Knowledge catalogue
What will we be like when he is gone? Can we return to mutual respect? Can we believe we are all on the same team as Obama and McCain did? Can we imagine the mutual respect of those two, competitors b
arXiv:2605.07969v1 Announce Type: new Abstract: Diffusion models perform remarkably well on high-dimensional data such as images, often using only a modest number of reverse-time steps. Despite this p
arXiv:2605.06723v1 Announce Type: new Abstract: Language models often generate reasoning before giving a final answer, but the visible answer does not reveal when the model's answer preference became
arXiv:2605.06772v1 Announce Type: new Abstract: As large language models (LLMs) show increasing promise on research-level physics reasoning tasks and agentic AI becomes more common, a practical questi
arXiv:2602.09229v3 Announce Type: replace Abstract: Cosine similarity normalizes both sides; dot product normalizes neither. We propose a 2x2 framework that independently controls query-side and docum
arXiv:2605.07756v1 Announce Type: cross Abstract: Modern deep models are often pretrained on large-scale data with missing labels using composite objectives, where the relative weights of multiple los
arXiv:2605.07533v1 Announce Type: new Abstract: Large Language Models (LLMs) have recently demonstrated strong performance in machine translation (MT). However, most prior work focuses on improving or
arXiv:2605.06913v1 Announce Type: cross Abstract: We present You Only Stack Once (YOSO), an automated pipeline designed to detect faint, slow-moving Solar System objects in wide-field astronomical sur
arXiv:2605.05405v2 Announce Type: replace Abstract: Semantic search of Earth observation archives remains challenging. Visual foundation models such as CLAY produce rich embeddings of satellite imager
A Washington Post/Ipsos poll found that 71% of respondents said Donald Trump is not honest or trustworthy, and 67% said he does not carefully consider important decisions. The poll data was shared by
Back from a little family break! Lots has happened, and I’m planning to do a deeper dive into the most interesting architectural components (soon). Btw, are there any major architectures I missed belo
France is the only European country that turned nuclear generation into a structural competitive advantage. 57 reactors built between the 1970s and 1990s produce 70% of its electricity today. Wholesal
This statement by François Chollet argues that true understanding of an idea requires the ability to formalize it mathematically or through code, rather than merely having intuitive grasp. The premise
(INTENTIONALLY) LOST IN TRANSLATION: Democrats: We'd like cops to stop killing minorities. Republicans: Dems hate police. Democrats: Women should have the right to choose. Republicans: Dems want to ki
François Chollet argues that intuition serves as the foundational precursor to the development of significant ideas and innovations. This perspective suggests that before formal analysis, rigorous met
防衛分野で働くSoftware Engineerのインタビュー記事を公開しました🐟 https://sakana.ai/defense-swe-interview-2026/ 内容を一部ご紹介 ・指揮統制システムや偽情報対策技術の開発など、防衛分野のSoftware Engineerが担う役割 ・多様な技術領域をまたいだ開発スタイル ・ミッションクリティカルな領域での緊張感と充実感 防衛×AIの最
The Top AI Papers of the Week (May 4 - 10) - Conductor - HeavySkill - Horizon Generalization - 1,000 Synthetic Computers - Self-Improving Pretraining - Coordination as Architecture - Connect Four Alph
Francois Chollet argues that AI amplifies existing disparities in user agency, where individuals with high agency gain further capabilities while those with low agency become increasingly dependent, c
One theorem every ML engineer should know: The Johnson–Lindenstrauss Lemma. It states that high-dimensional data can be projected into a much lower-dimensional space while approximately preserving pai
Reproducing all of Schmidhuber’s papers (1990-2025) using an AI coding assistant. Cool project by @yaroslavvb! It even reproduced the “World Models” paper by me and @SchmidhuberAI with a toy env, with
For those interested, I will be doing a live session on this topic soon: https://academy.dair.ai/events/cmovobp97000904l5h0n9a2yz Sign up if you are interested in some of the tools we are releasing so
Technology is changing the way we make babies. The pioneering work of the scientists who invented IVF led to the birth of the first “test tube baby” in 1978. We’ve come a long, long way since then. Th
MIT Technology Review Explains: Let our writers untangle the complex, messy world of technology to help you understand what’s coming next. You can read more from the series here. Eight passengers aboa
In the second week of the landmark trial between Elon Musk and OpenAI, Musk’s motivations for bringing the suit were under scrutiny. Last week, Musk took the stand, alleging that OpenAI CEO Sam Altman
Our crowd favorite from last year’s AI Ascent is back for round 2… this time: Robotics The Endgame ♟️ thank you for dazzling us @DrJimFan ! You can see the forest from the trees and are quite the ente
This appears to be a post by cognitive scientist and AI researcher Gary Marcus on X (formerly Twitter) expressing skepticism or disagreement about a claim or development, likely related to AI, machine
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. We’ve entered the era of AI malaise AI is spreading everywhere
We are less safe as a society by keeping Mythos (or any other smart model) tightly gated so only a few companies get it. Protecting 100 companies is not enough. There are 96 million open source projec
arXiv:2605.04757v1 Announce Type: new Abstract: We introduce an elastic-driven self-folding approach that fabricates robots directly from flat 3D-printed conductive PLA nets. Elastic bands routed thro
arXiv:2605.05095v1 Announce Type: cross Abstract: We develop a framework for task-specific active next-best-view selection in 3D reconstruction from point clouds, by casting the problem in the languag
arXiv:2605.03391v1 Announce Type: cross Abstract: Weighted first-order model counting (WFOMC) is a central task in lifted probabilistic inference: It asks for the weighted sum of all models of a first
arXiv:2605.04899v1 Announce Type: new Abstract: GPT-style language models are sensitive to single-token changes at generation points where the predicted probability distribution is spread across multi
arXiv:2605.04175v1 Announce Type: new Abstract: Gromov--Wasserstein optimal transport (GWOT) aligns metric measure spaces by matching their within-domain relational structures, but large-scale GWOT re
arXiv:2603.00714v2 Announce Type: replace Abstract: Visual analysis and reconstruction of pipeline inner walls remain challenging in industrial inspection scenarios. This paper presents a dedicated re
arXiv:2604.02995v2 Announce Type: replace-cross Abstract: We introduce a nonnegative functional mathfrak{S} on the space of line arrangements in P^2 that vanishes precisely on free arrangements, obtai
arXiv:2605.02936v1 Announce Type: cross Abstract: Representing dynamical systems through data-driven universal spaces has proven effective; however, achieving this universality for human brain activit
arXiv:2605.04169v1 Announce Type: cross Abstract: Surgical team performance arises from complex interactions between technical execution and non-technical skills, including communication and coordinat
arXiv:2605.04610v1 Announce Type: new Abstract: Robot-to-human object handover is an essential skill for robot assistants, from serving drinks at home to passing surgical tools in the operating room.
arXiv:2605.03644v1 Announce Type: new Abstract: Many-Shot In-Context Learning (ICL) has emerged as a promising paradigm, leveraging extensive examples to unlock the reasoning potential of Large Langua
arXiv:2605.04269v1 Announce Type: cross Abstract: We provide a theoretical analysis of Adam under non-stationary stochastic objectives, separating two regimes: Euclidean tracking under adaptive strong
arXiv:2509.10784v3 Announce Type: replace-cross Abstract: Medical vision foundation models remain limited in downstream tasks, particularly volumetric medical image segmentation. While fine-tuning on
arXiv:2605.04236v1 Announce Type: new Abstract: Large Language Model ensembles improve reasoning accuracy up to a performance boundary; beyond it, additional deliberation degrades accuracy. Static-bud
arXiv:2605.04952v1 Announce Type: new Abstract: Mixture-of-experts (MoE) models enable scalable transformer architectures by activating only a subset of experts per token. Recent evidence suggests tha
arXiv:2309.09550v4 Announce Type: replace-cross Abstract: The human brain can self-organize rich and diverse sparse neural pathways to incrementally master hundreds of cognitive tasks. However, most e
arXiv:2605.04609v1 Announce Type: new Abstract: Composition is a cornerstone of visual aesthetics, influencing the appeal of an image. While its principles operate independently of specific content, i
arXiv:2301.06217v1 Announce Type: cross Abstract: We provide a detailed exposition of the connections between Boltzmann machines commonly utilized in machine learning problems and the ideas already we
arXiv:2605.03149v1 Announce Type: new Abstract: Humans typically use natural language to update teammates on task states. Since not all updates are communicated, discrepancies arise between the team m
arXiv:2603.00492v2 Announce Type: replace Abstract: Per-scene optimization methods such as 3D Gaussian Splatting provide state-of-the-art novel view synthesis quality but extrapolate poorly to under-o
arXiv:2603.17771v2 Announce Type: replace Abstract: Attention sinks and massive activations are recurring and closely related phenomena in Transformer models. Existing explanations have largely focuse
arXiv:2605.04683v1 Announce Type: cross Abstract: We analyse the computational power of transformer encoders as sequence-to-sequence functions on vectors. We show that average hard attention can be us
arXiv:2605.04128v1 Announce Type: cross Abstract: We present JoyAI-Image, a unified multimodal foundation model for visual understanding, text-to-image generation, and instruction-guided image editing
arXiv:2605.04754v1 Announce Type: new Abstract: Deep neural network (DNN) inference at the edge demands simultaneous improvements in accuracy, computational efficiency, and energy consumption. Approxi
arXiv:2605.04406v1 Announce Type: new Abstract: The integration of Symmetric Positive Definite (SPD) matrices into deep learning has historically relied on fixed algebraic Riemannian metrics. Analogou
arXiv:2602.03452v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) is effective for training large language models on deterministic outcome reasoning tasks. Prio
arXiv:2605.04793v1 Announce Type: new Abstract: Koopman-based neural MPC models generate time-varying dynamics from historical data, but preserve convexity by enforcing that the system operator is ind
arXiv:2605.04087v1 Announce Type: cross Abstract: Optimization over the Stiefel manifold St(p,d), the set of p imes d column-orthonormal matrices, is fundamental in statistics, machine learning, and s
arXiv:2605.04834v1 Announce Type: new Abstract: Unlike vision and language domains, graph learning lacks a shared input space, as input features differ across graph datasets not only in semantics, but
arXiv:2601.11689v2 Announce Type: replace-cross Abstract: Multimodal image registration between diffusion MRI (dMRI) and T1-weighted (T1w) MRI images is a critical step for aligning diffusion-weighted
arXiv:2602.06810v2 Announce Type: replace Abstract: Tabular anomaly detection (TAD) remains challenging due to the heterogeneity of tabular data: features lack natural relationships, vary widely in di
arXiv:2605.03261v1 Announce Type: cross Abstract: Romantic breakups are among the most common and intense sources of psychological distress. We evaluated *overit*, a single-session AI chatbot that use