Knowledge catalogue
arXiv:2605.30736v1 Announce Type: cross Abstract: The rapid development of large language models, each with distinct capabilities and inference costs, raises a practical deployment question: given an
arXiv:2601.13704v3 Announce Type: replace-cross Abstract: In speech machine learning, neural network models are typically designed by choosing an architecture with fixed layer sizes and structure. The
arXiv:2605.31558v1 Announce Type: cross Abstract: Transformer-based language models are widespread in today's society. As such, understanding the mechanisms by which they solve structured tasks and pr
arXiv:2605.30581v1 Announce Type: cross Abstract: Industrial visual sim-to-real is often described as transferring from synthetic images to real images, but industrial deployment usually involves a br
arXiv:2502.12119v4 Announce Type: replace-cross Abstract: Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications
Production AI systems require fundamentally different infrastructure approaches as workloads scale, with demands that differ significantly from development or testing environments. Fireworks AI discus
arXiv:2605.31535v1 Announce Type: cross Abstract: Self-supervised novel view synthesis (NVS) remains challenging to scale, despite the abundance of video data, largely due to the brittleness of traini
arXiv:2605.30587v1 Announce Type: new Abstract: Chain-of-thought (CoT) reasoning has significantly improved the reasoning ability of large vision-language models (LVLMs) by verbalizing intermediate re
arXiv:2605.31512v1 Announce Type: new Abstract: Multilingual orthopedic decision support remains challenging in low-resource healthcare settings, where clinical narratives contain specialized terminol
arXiv:2605.31284v1 Announce Type: cross Abstract: The morphological analysis of mitochondria in fluorescence microscopy (FM) is crucial for understanding cellular health, energy production, and metabo
arXiv:2605.30593v1 Announce Type: cross Abstract: Engine Health Management (EHM) depends on reliable forecasting of Remaining Useful Life (RUL) and on tracking thermal indicators such as turbine gas t
arXiv:2605.31434v1 Announce Type: new Abstract: Robot-Assisted Minimally Invasive Surgery (RAMIS) enhances surgeon dexterity, with newer platforms leveraging haptic feedback to further improve perform
arXiv:2602.12686v2 Announce Type: replace Abstract: Navigational signs enable humans to navigate unfamiliar environments without maps. This work studies how robots can similarly exploit signs for mapl
arXiv:2601.18537v3 Announce Type: replace-cross Abstract: Accurate long-horizon vessel trajectory prediction remains challenging due to compounded uncertainty from complex navigation behaviors and env
arXiv:2605.30662v1 Announce Type: new Abstract: Spatio-temporal graph-based models have typically been used to forecast new cases of infectious diseases such as COVID-19 and chickenpox outbreaks. Howe
Lucinda Shen / Axios: Stockholm-based Endra, which automates the design of plumbing and electrical wiring in new buildings, raised 50M led by a16z — Endra, a startup automating the design of plumbing
arXiv:2605.31044v1 Announce Type: new Abstract: Reinforcement learning has shown promising results for optimizing the control of industrial energy systems, yet most existing studies remain limited to
The gains are most obvious in coding and operational areas. Even conservative organizations are adopting coding agents fast. That doesn't mean AI adoption doesn't come with huge challenges and cost co
arXiv:2605.31245v1 Announce Type: new Abstract: Recently, sparse autoencoders (SAEs) have emerged as an attractive tool for interpreting and interacting with representations in practical neural networ
arXiv:2605.31069v1 Announce Type: cross Abstract: Accurately predicting future events is fundamental to content understanding and decision-making across various domains. While prior research has prima
arXiv:2605.30898v1 Announce Type: new Abstract: In real-world deployments of large language models (LLMs), balancing inference quality and computational cost has become a central challenge. Existing a
arXiv:2605.31457v1 Announce Type: new Abstract: With the rapid advancement of large multimodal models (LMMs), inference-time overhead has become a key bottleneck for real-world deployment. Existing me
arXiv:2605.30506v1 Announce Type: cross Abstract: Global localization in geometrically aliased, quasi-static environments such as grocery stores, offices, schools, and hospitals poses a significant ch
Zack Abrams / The Block: A US court ordered Circle to blacklist Zama's cUSDC contract, freezing ~12.6M in funds, likely catching many in the “crossfire” of a civil suit against a DAO — Quick Take — A
/goal and other fully automated AI agents are cool, but not a great model for the future of work with people. Instead you want your AI to know when to ask you GOOD questions, maybe because it is stuck
Cailey Gleeson / Fierce Healthcare: NYC-based Garner Health, which uses data analytics to help 2.5M+ workers find physicians, raised a 100M Series E at a 2.74B valuation led by Index Ventures — Garner
Timeline of the Iran War: 🔸2015: JCPOA agreed to. Iran gives up most of its enriched uranium, leaving it with a limited amount enriched to under 4%. 🔸2016-2018: Iran is complying with the agreement. 🔸
Patricia Cohen / New York Times: How Schneider Electric is using AI in call centers and manufacturing to complement employees' work and boost productivity, rather than to replace them — For many chief
I think Epoch does a great job benchmarking, but I continue to believe that open weights models are much more fragile, especially out-of-distribution, than their benchmarks indicate. Vibe-wise, I don’
It does seem like meaningfully better AI releases are accelerating, especially from OpenAI & Anthropic. To illustrate, I caused this timeline to be created. It only lists new models that scored 3 poin
金融分野で働くSoftware Engineerのインタビュー記事を公開しました🐟 https://sakana.ai/finance-swe-interview-2026/ 内容を一部ご紹介 ・金融業界の業務を変革するための融資業務支援プロジェクトの開発 ・金融業界の制約を踏まえたAIエージェント開発における技術的課題 ・AIネイティブな環境における、高い裁量と オーナーシップを重視した働き方
arXiv:2511.08548v2 Announce Type: replace Abstract: The evolution of mathematics is shaped importantly by interestingness: researchers choose which problems to pursue, and students choose which proble
arXiv:2605.29273v1 Announce Type: new Abstract: A crucial component of machine learning algorithms is minimizing loss functions with less computational cost and less oscillations. While adaptive learn
arXiv:2605.29278v1 Announce Type: new Abstract: As LLMs become increasingly integrated into daily life, understanding how their presence will shape human linguistic behavior is an open question. We pr
arXiv:2605.28829v1 Announce Type: cross Abstract: Competitive STEM examinations such as JEE and NEET require multi-step symbolic reasoning, precise numerical computation, and deep conceptual understan
arXiv:2605.30318v1 Announce Type: cross Abstract: Portrait photography is largely decided before the shutter opens: the subject's pose, the camera configuration, and the lighting devices must be coord
arXiv:2605.29849v1 Announce Type: cross Abstract: Machine learning (ML) is increasingly used for data-driven modeling of buildings to enable downstream tasks such as fault detection and diagnosis, and
arXiv:2605.29868v1 Announce Type: cross Abstract: Centralised biometric identity systems expose users to single points of failure, opaque verification processes, and irreversible biometric compromise.
Pritam Biswas / Reuters: Coinbase and Kalshi introduce perpetual crypto futures, marking the first time the contracts will be available to US investors via domestic, regulated exchanges — Cryptocurren
Dear Grimes, Appreciate your candor, and I understand that your subjective impression is to believe that there is something there. But a. That’s the very Eliza illusion I am pointing out. It is possib
arXiv:2605.29378v1 Announce Type: new Abstract: Natural language interfaces can simplify interaction with multi-robot systems, especially when non-expert users need to issue high-level commands. Acous
Deep Agents v0.6 makes harness profiles a first-class abstraction. Now, you can get production-grade performance from models like @Kimi_Moonshot, @Alibaba_Qwen, and @DeepSeek_ai at 20x+ lower cost tha
arXiv:2605.29353v1 Announce Type: cross Abstract: The proliferation of AI-generated synthetic media poses a critical threat to the integrity of digital evidence in legal and forensic contexts. Existin
Different models need different prompts, sometimes tools “Harness profiles” are how we do that in deepagents Deep Agents v0.6 makes harness profiles a first-class abstraction. Now, you can get product
arXiv:2605.30200v1 Announce Type: new Abstract: The double-edged sword of integrating Large Language Models (LLMs) requires an effective triadic collaboration mechanism among LLMs, teachers and studen
arXiv:2602.00324v2 Announce Type: replace-cross Abstract: Synchronization over the special Euclidean group SE(3) aims to recover absolute poses from noisy pairwise relative transformations and is a co
arXiv:2605.29773v1 Announce Type: cross Abstract: Reliable semantic segmentation for mobile robots requires both accurate dense prediction and robust uncertainty estimation under distribution shift. S
arXiv:2511.11703v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) in 3D environments with high-dimensional sensory input poses two major challenges: (1) the high memory consumption
arXiv:2605.30099v1 Announce Type: new Abstract: Valuable decisions and highly prioritized analysis now depend on applications such as facial biometrics, social media photo tagging, and human robots in
arXiv:2605.30119v1 Announce Type: cross Abstract: Survival analysis concerns the task of predicting the time until an event occurs. Often used in the medical field, survival analysis deals with incomp
arXiv:2605.25975v2 Announce Type: replace-cross Abstract: Capturing relightable 3D assets from real-world objects is a widely researched problem. Several per-scene optimization-based methods, based on
arXiv:2602.14975v3 Announce Type: replace-cross Abstract: Following our previous work (J. Phys. Chem. Lett., 2026, 17, 5, 1288-1295), we propose the DMTS-NC approach, a distilled multi-time-step (DMTS
arXiv:2504.19399v4 Announce Type: replace Abstract: Robust and flexible leader-following is a critical capability for robots to integrate into human society. While existing methods struggle to general
arXiv:2602.13436v2 Announce Type: replace Abstract: Mechanically characterizing the human-machine interface is essential to understanding user behavior and optimizing wearable robot performance. This
arXiv:2605.29453v1 Announce Type: cross Abstract: Representation learning on dynamic graphs requires capturing complex dependencies that evolve across both time and structure. Existing approaches typi
arXiv:2605.30014v1 Announce Type: new Abstract: Urban trajectories play a crucial role in modeling urban dynamics and supporting various smart city applications. However, privacy concerns restrict acc
fun fact many people don’t know: LLMs actually produce bullshit for many reasons, and would continue to do so (though less) even they weren’t trained on bullshit. legal citation hallucinations are a n
arXiv:2404.07977v4 Announce Type: replace Abstract: We introduce Gaga, a framework that reconstructs and segments open-world 3D scenes by leveraging inconsistent 2D masks predicted by zero-shot class-
arXiv:2605.28888v1 Announce Type: cross Abstract: Real-world user behavior rarely consists of isolated actions; instead, it often forms intent flows governed by spatiotemporal dependencies. To provide
arXiv:2605.29762v1 Announce Type: new Abstract: Video Motion Magnification (VMM) reveals imperceptible dynamics but often suffers from structural inconsistencies under complex geometric transformation