Knowledge catalogue
日経デジタルガバナンスにて、Sakana AIの「事後学習」技術と Sakana Chat / Namazuモデルに関する記事が掲載されました。 Namazuモデル開発をリードしたリサーチサイエンティストの菅沼雅徳とチーフサイエンティストの秋葉拓哉に取材いただきました。 記事: https://www.nikkei.com/prime/digital-governance/article/DGXZ
arXiv:2605.02897v1 Announce Type: cross Abstract: LLM assistant personalities play a critical role in user experience and perceived response quality. We present a large-scale experiment of frontier LL
arXiv:2605.04560v1 Announce Type: new Abstract: Perceptual image compression focuses on preserving high visual quality under low-bitrate constraints. Most existing approaches to perceptual compression
arXiv:2605.04496v1 Announce Type: new Abstract: Long-Text Understanding (LTU) at million-token scale requires balancing reasoning fidelity with computational efficiency. Frontier long-context LLMs can
arXiv:2605.05057v1 Announce Type: new Abstract: Open-vocabulary human-object interaction (HOI) detection requires recognizing interaction phrases that may not appear as annotated categories during tra
arXiv:2508.00049v2 Announce Type: cross Abstract: The formation of dark-matter halos from small cosmological perturbations generated in the early universe is a highly non-linear process typically mode
arXiv:2605.04887v1 Announce Type: new Abstract: The exponential expansion of digital commerce in Indonesia has significantly shifted consumer interactions toward video-centric social networks, particu
arXiv:2605.04126v1 Announce Type: new Abstract: This paper develops convolutional neural network (CNN) methods for simultaneous approximation and elliptic boundary value problems on compact Riemannian
arXiv:2602.03204v2 Announce Type: replace Abstract: While Mixture-of-Experts (MoE) architectures define the state-of-the-art, their theoretical success is often attributed to heuristic efficiency rath
arXiv:2605.03202v1 Announce Type: new Abstract: Large language models offer a tempting solution to address the peer review crisis. This position paper argues that today's AI systems should not be used
arXiv:2605.04412v1 Announce Type: new Abstract: 3D asset generation plays a pivotal role in fields such as gaming and virtual reality, enabling the rapid synthesis of high-fidelity 3D objects from a s
arXiv:2605.05151v1 Announce Type: new Abstract: Transformer architectures have been widely adopted for time series forecasting, yet whether the representational mechanisms that make them powerful in N
arXiv:2605.05206v1 Announce Type: new Abstract: We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small
This is today’s edition of The Download, our weekday newsletter that provides a daily dose of what’s going on in the world of technology. What’s next for IVF IVF has brought millions of babies into th
arXiv:2605.05166v1 Announce Type: new Abstract: Self-consistency detects hallucinations by generating multiple sampled answers to a question and measuring agreement, but this requires repeated decodin
arXiv:2605.04196v1 Announce Type: new Abstract: Knowledge transfer, especially across related languages, has been found beneficial for multilingual neural machine translation (MNMT), but some aspects
arXiv:2602.14872v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mys
arXiv:2605.05066v1 Announce Type: new Abstract: We identify and prove a fundamental trade-off governing long-sequence models: no model can simultaneously achieve (i) per-step computation independent o
arXiv:2605.04552v1 Announce Type: new Abstract: Media coverage influences disaster response, yet the drivers of international media attention to local events remain unevenly understood. Brazil offers
arXiv:2605.05080v1 Announce Type: new Abstract: We administer 45 validated psychometric questionnaires to 50 large language models (LLMs) to identify the dimensions along which LLMs differ psychometri
arXiv:2507.14874v2 Announce Type: replace Abstract: Pattern recognition with concise and flat AND-rules makes the Tsetlin Machine (TM) both interpretable and efficient, while the power of Tsetlin auto
arXiv:2603.14764v3 Announce Type: replace Abstract: Geometric data augmentation is widely used in segmentation workflows, but polygon annotations are often assumed to remain valid after transformation
Total Jobs Created by Party (1989-2026): Democratic Presidents 50,600,000 Republican Presidents 1,469,000 The biggest scam the GOP has ever pulled off is convincing people that Republicans are good fo
arXiv:2605.04070v1 Announce Type: cross Abstract: Human-AI complementarity, the idea that combining human and AI judgments can outperform either alone, offers a promising pathway toward robust oversig
arXiv:2602.03396v3 Announce Type: replace Abstract: Proprietary large language models (LLMs) embody substantial economic value and are generally exposed only as black-box APIs, yet adversaries can sti
arXiv:2605.05133v1 Announce Type: new Abstract: Multi-Output Gaussian Processes (MOGPs) provide a principled probabilistic framework for modelling correlated outputs but face scalability bottlenecks w
arXiv:2605.04827v1 Announce Type: new Abstract: Label Distribution Learning (LDL) models supervision as an instance-wise probability distribution, enabling fine-grained learning under inherent ambigui
arXiv:2603.01097v2 Announce Type: replace Abstract: Continuous knowledge updating for pre-trained large language models (LLMs) is increasingly necessary yet remains challenging. Although inference-tim
arXiv:2508.08289v2 Announce Type: replace Abstract: Transformer architectures have revolutionized artificial intelligence (AI) through their attention mechanisms, yet the computational principles unde
arXiv:2605.04209v1 Announce Type: cross Abstract: We present Sparse Backdoor, a supply-chain attack that plants a provably undetectable backdoor in pre-trained image classifiers, including convolution
arXiv:2605.04926v1 Announce Type: new Abstract: Promotional language has been increasingly used to aid the communication of innovative ideas in science. Yet, less is known about its role in the contex
arXiv:2605.04635v1 Announce Type: new Abstract: Printed Circuit Board (PCB) defect inspection faces two compounding challenges: scarce and imbalanced defect samples that limit model training, and insu
arXiv:2605.04750v1 Announce Type: new Abstract: Identification of less-articulated objects using single-channel images, such as thermal images, is important in many applications, such as surveillance.
arXiv:2601.21851v2 Announce Type: replace Abstract: Foundation models, despite their robust zero-shot capabilities, remain vulnerable to spurious correlations and 'Clever Hans' strategies. Existing mi
arXiv:2605.04705v1 Announce Type: cross Abstract: Today, advances in medical technology extensively utilize 3D volume data for accurate and efficient diagnostics. However, sharing these data across ne
arXiv:2510.24215v4 Announce Type: replace-cross Abstract: Recovery from linear measurements under sparse adversarial corruption is typically formulated as an exact-recovery problem: one seeks structur
MIT Technology Review’s What’s Next series looks across industries, trends, and technologies to give you a first look at the future. You can read the rest of them here. Forty-eight years ago this July
arXiv:2605.04930v1 Announce Type: new Abstract: Despite theoretical advantages, causal methods for Gene Regulatory Network (GRN) inference from single-cell RNA-seq data consistently fail to match or o
arXiv:2507.20021v3 Announce Type: replace-cross Abstract: Recent ObjectNav systems credit large language models (LLMs) for sizable zero-shot gains, yet it remains unclear how much comes from language
arXiv:2605.05045v1 Announce Type: cross Abstract: Vision-language models (VLMs) achieve strong multimodal performance but remain prone to relation hallucination, which requires accurate reasoning over
arXiv:2605.04971v1 Announce Type: cross Abstract: Weight matrices in deep networks exhibit geometric continuity -- principal singular vectors of adjacent layers point in similar directions. While this
arXiv:2605.03996v1 Announce Type: new Abstract: Nowadays as convolution neural networks demonstrate its powerful problem-solving ability in the area of image processing, efforts have been made to reco
arXiv:2602.10094v2 Announce Type: replace Abstract: We present 4RC, a unified feed-forward framework for 4D reconstruction from monocular videos. Unlike existing approaches that typically decouple mot
arXiv:2507.23045v2 Announce Type: replace Abstract: Automatic extrinsic sensor calibration is a fundamental problem for multi-sensor platforms. Reliable and general-purpose solutions should be computa
arXiv:2605.04046v1 Announce Type: new Abstract: We introduce PALACE (Persistence Adaptive-Landmark Analytic Classification Engine), the data-adaptive companion to PLACE, paying a small cross-validatio
arXiv:2605.03360v1 Announce Type: cross Abstract: We present A-CODE, a fully atomic unified one-stage protein co-design model that simultaneously refines discrete atom types and continuous atom coordi
arXiv:2605.03696v1 Announce Type: new Abstract: The performance of end-to-end automatic speech recognition (ASR) systems enables their increasing integration into numerous applications. While there ar
arXiv:2605.03499v1 Announce Type: new Abstract: We study expected generalization bounds for the Hierarchical Federated Learning (HFL) setup using Wasserstein distance. We introduce a generalized frame
arXiv:2507.04330v2 Announce Type: replace-cross Abstract: We consider the problem of sampling from a probability distribution pi which admits a density w.r.t. a dominating measure. It is well known th
arXiv:2605.03671v1 Announce Type: new Abstract: The most commonly used metrics for evaluating automatic speech transcriptions, namely Word Error Rate (WER) and Character Error Rate (CER), have been he
arXiv:2605.03203v1 Announce Type: cross Abstract: An alternative generating function is proposed to enumerate row-convex polyominoes without internal holes on a discrete grid. The approach is based on
arXiv:2508.13100v3 Announce Type: replace Abstract: Calibration requires that predictions are conditionally unbiased and, therefore, reliably interpretable as probabilities. A calibration measure quan
arXiv:2605.01078v1 Announce Type: cross Abstract: Retrieval-augmented generation and tool-integrated LLM agents increasingly depend on external textual sources. This reliance broadens the available at
arXiv:2605.01282v1 Announce Type: cross Abstract: In MRI, variations in scan parameters, sequence, or hardware can lead to discrepancies in image appearance, even for the same subject. These inconsist
arXiv:2605.02903v1 Announce Type: cross Abstract: In recent years, AI systems in the medical domain have advanced significantly. However, despite outperforming humans, they are rarely used in practice
arXiv:2505.24791v2 Announce Type: replace Abstract: Discrete normalizing flows are promising generative models with advantages such as analytical log-likelihood computation and end-to-end training. Ho
arXiv:2605.03085v1 Announce Type: new Abstract: Electroencephalography (EEG) signals provide millisecond-level temporal resolution but their analysis is limited by remarkable noise and inter-subject v
arXiv:2605.03393v1 Announce Type: cross Abstract: Contextual MDPs are powerful tools with wide applicability in areas from biostatistics to machine learning. However, specializing them to offline data
arXiv:2605.03495v1 Announce Type: new Abstract: We develop graph-based methods for semi-supervised learning based on label propagation on a data similarity graph. When data is abundant or arrive in a
AI agents often struggle to plan movements because their internal representations of the physical world can be overly tangled. CDS PhD student Ying Wang (@yingwww_) shows how straightening these pathw