Knowledge catalogue
arXiv:2609.27912v1 Announce Type: new Abstract: Global forecasting models pool many series and learn one shared function. Gradient-boosted trees are their most common form. We measure a failure of thi
arXiv:2609.27287v1 Announce Type: new Abstract: Real-time payment fraud detection is a non-stationary streaming prediction problem: adversaries adapt before supervised labels mature, and localized bur
arXiv:2609.28137v1 Announce Type: cross Abstract: Educational technology (EdTech) platforms collect highly sensitive student data, including behavioral logs, disability records, and academic histories
In real-time streaming, every millisecond counts. For example, at 30 frames per second (fps), developers have a strict frame budget of just 33.3 ms (and only 16.6 ms at 60 fps) to ingest camera frames
arXiv:2609.26679v1 Announce Type: new Abstract: In grokking an early fit to the training data separates from a much later improvement in generalization. During this delay, training can move from a fix
arXiv:2609.25924v1 Announce Type: cross Abstract: Causal inference guides operational and managerial decisions but remains challenging in high-dimensional panel or tensor settings, where decisions may
arXiv:2609.23058v1 Announce Type: new Abstract: Current agent runtimes that plan before acting generally execute a step once it becomes ready. We present LazyAgent, a unified execution framework for a
arXiv:2609.23363v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have led to the emergence of coding agents capable of performing complex engineering tasks, including re
Skills let you encode domain-specific procedures as reusable, portable instructions for agents, but a fluent answer doesn't prove the agent picked the right skill or followed it. Learn how to measure
arXiv:2603.01590v2 Announce Type: replace-cross Abstract: Content-driven platforms such as Xiaohongshu often leverage click-through rate (CTR) prediction models for recommendation. However, these mode
arXiv:2609.23995v1 Announce Type: new Abstract: Linear models with an L_1-norm penalty remain state-of-the-art for high-dimensional (d > 1,000,000) tasks, offering a straightforward method for solving
arXiv:2609.22172v1 Announce Type: cross Abstract: This paper presents two interpretable machine-learning frameworks for quality screening of e-transaxle assemblies in electric vehicles: a Stagewise Wa
arXiv:2609.22160v1 Announce Type: new Abstract: Semiconductor manufacturing relies on tightly interconnected components, so early identification of the assets most likely to fail is essential to preve
arXiv:2609.21876v1 Announce Type: new Abstract: As an alternative to the additive and extremal biases of average and max pooling, we introduce Geometric Mean Pooling (GMP), a signed pooling operator t
Meet Wally. Our inference stack for open frontier models, built to be the fastest place to run them. Performance snapshot: GLM-5.3 Flash: 380 tok/s. GLM-5.3 Max: 790 tok/s Qwen3.8-27B: 485 tok/s DeepS
One hope for Tinker is that it can handle all the ML infra for posttraining for (approximately) everyone. So, curious, what prevents you from using Tinker for all your posttraining needs? Speed? Cost?
arXiv:2607.16894v2 Announce Type: replace Abstract: Many complex systems, including brain networks, financial markets, and gene-regulatory circuits, are better described by interaction structures that
ZCode is now open source, and the reported security issues have been addressed. Source code: https://github.com/zai-org/ZCode The repo includes its desktop app, web workspace, backend, Agent CLI, and
Impressive paper showing the impact of a good harness. Improves Qwen3-8B from 41.2% to 91.8% on long-horizon robot tasks without any change to the model. The gain comes from the harness. GAVEL keeps a
arXiv:2609.19802v1 Announce Type: new Abstract: Physical teleoperation integrates human cognitive flexibility with robotic precision, yet demanding manipulation tasks frequently induce severe cognitiv
AI is accelerating software development at an unprecedented pace. But as code generation scales, so do the challenges of securing the code, especially emerging AI-based vulnerability exploitations. To
arXiv:2609.19170v1 Announce Type: new Abstract: Emphatic temporal-difference learning (ETD) stabilizes the expected off-policy TD update and changes its projection geometry, but neither property deter
This week we kicked off the DevFest season in North America at Google Hudson Square in New York City with 80 engineers packed into the room. Typical technical workshops hand you a finished repo, tell
arXiv:2609.19844v1 Announce Type: cross Abstract: AI-generated RTL verification plans can satisfy a provider schema yet fail at the boundary to trusted execution. We present SecTB-RTL, an auditable fr
arXiv:2609.19212v1 Announce Type: new Abstract: Systematic generalization, the ability to solve novel problems by recombining known atomic elements, is central to human intelligence but difficult to s
arXiv:2609.18298v1 Announce Type: cross Abstract: Agentic-AI based software development offers the promise of faster completion of the software, greater programmer efficiency, and more reliable code.
arXiv:2609.18577v1 Announce Type: new Abstract: We consider the problem of estimating the trace of an implicit matrix mathbf{A} in R^{d^pimes d^p} that can only be accessed through matrix-vector produ
arXiv:2609.18038v1 Announce Type: new Abstract: The world population is growing rapidly, and technology is improving in parallel. Meeting the huge demand for food for these 7 billion people not only d
deepseek v4.1 flash on together ai is leading on ttft for pre-warmed queries for agent workflows, that startup time shows up again on every model turn, so shaving it down matters more as the loop gets
Good implementation of agent shared memory from the NVIDIA team. Banger paper from NVIDIA on shared memory for research agents. (bookmark it) If you run several coding agents on the same research prob
At Google, we see firsthand how the speed, scale, and sophistication of cyber threats continue to challenge traditional enterprise defenses. Today’s defenders can’t rely on reactive triage or fragment
Learn how to enforce defense-in-depth authorization for Model Context Protocol (MCP) tools on Amazon Quick. This walkthrough wires Microsoft Entra ID group and claims-based JWTs through an Amazon Bedr
arXiv:2609.17639v1 Announce Type: cross Abstract: Modern recommendation systems largely infer user preferences from implicit behaviors such as clicks, watch time, and negative feedback, but these sign
arXiv:2609.17863v1 Announce Type: new Abstract: LLM inference optimizations report speedups on different models, GPUs, prompts, and quality metrics, making them hard to compare or combine. We build a
This might be the biggest admission in any of the 100+ AI copyright lawsuits. OpenAI & Microsoft execs admit the case is about “the largest theft of labor in human history”, that publishers face an “e
According to The Information, Apple is planning to get back into the server game and might just pair up with Nvidia to make it happen. Apple retired its Xserve line in 2011 and has largely left enterp
Enterprise artificial intelligence services startup Hang Ten Systems Inc. today announced it has raised 53 million in a second seed round, less than three months after announcing its first. Hang Ten p
Editor’s note: Today we hear from SeaVerse, a gaming startup from SeaArt that is building a platform for playable AI experiences, where users can open lightweight games, character chats, and interacti
arXiv:2609.16252v1 Announce Type: cross Abstract: Machine-readable models such as SysML v2 are now programmatically accessible, and a growing body of work treats that access as the enabling condition
arXiv:2609.16487v1 Announce Type: new Abstract: We present a framework for evaluating data-science agents on live, continuously updated data using executable ground truth and format-agnostic factoid s
arXiv:2609.16275v1 Announce Type: new Abstract: Charismatic speech is shaped by language and speaking style, yet their relative contribution in bilingual public speaking remains unclear. We analyzed s
The hardest part of and “org harness” or “enterprise ai” (as opposed to personal ai” is auth, and managing auth in a multiplayer channel (like slack) We’re thinking a lot about how to do this right fo
arXiv:2609.16705v1 Announce Type: new Abstract: Physical AI requires more than increasingly large robot datasets: intelligent robots acquire knowledge through continuous interaction with the physical
arXiv:2609.13512v1 Announce Type: cross Abstract: Federated fine-tuning of large language models with low-rank adaptation reduces per-client trainable parameters, but client-to-server communication re
arXiv:2609.12394v2 Announce Type: replace Abstract: Mobile GUI agents are shifting from multi-module frameworks to native models trained end-to-end, yet industrial deployment faces three persistent ga
arXiv:2609.14424v1 Announce Type: cross Abstract: Reporting the Fisher geometry of a trained variational quantum model is routine; quoting the shot budget that would establish it is not. Certifying an
arXiv:2609.15722v1 Announce Type: new Abstract: AI-driven automated decision-making requires both predictive performance and interpretability. Recent advances in interpretable machine learning (IML) p
arXiv:2409.17685v3 Announce Type: replace Abstract: Hypomimia has drawn growing interest as a digital marker for screening Parkinson's disease (PD). However, developing reliable facial-expression-base
arXiv:2609.15794v1 Announce Type: new Abstract: Clinical AI systems are evaluated with instruments built for research settings (reference-based similarity metrics and expert rubric panels) that measur
arXiv:2609.14767v1 Announce Type: cross Abstract: Hierarchical orchestration, in which a Manager agent reviews worker output and can send it back for revision, is the default coordination pattern in p
memory has been a hot topic for the past ~2 years every time we bring it up or do anything there, gets ton of interest, but nothing sticks few takes on why below: - how to update and then use memory n
arXiv:2609.15152v1 Announce Type: cross Abstract: Multimodal embedding models encode heterogeneous inputs into a shared embedding space, enabling efficient similarity computation across modalities and
arXiv:2609.14307v1 Announce Type: new Abstract: Low-rank tensor factorization provides a flexible framework for completing multidimensional data from incomplete and corrupted observations. However, un
arXiv:2609.14691v1 Announce Type: cross Abstract: As autonomous vehicles and Extended Reality (XR) headsets enable novel in-car interactions, seamlessly querying physical landmarks, known as Outside-t
arXiv:2609.13279v1 Announce Type: new Abstract: Fashion attribute extraction is evaluated inconsistently: results are reported as single aggregate numbers across image types that pose different proble
arXiv:2609.15735v1 Announce Type: cross Abstract: We address the problem of color attribute compression for 3D splats. We show that all images generated by 3D splats are linear in the coefficients for
arXiv:2609.14991v1 Announce Type: new Abstract: Open Thai automatic speech recognition (ASR) is dominated by offline, Whisper-based models that read the whole utterance before transcribing, ruling out
arXiv:2609.12431v1 Announce Type: new Abstract: Automated crack inspection increasingly relies on deep learning, yet its reliability is limited by scarce and weakly controllable defect data. Existing
OverviewAs enterprises scale their AI and agentic workflows, they require serverless platforms that make data preparation for model training, evaluation, and inference effortless and efficient. Datafl
arXiv:2609.11962v1 Announce Type: cross Abstract: We study vector-valued binary affine refinement operators with finitely supported matrix masks and compactly supported continuous piecewise linear inp