Knowledge catalogue
Yes, this result cost millions of dollars. But remember that when @OpenAI announced o3 it cost ~500,000 to score 87.5% on ARC-AGI 1. Today, Astra scores higher for ~20. In 2025 it took us and GDM an e
arXiv:2509.20219v2 Announce Type: replace Abstract: Robotic tails can enhance the stability and maneuverability of mobile robots, but current designs face a trade-off between the power of rigid system
arXiv:2609.04695v1 Announce Type: cross Abstract: Large-volume neutrino telescopes infer neutrino properties from Cherenkov light, but simulating the transport of billions of photons through highly sc
arXiv:2609.04303v1 Announce Type: cross Abstract: Information abstraction, which groups strategically similar private states into a tractable number of buckets, is essential for scaling game-solving a
arXiv:2609.04369v1 Announce Type: new Abstract: Visual Place Recognition (VPR) localizes a query image by retrieving database images of the same or nearby place, yet its robustness is often degraded b
arXiv:2609.05270v1 Announce Type: new Abstract: Artificial intelligence (AI) is transforming not only what information systems researchers design, but also how design research is conducted. Yet existi
arXiv:2609.05161v1 Announce Type: cross Abstract: Rigid Body Dynamics (RBD) forms the computational core of real-time robotic control, but its immense computational complexity creates a performance bo
Tae Kim / Key Context: Astra working with Blender via computer use feels like magic, showing computer use could be the fourth demand wave after chatbots, reasoning, and agentic coding — AI computer to
arXiv:2609.04206v1 Announce Type: cross Abstract: Voice AI systems increasingly mediate customer care interactions where caller presentation cues such as accent, affect, fluency, and urgency are avail
arXiv:2609.04232v1 Announce Type: cross Abstract: This paper offers a unique perspective on how speech technologies are being adopted by community-led heritage language preservation and revitalisation
arXiv:2603.23723v3 Announce Type: replace-cross Abstract: Deep spatially selective filters achieve high-quality enhancement with real-time capable architectures for stationary speakers of known direct
arXiv:2609.04995v1 Announce Type: new Abstract: Deep Imbalanced Regression (DIR) is pervasive in continuous prediction tasks across diverse modalities, such as age estimation, depth prediction, and pr
arXiv:2609.04711v1 Announce Type: cross Abstract: Generative AI and coding agents can accelerate research software development, but they also increase the need for efficient software discovery and mai
arXiv:2609.04647v1 Announce Type: new Abstract: Traditional Retrieval-Augmented Generation (RAG) systems score each passage independently against the query, assembling context sets that may be individ
arXiv:2609.04781v1 Announce Type: new Abstract: Multi-modal medical images and clinical reports provide complementary anatomical, functional, and semantic information for medical image segmentation. E
arXiv:2609.05104v1 Announce Type: new Abstract: Biological agents navigate familiar environments not by re-solving routes for each new goal, but by reusing a learned map built once and read off as goa
arXiv:2602.13784v2 Announce Type: replace-cross Abstract: Explaining with examples is an intuitive way to justify AI decisions. However, it is challenging to understand how a decision value should cha
arXiv:2609.04266v1 Announce Type: cross Abstract: Softmax is a key operation in Transformer attention, but its exponentiation and normalization add significant overhead in compute-in-memory (CIM) acce
arXiv:2602.03102v2 Announce Type: replace Abstract: Many strong decoding methods for text generation follow a sample-and-rerank paradigm: they draw multiple candidates, score each under a utility (rew
arXiv:2609.05090v1 Announce Type: new Abstract: Evaluation of medical artificial intelligence agents remains predominantly answer-centric, assessing only the correctness of final outputs while overloo
arXiv:2609.05269v1 Announce Type: cross Abstract: LLM agent systems increasingly combine provenance tracking, authorization, policy enforcement, protocol adapters, and execution controls. However, ind
arXiv:2609.04809v1 Announce Type: new Abstract: Comparing intelligent systems under deployment constraints requires more than predictiveaccuracy.This paper develops Compression-Prediction-Resource Int
arXiv:2609.05374v1 Announce Type: new Abstract: Computer-use agents have advanced on benchmarks like OSWorld and AndroidWorld, but still act mostly through the GUI, often producing inefficient traject
arXiv:2609.04300v1 Announce Type: new Abstract: Ensuring the security of the power system is essential for stability and reliability, especially in the event of disruption. Effective classification of
arXiv:2609.04390v1 Announce Type: cross Abstract: Metabolic dysfunction-associated steatotic liver disease (MASLD) affects approximately 30% of the general population. Ultrasound-based imaging, includ
arXiv:2609.05361v1 Announce Type: new Abstract: Human-robot interaction (HRI) enables intuitive and intelligent collaboration between humans and robots in real-world environments. This paper introduce
arXiv:2609.04959v1 Announce Type: new Abstract: Recent calls for harder machine translation benchmarks have not clarified what difficulty should mean. We argue that one meaningful and currently unmeas
arXiv:2609.05049v1 Announce Type: new Abstract: Autonomous systems require robust low-latency perception under rapidly changing scene dynamics and challenging illumination. In event cameras object det
arXiv:2609.05328v1 Announce Type: new Abstract: Generating categorical graphs requires choosing node and edge types that form a coherent structure without depending on node order. Many graph generator
arXiv:2609.05325v1 Announce Type: new Abstract: Achieving robust SLAM in large-scale underground coal mines with complex structures and severe degeneracies remains highly challenging. Dense smoke and
arXiv:2609.04394v1 Announce Type: cross Abstract: This technical report is a study of the use of differential game (DG) theory to solve the target-assignment and midcourse guidance problems of drone s
arXiv:2609.05253v1 Announce Type: new Abstract: We introduce GLASS, a framework for graph-level anomaly detection (GLAD) that achieves robust cross-domain transferability through graph-language alignm
arXiv:2609.05233v1 Announce Type: new Abstract: While machine-learning interatomic potentials (MLIPs) have successfully learned potential energy surfaces (PES) and atomic forces, many practical applic
arXiv:2609.04592v1 Announce Type: new Abstract: Intelligent extended reality (XR) systems increasingly use eye and head tracking to infer user intent, task, and attention, but the same signals can als
arXiv:2609.04718v1 Announce Type: new Abstract: Structure-from-Motion (SfM) is a fundamental tool for sparse 3D reconstruction with broad impact in robotics and vision, supporting mapping, localizatio
I ran a 112-case MiniMax H3 quality sweep on an RTX 3090 last night trying to find the best combos . Kept the prompt, seed, reference image, RefMods, Sage setup, sampler, and scheduler stayed constant
arXiv:2609.05099v1 Announce Type: new Abstract: Automatic identification of code-switched (CS) utterances remains a challenge for language identification (LID) systems, causing such texts to be underr
arXiv:2609.04585v1 Announce Type: cross Abstract: The Multi-Level Intermediate Representation (MLIR) has made reusable compiler infrastructure practical for domain-specific computation. However, MLIR'
arXiv:2609.04564v1 Announce Type: new Abstract: Self-driving laboratories (SDLs) combine automated experimentation with adaptive decision-making to accelerate scientific discovery. Their operation nev
arXiv:2609.05294v1 Announce Type: new Abstract: Late Gadolinium Enhancement (LGE) on cardiac magnetic resonance is a key marker of myocardial scar, but its limited accessibility motivates routine ECG-
arXiv:2609.04846v1 Announce Type: new Abstract: Weakly supervised 3D occupancy prediction reduces the reliance on costly 3D annotations by learning from 2D pseudo-labels generated by vision foundation
arXiv:2609.04698v1 Announce Type: new Abstract: Vision transformers typically treat every image token as equally important, yet for most tasks in computer vision only a fraction are needed. Adaptive c
arXiv:2609.05075v1 Announce Type: new Abstract: General continual learning (GCL) aims to learn from evolving data streams without task identities, explicit boundaries, or repeated access to previous d
arXiv:2609.05022v1 Announce Type: new Abstract: This paper presents new tokenization resources for Irish and evaluation measures of alignment with the morphological boundaries of the language. We pres
arXiv:2601.21547v2 Announce Type: replace-cross Abstract: Real-world time series exhibit complex and evolving dynamics, making accurate forecasting extremely challenging. Recent multi-modal forecastin
arXiv:2609.04574v1 Announce Type: cross Abstract: Multimodal Graph Neural Networks have become standard for recommendation by augmenting sparse interaction data with content features. Yet current arch
arXiv:2609.04458v1 Announce Type: new Abstract: Data collected during aerial and spaceborne imaging spectroscopy campaigns enables the detection of transient events such as trace gas emissions. Howeve
arXiv:2609.04607v1 Announce Type: new Abstract: Three-dimensional scene graphs (3DSGs) have emerged as a promising approach for building geometrically grounded, semantically informed, hierarchical gen
arXiv:2609.04577v1 Announce Type: new Abstract: We investigate how optimizers scale across the overtraining axis and show that relative optimizer performance and optimal hyperparameters change substan
Ouch: “Nvidia is building the most concentrated bet on a single technology cycle that any company has ever made. If these valuations keep climbing, Jensen looks like a genius. If they don't, Nvidia is
arXiv:2609.04382v1 Announce Type: cross Abstract: We present a systems-security case study of a two-node split-LLM training system whose privacy evaluation passed while leaving an observable channel u
arXiv:2609.05094v1 Announce Type: new Abstract: Electroencephalogram (EEG) visual decoding aims to recover visual semantics from non-invasive neural time-series signals, for which robust alignment bet
arXiv:2609.04880v1 Announce Type: new Abstract: Designing effective and fiscally sustainable policies for solar photovoltaic (PV) adoption requires balancing adoption gains against public expenditure
Is LfD and BC research being effected by recent advances in (so-called) Frontier LLMs? Or is research in LfD and BC sort of going along in an independent direction from these? Are you seeing any use f
arXiv:2609.04748v1 Announce Type: cross Abstract: Prefix caching, in which a serving engine reuses the key and value tensors of a shared prompt prefix across requests, is enabled by default in the maj
arXiv:2609.05323v1 Announce Type: new Abstract: Palynomorphs (microscopic, organic-walled fossils such as pollen, spores, and dinoflagellates) are important high-resolution records of past climates an
arXiv:2609.05262v1 Announce Type: new Abstract: Computational phylogenetics has become an essential tool in historical linguistics, yet its application at a global scale remains constrained by two fac
arXiv:2603.20686v2 Announce Type: replace-cross Abstract: Recent advancements in text-to-speech technologies enable generating high-fidelity synthetic speech nearly indistinguishable from real human v
arXiv:2606.17398v2 Announce Type: replace-cross Abstract: Binary reversing is fundamental to software understanding, vulnerability discovery, malware investigation, and firmware auditing. However, it
arXiv:2609.04902v1 Announce Type: cross Abstract: Can we recover the 3D poses of multiple people using only sound? This paper presents the first attempt to estimate multi-person 3D poses solely from a