETR-based detectors struggle with tiny-object detection. YOLO-style models benefit from efficient dense prediction, but their large-s
arXiv:2605.25399v1 Announce Type: new Abstract: Objective: Survival analysis is central to medical prediction, yet large language models (LLMs) are rarely used as end-to-end survival models because ce
arXiv:2605.24213v1 Announce Type: cross Abstract: Evaluation harnesses are software systems that orchestrate model evaluation by managing model invocation, data loading, metric computation, and result
arXiv:2602.01914v2 Announce Type: replace Abstract: Token attribution methods provide intuitive explanations for language model outputs by identifying causally important input tokens. However, as mode
arXiv:2605.24526v1 Announce Type: cross Abstract: Interactive assistance systems typically provide feedback after an action has been completed, supporting error recovery but not preventing the error i
arXiv:2401.01160v3 Announce Type: replace-cross Abstract: We investigate a framework for train-free MRI segmentation based on Topological Data Analysis. The pipeline proceeds in three steps, first ide
arXiv:2402.08726v2 Announce Type: replace-cross Abstract: We study quantum neural networks made by parametric one-qubit gates and fixed two-qubit gates in the limit of infinite width, where the genera
arXiv:2605.24680v1 Announce Type: new Abstract: Gradient-boosted trees achieve strong performance on tabular data, yet often leave a long tail of poorly predicted instances. We introduce a Trajectory-
arXiv:2408.08399v3 Announce Type: replace Abstract: Electricity Consumption Profiles (ECPs) are crucial for operating and planning power distribution systems, especially with the increasing number of
arXiv:2605.25969v1 Announce Type: new Abstract: Causal Transformer language models suffer from strictly sequential decoding and a quadratic per-step attention cost. While linear-time causal models and
arXiv:2605.23988v1 Announce Type: cross Abstract: Adapting large AI models (LAMs) to personalized edge data is challenging because wireless devices have limited memory, computation, and uplink capacit
arXiv:2605.24292v1 Announce Type: new Abstract: Log-likelihood is a standard metric for evaluating generative models. Unfortunately, in contrast to autoregressive models (ARMs), discrete diffusion mod
arXiv:2601.14340v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are widely integrated into interactive systems such as dialogue agents and task-oriented assistants. This growing
arXiv:2410.15173v4 Announce Type: replace-cross Abstract: The thematic fit estimation task measures semantic arguments' compatibility with a given semantic role for a given predicate. We investigate i
arXiv:2509.23573v4 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used to help security analysts manage the surge of cyber threats, automating tasks from vulnerab
arXiv:2511.19065v2 Announce Type: replace-cross Abstract: MeanFlow promises high-quality generative modeling in few steps, by jointly learning instantaneous and average velocity fields. Yet, the under
arXiv:2605.24642v1 Announce Type: cross Abstract: Recent work explores new opportunities at the intersection of vision-language-action models (VLAs) and geometric foundation models (GFMs) for 3D recon
arXiv:2605.25903v1 Announce Type: new Abstract: Activation verbalization explains hidden representations in natural language, but existing methods are mostly limited to self-explanation, where each mo
arXiv:2212.07944v3 Announce Type: replace Abstract: We study a multi-factor block model for variable clustering and connect it to regularized subspace clustering through a distributionally robust vers
arXiv:2605.24084v1 Announce Type: cross Abstract: Shapley additive explanations (SHAP) are widely recognised as computationally intractable for neural networks, since they induce an exponential search
arXiv:2605.24031v1 Announce Type: cross Abstract: We study the reconstruction of implied volatility surfaces from sparse and noisy option quotes using deep learning models under no-arbitrage constrain
arXiv:2510.15514v3 Announce Type: replace Abstract: Reinforcement Learning from AI Feedback (RLAIF) relies on LLM judges as preference measurement instruments, yet these instruments are fundamentally
arXiv:2510.16435v2 Announce Type: replace-cross Abstract: With the growing use of large language models and conversational interfaces in human-robot interaction, robots' ability to answer user questio
arXiv:2605.24296v1 Announce Type: new Abstract: We study when LLM-generated synthetic data helps low-resource multi-label patent classification, separating true synthetic value from the confound that
arXiv:2605.26046v1 Announce Type: cross Abstract: Customizing an LLM judge to a specific task or domain often involves optimizing its prompt across multiple evaluation criteria simultaneously. Textual
arXiv:2605.25629v1 Announce Type: new Abstract: Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train--t
arXiv:2510.08609v3 Announce Type: replace-cross Abstract: Developers consistently use version constraints to specify acceptable versions of the dependencies for their project. Pinning dependencies can
arXiv:2605.24651v1 Announce Type: cross Abstract: We propose a Weak-form Physics-Informed Neural Operator (WINO), a data-free framework that combines the efficiency of neural operators with the geomet
arXiv:2605.24585v1 Announce Type: new Abstract: Language models are typically trained to predict the next token in a sequence. Here, we explore an alternative predictive principle from reinforcement l
arXiv:2605.24034v1 Announce Type: cross Abstract: Chromatin regulators can alter transcriptional programs by modifying the accessibility of regulatory DNA elements. Understanding how regulatory sequen
arXiv:2303.07863v3 Announce Type: replace-cross Abstract: Given an untrimmed video, temporal sentence grounding (TSG) aims to locate a target moment semantically according to a sentence query. Althoug
arXiv:2605.24806v1 Announce Type: cross Abstract: Large audio and language models have recently demonstrated zero-shot reasoning capabilities across various domains. However, it remains unclear how th
arXiv:2605.24513v1 Announce Type: new Abstract: This paper considers the nonconvex nonsmooth problem in which the objective function is Lipschitz continuous. We focus on the stochastic setting where t
5月25日、内閣総理大臣官邸で開催された車座対談に、Sakana AIの伊藤錬が参加しました。 金融など各産業に特化した高度なAI実装の実例をご紹介しました。また、海外の先端モデルも活用しつつ、日本独自の技術で、我が国の防衛の自律性やデータ主権を確保する具体的方法についても高市総理と貴重な意見 交換の機会をいただきました。 本日、スタートアップ４社（Atomis、Sakana AI、Oceanic
arXiv:2410.19842v2 Announce Type: replace-cross Abstract: Contrastive learning yields impressive results for self-supervision in computer vision. The approach relies on the creation of positive pairs,
arXiv:2508.18958v2 Announce Type: replace-cross Abstract: Obtaining pixel-level annotations over large spatial extents remains a major bottleneck for deploying machine learning in ecological applicati
arXiv:2605.23103v1 Announce Type: cross Abstract: I present Lepton (Letter Prediction), a fine-tuned BERT classifier that predicts whether a title in a Classical Chinese wenji table of contents is a p
arXiv:2605.23710v1 Announce Type: new Abstract: Semantic type mismatch between a noun and its context is central to coercion phenomena. This paper introduces a graph-based method to examine how lexica
arXiv:2605.23258v1 Announce Type: new Abstract: KV cache growth is a major bottleneck for long-context inference in large language models. Existing methods are often dominated by binary eviction or re
arXiv:2510.15060v3 Announce Type: replace Abstract: One-year-old infants rapidly form and generalize categories of the everyday objects they encounter. Here we provide evidence on infants daily-life v
arXiv:2605.22828v1 Announce Type: new Abstract: This survey provides a comprehensive catalog of publicly available text and speech resources for two West African languages: Hausa, an Afroasiatic langu
arXiv:2605.23295v1 Announce Type: cross Abstract: Spatial photonic Ising machines (SPIMs) based on spatial light modulators (SLMs) have emerged as highly effective solvers for many tasks, including co
arXiv:2605.22988v1 Announce Type: cross Abstract: Active sensing is traditionally defined as the expenditure of energy, typically in the form of movement, for obtaining information. Here, we propose t
arXiv:2605.23200v1 Announce Type: cross Abstract: The linear growth of the Key-Value (KV) cache is a critical bottleneck in long-form LLM inference. Existing KV compression methods mitigate this by ev
arXiv:2605.23623v1 Announce Type: cross Abstract: We present a longitudinal, drift-aware evaluation of adversarial robustness across more than a decade of Android applications using static and dynamic
arXiv:2601.17261v4 Announce Type: replace Abstract: Zeroth-Order (ZO) optimization has emerged as a promising solution for fine-tuning LLMs under strict memory constraints, as it avoids the prohibitiv
arXiv:2605.22923v1 Announce Type: cross Abstract: Large language models can answer questions about textbooks, lecture notes, and programming exercises more reliably when their answers are grounded in
arXiv:2601.22367v2 Announce Type: replace-cross Abstract: Generalized Bayesian Inference (GBI) tempers a loss with a temperature eta > 0 to mitigate overconfidence and improve robustness under model m
arXiv:2605.22824v1 Announce Type: cross Abstract: Environmental monitoring is a crucial component of the smart city infrastructure. It enables informed decision making which enhances sustainability, p
arXiv:2605.23156v1 Announce Type: new Abstract: Several machine learning models are defined for inputs of any size, such as graphs with different numbers of nodes and point clouds containing varying n
arXiv:2602.07235v2 Announce Type: replace-cross Abstract: Watermarking is an important tool for promoting the responsible use of large language models (LLMs). Existing watermarks insert a signal into
arXiv:2509.06896v2 Announce Type: replace Abstract: Targeted data poisoning attacks manipulate model predictions on specific test samples by injecting malicious data into training. Yet existing evalua
arXiv:2605.23591v1 Announce Type: cross Abstract: We introduce a model for neural scaling laws under sparse activations. In the model, test loss is often dominated by rare coordinates that are never o
arXiv:2601.22324v2 Announce Type: replace Abstract: Modern clinical practice relies on evidence-based guidelines implemented as compact scoring systems composed of a small number of interpretable deci