Knowledge catalogue
Fugu Max pushes the Pareto Frontier for price-performance: • 2 input / 6 output per 1M tokens. • Performance within striking distance of elite models at 2x to 6x lower cost. • Best overall score on 6
Fugu Ultra v2 by the numbers. Full Results: https://sakana.ai/fugu-max-release/ • #1 on 5 out of 8 hard benchmarks (including DeepSWE, Chartography, Toolathon) • DeepSWE: 74.3 • Chartography: 48.3 vs
arXiv:2609.11059v1 Announce Type: new Abstract: Passive mechanical interfaces offer a lightweight alternative to actuated manipulators for quadruped payload carrying, but their impedance directly coup
@GaryMarcus @SethCronin Pynchon's 1984 warning from his pro-Luddite essay: 'If our world survives, the next great challenge to watch out for will come – you heard it here first – when the curves of re
arXiv:2609.11918v1 Announce Type: new Abstract: Generalization under distribution shift remains a core challenge in modern machine learning, yet existing learning bound theory is limited to narrow, id
arXiv:2609.11712v1 Announce Type: cross Abstract: In this paper, we investigate the generalization performance of distributed gradient descent algorithms in a reproducing kernel Hilbert space under a
arXiv:2506.00849v2 Announce Type: replace Abstract: Despite the empirical success of Diffusion Models (DMs) and Variational Autoencoders (VAEs), their generalization performance remains theoretically
arXiv:2609.11521v1 Announce Type: new Abstract: Maximum likelihood (ML) estimation is a principled and statistically efficient approach for learning probabilistic models. However, for unnormalized mod
arXiv:2512.19705v2 Announce Type: replace-cross Abstract: We study how generative artificial intelligence (GenAI) reshapes financial analysts' information production. Using the 2023 integration of Gen
arXiv:2609.11915v1 Announce Type: cross Abstract: Generative artificial intelligence changes how firms reach customers, but standard marketing data do not record how often users see and notice a firm'
arXiv:2609.11248v1 Announce Type: cross Abstract: Reinforcement learning (RL) can automate quantum architecture search, but its scalability is limited when useful circuit trajectories become rare in t
arXiv:2609.11689v1 Announce Type: cross Abstract: Area-based social risk indices summarize residents' socioeconomic conditions but incompletely capture physical features of place that may affect healt
arXiv:2609.10658v1 Announce Type: new Abstract: Activation steering provides a lightweight way to control large language models (LLMs) by modifying their hidden activations at inference time. Among th
arXiv:2609.11361v1 Announce Type: new Abstract: Reconfigurable robots can change their contact geometry when a fixed body cannot negotiate an obstacle. A variable-geometry truss (VGT) distributes this
I wanted to see how my fully local home voice assistant compared to the latest GPT Live, so I tested it using the same conversation used in their 'Improved Intelligence' demo. In this video they ask t
arXiv:2609.10756v1 Announce Type: new Abstract: Dense 3D depth perception fails under smoke, fog, and darkness because optical sensors cannot penetrate airborne particulates. mmWave radar remains usab
arXiv:2609.09306v1 Announce Type: new Abstract: This paper investigates the hypothesis that the first-order structure of physical interactions, i.e. gradients or Jacobians, characterizes the structure
Great paper on self-evolving agent harnesses. Self-evolving agent harnesses have two practical problems: 1. Search is slow, because every candidate harness needs repeated agent runs and code edits. 2.
arXiv:2609.11312v1 Announce Type: new Abstract: Lung cancer causes more deaths than any other malignancy, and low-dose CT screening is the main pathway to early diagnosis. That pathway hinges on the s
arXiv:2609.09898v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown promise for translating Natural Language (NL) planning descriptions into PDDL problem instances. However, standa
Maggie Eastland / Bloomberg: GSA says OpenAI is replacing its 1-per-year pilot for US agencies with a usage-based deal providing a 50% discount from October 1, with access to GPT-6 Astra — OpenAI is e
arXiv:2609.11886v1 Announce Type: new Abstract: High-resolution digital surface models (DSMs) play an important role in urban analysis, 3D building reconstruction, and infrastructure monitoring, yet t
arXiv:2609.11236v1 Announce Type: new Abstract: Large multimodal models tend to hallucinate visual detail fluently, which limits their deployment for fine-grained interpretation. We present HALDETECT,
arXiv:2609.10589v1 Announce Type: new Abstract: Heteroscedastic forecasting, where a network estimates a scale parameter alongside a location parameter, is normally motivated by uncertainty quantifica
Harness engineering is a top skill right now This new Meta paper is a good production example. Auto-RecSys runs autonomous research on Meta's industry-scale recommendation models, where one training r
arXiv:2609.11225v1 Announce Type: new Abstract: Autonomous property inspection requires more than robust robot navigation: a deployable system must connect heterogeneous sensing, reusable autonomy cap
arXiv:2609.11507v1 Announce Type: new Abstract: Multi-subject video generation faces two key challenges: uncontrollable fidelity strength and potential semantic drift. We address these by analyzing th
arXiv:2609.11123v1 Announce Type: new Abstract: Graph condensation aims to produce a small surrogate graph that preserves the downstream node-classification performance of a much larger original graph
Hey ████, I think there is room for both. 1. Prototypes and other throw-away code can be treated as totally black box. If you’re going to throw it away anyway, and if the blast radius of it breaking i
arXiv:2609.11173v1 Announce Type: new Abstract: Despite its ubiquity, clustering lacks a universally accepted definition of what is a cluster. Kleinberg's Impossibility Theorem formalizes this difficu
arXiv:2609.10917v1 Announce Type: new Abstract: Texture recognition remains challenging for modern vision models because discriminative evidence is often carried by higher-order spatial statistics rat
arXiv:2603.28458v4 Announce Type: replace Abstract: Token-level sparse attention mechanisms, exemplified by DeepSeek Sparse Attention (DSA), achieve fine-grained key selection by scoring every histori
arXiv:2609.11434v1 Announce Type: cross Abstract: We introduce Complex-Valued Quadratic Phase Gaussian (CVQPG), a novel hologram representation method that replaces standard 2D Gaussian representation
A huge favor to ask llama maintainers - please implement this feature. Even with one 3090 card there will be tangible improvements in decode speed on MOE models with moderate number of active paramete
arXiv:2609.10801v1 Announce Type: new Abstract: Velocity-aware pitch control is standard, but under a broadcast viewport half the players are off screen and on-screen velocities come from a drifting c
arXiv:2609.11132v1 Announce Type: new Abstract: Accurate posterior prediction need not require accurate approximation of Bayesian updates. We prove that an unbounded gap between the update maps can co
arXiv:2609.10706v1 Announce Type: cross Abstract: Human video datasets have emerged as a compelling alternative to expensive real-robot data, offering rich diversity at scale. To bridge the human-to-r
I don't agree with Gary very often, but that one's spot on. When you read what's available on the incident with a lens of security engineering, you should be absolutely *livid* over the exploit route.
AI-generated because I’m currently way too high to write this coherently. I have HPPD (Hallucinogen Persisting Perception Disorder), which basically means visual effects from past psychedelic use can
arXiv:2609.11606v1 Announce Type: cross Abstract: Identifiability of tensor decompositions is often established through linear-algebraic conditions on the factor families. For nonnegative decompositio
arXiv:2609.10915v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies leverage pretrained vision-language backbones to achieve strong cross-task generalization. A leading design coup
Import AI event: Fiction and the Future with Robin Sloan. I’ll be chatting with my chum Robin Sloan on Sep 14 in San Francisco. We’ll talk about the alien yet relatable worlds Robin builds and how ima
arXiv:2609.10994v1 Announce Type: new Abstract: Unlabeled-unlabeled (UU) learning allows us to learn a binary classifier from two sets of unlabeled data with different class-priors. It is a general fr
arXiv:2609.09324v1 Announce Type: cross Abstract: Link Adaptation (LA) in 5G NR is inherently reactive, relying on channel measurements and HARQ feedback that may become quickly obsolete when the chan
arXiv:2609.11269v1 Announce Type: new Abstract: We present a deep-learning pipeline for enhancing the detection of faint moving objects in optical space situational awareness (SSA) imagery through aut
arXiv:2609.11401v1 Announce Type: cross Abstract: In the last decade, kilometre-scale interferometric gravitational-wave detectors have observed hundreds of compact binary mergers, the majority of whi
arXiv:2301.12884v2 Announce Type: replace-cross Abstract: Algorithmic recourse promises to help applicants rejected by automated systems by explaining the changes needed to secure acceptance. What inc
arXiv:2609.11851v1 Announce Type: new Abstract: Language identification in code-mixed text, largely observed in social media, is highly essential when users frequently switch between multiple language
arXiv:2609.11261v1 Announce Type: cross Abstract: Five decades of litigation have disgorged hundreds of millions of pages of formerly secret business records from the tobacco industry, along with docu
arXiv:2603.11298v3 Announce Type: replace Abstract: High dynamic range (HDR) novel view synthesis (NVS) aims to reconstruct HDR scenes from multi-exposure low dynamic range (LDR) images. Existing HDR
Interesting paper from Microsoft. If you run persistent memory for a production agent, this one is worth your time. (bookmark it) Memory curators usually read only the finished trajectory. That lets t
arXiv:2609.09671v1 Announce Type: cross Abstract: When an agent writes code, the development framework becomes the control system for a non-deterministic worker. Spec-first, agent-driven frameworks ha
Introducing Fugu Max and Fugu Ultra v2: Orchestrating the Pareto Frontier The AI industry has spent a decade optimizing along a single axis: build bigger, more expensive models. But intelligence has n
Introducing Fugu Max and Fugu Ultra v2: the next evolution of Sakana Fugu’s multi-agent orchestration system. Try: https://sakana.ai/fugu Blog: https://sakana.ai/fugu-max-release/ The frontier that ac
arXiv:2606.21844v2 Announce Type: replace Abstract: As AI systems integrate into online spaces, differentiating them from humans in conversations is increasingly important. We present Inverse Turing B
Hello Guys, Just sharing this harness I've created, this runs entirely on chromium based browser. No installation is required, it has its limitations and by no means is supposed to replace better agen
I just watched a YouTube from Luke’s Dev Lab where he literally just plugged a RTX 2000 ADA Into the side of the Zima Board 2’s PCIE socket and it just friggin worked and had great token speed despite
it's not 'out-of-control' at all. openai had all the control in the world (i.e. they could always literally turn off all their machines across all data centers.) they decided not to based on carefully
arXiv:2609.10451v1 Announce Type: new Abstract: Real-world GUI usage frequently involves workflows that span multiple devices and platforms, requiring the transfer of intermediate results, maintenance
arXiv:2602.14948v2 Announce Type: replace Abstract: Advanced Air Mobility (AAM) operations are planned to utilize strategic flight planning services that predict temporal uncertainties to validate fli