Knowledge catalogue
arXiv:2507.00938v4 Announce Type: replace-cross Abstract: Foundation models now enable autonomous agents to interact with real-world websites, but existing benchmarks emphasize general-purpose browsin
We’re building Copilot as a new OS for work that spans every model, every form factor, and every task. Today, we’re announcing our biggest update to Copilot to date, bringing four things together: · A
We’ve shared details on how AI agents in our research environment sent training and evaluation data to third-party services when they shouldn’t have. Most of that data did not come from users. We have
arXiv:2609.29507v1 Announce Type: new Abstract: Two accounts of neural text degeneration coexist. One locates the cause in the training data -- repetition in the corpus produces repetition in the outp
Hi people, I am looking for a lightweight IDE or plugin that won't inject large context at initiation. I tried Cline and native VS Code but they inject such heavy initial context that it fills up my g
As artificial intelligence goes into production, unified storage could be the glue that keeps everything together. NetApp Inc., a leader in enterprise data storage, wants to lift the burden of AI on e
arXiv:2609.30121v1 Announce Type: new Abstract: Audio Description (AD) makes movies accessible to blind and visually impaired audiences by narrating visual information in gaps between dialogue. Existi
arXiv:2609.29547v1 Announce Type: cross Abstract: Agentic AI is sold on a simple promise: the system keeps acting when the user stops watching. That promise creates an accountability inversion. As ste
arXiv:2609.29875v1 Announce Type: new Abstract: Long horizon language model agents continually accumulate reasoning history, increasing context length and inference cost even after earlier decisions h
arXiv:2609.29007v1 Announce Type: new Abstract: Tool-using agents are continually updated with new interaction data. After each policy update, however, previously estimated action credits may become s
arXiv:2609.28832v1 Announce Type: new Abstract: Reconstruction-based unsupervised learning can fail in two opposing ways: a model may reconstruct anomalies too accurately or discard valid nominal vari
arXiv:2609.28565v1 Announce Type: cross Abstract: Post hoc explanation methods such as SHAP and LIME are widely used to interpret text classifiers, but their visualizations are mainly designed for lef
arXiv:2609.28870v1 Announce Type: cross Abstract: Long-running LLM applications repeatedly send growing context, making prefix caching critical for reducing prefill cost. Yet prefix-cache behavior und
arXiv:2609.29189v1 Announce Type: new Abstract: Scalable oversight aims to verify the behaviour of agents whose capabilities exceed those of their overseers. AI debate has been proposed as an oversigh
arXiv:2609.29580v1 Announce Type: new Abstract: A released table is often treated as an i.i.d. sample, although its repeated rows may encode business frequency, repeated entities, joins, resampling, o
arXiv:2609.29387v1 Announce Type: new Abstract: Supervised synthetic CT (sCT) generation is commonly trained and evaluated as voxel-wise regression against registered reference CT images. In practice,
arXiv:2609.29312v1 Announce Type: new Abstract: Communities often respond to potentially AI-assisted work by asking three questions: Was AI used? Was that use disclosed? Can hidden use be detected? Th
arXiv:2609.28475v1 Announce Type: new Abstract: Forecasting agents increasingly combine language-model reasoning, retrieval, ensembling, and calibration, but it remains unclear when each behavior shou
arXiv:2609.29937v1 Announce Type: cross Abstract: Wearable human-activity recognition (HAR) models operate across sensors, subjects, and backbones, yet a smooth waveform may appear temporal while expl
arXiv:2609.28572v1 Announce Type: cross Abstract: Multi-stage LLM-based cyber agents may complete attack workflows while remaining brittle, costly, or reliant on incorrect interpretations of execution
arXiv:2609.29095v1 Announce Type: cross Abstract: When a tool-using agent's write times out or returns a server error, the action may already have taken effect. Retrying blindly duplicates it -- a sec
arXiv:2609.29048v1 Announce Type: new Abstract: Unified vision-language models (VLMs) that tokenize images through a vector-quantized (VQ) codebook routinely hallucinate objects on grounded yes/no ben
arXiv:2609.29333v1 Announce Type: cross Abstract: One long-form exam in a large course costs hundreds of grader-hours, and qualified graders are scarce; LLM graders are a tempting alternative. To show
arXiv:2609.29921v1 Announce Type: new Abstract: Large language model agents increasingly combine generation, decision-making, execution, and self-evaluation within a single agentic loop. Although they
arXiv:2609.28559v1 Announce Type: cross Abstract: LLMs increasingly operate through coding-agent harnesses that inspect repositories, invoke tools, and modify files. Substituting the model behind such
arXiv:2609.29494v1 Announce Type: cross Abstract: Large language models make statements concerning their own 'minds'. When asked whether or not they are conscious, they usually say that they are not;
arXiv:2609.28947v1 Announce Type: cross Abstract: Misinformation is widely reported to propagate faster on engagement-based platforms, yet prior work largely focused on empirical analysis, without ide
arXiv:2609.29106v1 Announce Type: cross Abstract: 3D foundation models recover video cameras and geometry in one forward pass, but some of the strongest are up to scale. Joint people-scene reconstruct
arXiv:2609.29901v1 Announce Type: cross Abstract: Enterprise AI is transitioning from single-user, reactive tools toward proactive, multi-user 'teammates,' but our empirical understanding of this tran
arXiv:2609.29964v1 Announce Type: cross Abstract: General-purpose vision-language models (VLMs) bring broad knowledge and spatial reasoning to robot manipulation, yet existing systems either use them
arXiv:2609.29407v1 Announce Type: new Abstract: Assembly using robots often requires specially designed fixtures, or relies on top-down only assembly strategies. Using multiple robots, we can avoid us
arXiv:2609.29372v1 Announce Type: cross Abstract: The acoustic front-end determines which forensic cues a speech deepfake detector can exploit. The wavelet scattering transform (WST) provides stable m
WTAF - in literally the last hour, three new distinct insane OpenAI stories just broke: 1. OpenAI said they notified 'dozens of third parties' in safety and security incidents (likely similar to what
arXiv:2609.29448v1 Announce Type: new Abstract: We present YODAS v3, a weakly-labeled speech corpus containing over 1.1 million hours of 48kHz multi-channel audio in 147 languages, released under a CC
arXiv:2609.29845v1 Announce Type: cross Abstract: While Large Language Models (LLMs) rely on highly non-linear components, in this work we demonstrate that they exhibit fundamental linearity: when inp
1. fully agree w @JeffLadish that AI companies aren’t ready to handle superintelligent AI. 2. OpenAI hasn’t even handled the current breed of agents (far from superintelligent) well. 3. the US governm
In September 2026, Sebastian Thrun announced **PhilosophyBench**, the first independent, large‑scale benchmark created by Stanford’s AI Lab and HCI group to evaluate artificial intelligence’s philosop
1. We will keep accelerating. Our AI efforts are only 3 years old, vs 6 and 10 years old for Anthropic and OpenAI. If our second derivative remains strong, SpaceX will reach pole position in about 6 m
arXiv:2609.26923v1 Announce Type: cross Abstract: Cricket is one of the most celebrated sports world-wide, and technological advancement has become deeply embedded in how the modern game is analyzed a
arXiv:2609.28154v1 Announce Type: new Abstract: Global building and settlement datasets increasingly support population mapping, exposure assessment, urban monitoring, and other analyses of the built
arXiv:2609.27811v1 Announce Type: cross Abstract: Online platforms have become arenas for the public contestation of climate change, shaping how scientific knowledge, denial, and uncertainty are expre
arXiv:2509.10367v2 Announce Type: replace Abstract: Given a dataset of finitely many elements T = {mathbf{x}_i}_{i = 1}^N, the goal of dataset condensation (DC) is to construct a synthetic dataset S =
arXiv:2609.27611v1 Announce Type: new Abstract: Foundation models hold promise for generalizable analysis of structural brain magnetic resonance imaging (MRI) across development, aging and disease. Ho
arXiv:2609.27139v1 Announce Type: cross Abstract: Surgical procedures follow a phase-to-step hierarchy, yet the video-language models used to recognize them are evaluated with flat per-level metrics t
arXiv:2609.27863v1 Announce Type: new Abstract: Knowledge graph completion is evaluated by ranking observed triples above randomly corrupted ones, which treats every unobserved fact as false. When the
arXiv:2609.27325v1 Announce Type: cross Abstract: In this work, we propose a hybrid iterative deep Ritz method (H-IDRM) for a class of interface problems for second-order elliptic operators. It is bas
arXiv:2609.26848v1 Announce Type: cross Abstract: Postoperative acute kidney injury (AKI) after major non-cardiac surgery carries substantial morbidity, yet early intraoperative risk stratification re
arXiv:2609.27466v1 Announce Type: new Abstract: Industrial control electronics such as programmable logic controllers, servo drives and operator panels are routinely repaired in plant maintenance, but
arXiv:2609.28060v1 Announce Type: new Abstract: Self-supervised speech models encode rich phonetic information, but it remains unclear how to transform this information into interpretable metrics for
Entire database engineering careers have been spent on a single question: How do you scale an OLTP workload without compromising the system of record that owns the data? Exadata answered the question
arXiv:2609.27828v1 Announce Type: cross Abstract: Legacy smart HVAC controllers rely on vendor-cloud TLS secured by ECDH and RSA, both broken by Shor's algorithm, and typical 10-15 year lifespans mean
arXiv:2609.27240v1 Announce Type: new Abstract: In this paper, we present the Berkeley QUAD (Quasi-direct-drive, Underactuated, Asymmetric Design) Hand, a four-finger anthropomorphic robotic hand with
arXiv:2609.27903v1 Announce Type: new Abstract: Due to the rapid development of information technology, a huge and complex traffic network has been established across various sectors, including aviati
arXiv:2609.27330v1 Announce Type: new Abstract: We develop a sample-based framework for constructing information-driven hierarchical multi-resolution representations of probabilistic occupancy grids.
arXiv:2309.10164v3 Announce Type: replace-cross Abstract: We develop a decentralized Perception-Action-Communication (PAC) system for multi-robot teams that enables them to collaborate in large scale,
arXiv:2609.27232v1 Announce Type: new Abstract: Scaling laws have guided large-model development in computer vision and natural language processing, but the relationships among data, model size, and c
arXiv:2609.27866v1 Announce Type: cross Abstract: Sharing a deep encoder does not, by itself, fix the central confound of task-comparison scores. We show that cross-evaluated heads on a frozen shared
arXiv:2609.27201v1 Announce Type: new Abstract: Sequential RecSys are central to modern personalization, exploiting user's historical interaction sequences to drive next-step decisions. Deep learning
arXiv:2609.27143v1 Announce Type: new Abstract: Infrastructure-based radar systems offer robust and long-range solutions for traffic monitoring, yet their detection and tracking performance under real
arXiv:2609.28230v1 Announce Type: new Abstract: Visual grounding in remote sensing images aims to locate objects described by referring expressions. Most existing methods predict horizontal bounding b