Knowledge catalogue
arXiv:2610.09919v1 Announce Type: new Abstract: Hessian spectra at trained models in deep learning exhibit a persistent pattern: eigenvalues organize into distinct clusters, including a large bulk nea
arXiv:2610.09187v1 Announce Type: new Abstract: Multi-robot task allocators in dynamic missions commonly admit newly released tasks immediately, potentially invoking allocation for each new arrival. W
Today, we announced the new Gemini agent, your single, universal agent for work. For small and midsize businesses, with lean teams and margins, Gemini will be a critical tool for you to operate effici
arXiv:2610.10533v1 Announce Type: new Abstract: Conditional memory architectures such as DeepSeek Engram use input n-grams to look up learned embeddings, expanding the capacity of large language model
arXiv:2506.11481v2 Announce Type: replace Abstract: Scene Change Detection (SCD) evaluates changes using predefined query-reference (i.e., present-past) image pairs. However, this formulation overlook
arXiv:2609.35308v2 Announce Type: replace Abstract: Large language models treat conversation history as unverified context, so false premises injected into prior turns can be adopted as fact, a failur
arXiv:2610.09272v1 Announce Type: new Abstract: Attention routing requires a signal that predicts the value of attention on the current prefix. We evaluate whether hidden-state extrapolation error, cu
arXiv:2610.10395v1 Announce Type: new Abstract: Transformers can execute algorithms on data given in their input. We ask whether they can do the same for causal discovery. We study a standard continuo
arXiv:2610.09692v1 Announce Type: new Abstract: Pain perception varies substantially across individuals, making it difficult for population-based classifiers to generalise across all subjects in a dat
arXiv:2610.08882v1 Announce Type: cross Abstract: FinVector-Market-4B adapts Qwen/Qwen3.5-4B with rank-16 LoRA on a 22,000-example corpus for structured financial tasks. We evaluate the base and adapt
arXiv:2610.09768v1 Announce Type: new Abstract: Mean field limits describe the training dynamics of wide neural networks through the evolution of the empirical distribution of their parameters. Althou
arXiv:2610.09449v1 Announce Type: new Abstract: Zero-shot Chinese character recognition (ZS-CCR) aims to recognize characters whose categories are never observed during training, and typically relies
arXiv:2610.10066v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities in both visual understanding and code generation. However, existing b
arXiv:2610.09115v1 Announce Type: cross Abstract: Steering an LLM agent means deciding whether to correct it, at which step, and with which mechanism. Uncertainty is often used to decide when to corre
arXiv:2610.10201v1 Announce Type: cross Abstract: Joint spatial-geometric and analytic function reasoning requires translating a perceived spatial configuration into a symbolic function whose executed
arXiv:2610.09165v1 Announce Type: new Abstract: Planning motions that respect the intrinsic geometry of a robot's configuration space, including its curvature and a configuration-dependent notion of c
Google LLC’s Cloud division today introduced Gemini agent, a unified artificial intelligence assistant that can act autonomously, generate code and complete work across any device, including web, mobi
Carl Franzen / VentureBeat: Google Cloud unveils a universal Gemini agent to handle multi-day enterprise workflows in Workspace, Microsoft 365, and Slack that supports several AI models — Google is un
Ivan Mehta / TechCrunch: Google debuts Google AI Edge Foresight, a local macOS note-taking app for meetings that uses its 740M-parameter EmbeddingGemma 2 model and Gemma 4 assistant — Earlier in April
Google is launching a 'universal' Gemini AI agent that can work across apps and devices in the background. The tool, announced as part of the Gemini at Work event on Thursday, will be available within
Public research universities solve some of society’s most urgent challenges, but turning ideas into breakthroughs requires fast, secure access to cutting edge technology. In the agentic AI era institu
Google has released an experimental note-taking app that can transcribe meetings and audio files entirely offline, as reported earlier by TechCrunch. The app, called Google AI Edge Foresight, is free
This table to help anyone looking to build a budget Data Center homelab. I copied the bulk of value based, mid level, decent speed results GPUs and feed it to AI or SI and here are the recommended res
arXiv:2610.08959v1 Announce Type: new Abstract: On-policy distillation post-trains large language model agents by supplying dense, step-level guidance from a teacher policy when the reinforcement-lear
Grok 4.7 ranks first in legal matters Today we are announcing Harvey LAB-AA v1.1 in collaboration with Harvey. This updates our scoring methodology for the Legal Agent Benchmark (LAB) to add a halluci
With latest Halogen version update (0.17.2), decode is consistently at ~45 tps even at high context with Qwen 3.8 Flash Next on a 128GB Strix Halo. This is some great work u/peonist-ai. Have been pump
arXiv:2610.10323v1 Announce Type: new Abstract: Short-horizon realized volatility forecasting requires the integration of market information that evolves at incompatible temporal resolutions, from sec
arXiv:2610.09849v1 Announce Type: new Abstract: Selecting synthetic degradations for dense prediction requires an estimate of their training utility, the generalization gain they bring under a finite
arXiv:2610.10133v1 Announce Type: new Abstract: Real-world low-quality images suffer from complex mixed degradations, including but not limited to noise, blur, atmospheric effects, etc. Recent agentic
arXiv:2610.10156v1 Announce Type: new Abstract: Recent advances in Vision-Language Models (VLMs) have led to rapid progress in video understanding across a wide range of benchmark tasks. However, exis
arXiv:2606.13994v2 Announce Type: replace-cross Abstract: LLM-based Agents are becoming increasingly capable and widely deployed, creating growing incentives for adversarial misuse in the real-world.
arXiv:2610.09624v1 Announce Type: cross Abstract: Tool calling, invoking external tools on demand, is central to agentic LLMs, yet the mechanism that decides whether a model calls a tool or responds d
arXiv:2610.09571v1 Announce Type: new Abstract: Negation is an essential feature of human language, yet large language models (LLMs) remain unreliable in processing it. We evaluate recent open-source
arXiv:2610.09000v1 Announce Type: cross Abstract: As small language models (SLMs) are increasingly deployed on resource-constrained and on-device platforms, including as components of agentic systems,
arXiv:2610.10334v1 Announce Type: new Abstract: Face de-identification (FDeID) has emerged as a critical privacy-preserving technology, yet its evaluation remains fundamentally fragmented. Existing pr
arXiv:2610.10203v1 Announce Type: new Abstract: Model organisms of alignment-relevant behaviors (e.g., backdoors, sycophancy, spurious correlations) have emerged as a key tool for evaluating whitebox
Huge release from @odysseyml. Odyssey-3 Pro sets a new top score on Physics-IQ Verified, a benchmark that asks models to continue videos of real physics experiments. The robotics results stood out to
arXiv:2610.10154v1 Announce Type: new Abstract: We introduce Hyperbolic Symplectic Positional Encoding (HySPE), grounding positional attention in non-compact symplectic transformations. While canonica
Disclosure first: I'm one of the maintainers, this is my project. If you've pointed Open WebUI or a script at a local server, you know the failure modes: the server restarts and every conversation is
I oppose the death penalty, but I didn't always feel that way. I understand the people who support it - because I once was one of them. But either way, the death penalty staged as a public spectacle i
In recent decades, Ireland has grown into a vibrant hub for global technology. As modernization accelerates, Irish organizations — spanning government agencies, established enterprise brands, and grow
arXiv:2610.10368v1 Announce Type: cross Abstract: Adaptive computation aims to improve language-model inference by tailoring execution to each input. For layer programs, oracle evaluations use known a
arXiv:2610.09671v1 Announce Type: new Abstract: Recent advances in reasoning-oriented large language models (LLMs) have motivated increasing evaluation of their ability to perform professional decisio
arXiv:2610.10491v1 Announce Type: new Abstract: This paper investigates AutoResearch, a protocol in which a coding language model edits a training program under a one-hour GPU budget and retains a cha
arXiv:2610.09478v1 Announce Type: new Abstract: Referring Expression Segmentation (RES) links natural-language descriptions to pixel-level object masks. Yet standard evaluation provides limited insigh
Write-up + demo: https://drksci.com/labs-phosphene So this started as a bit of a gripe. Modern terminal renderers are seriously impressive and seriously complicated. GPU glyph atlases, texture caches,
arXiv:2610.09920v1 Announce Type: cross Abstract: Prevailing multi-vector visual document retrievers store each page as about a thousand patch vectors, often in vector databases run by a third party.
arXiv:2610.09450v1 Announce Type: new Abstract: Pixel-space diffusion models avoid the lossy VAE of latent models, which suggests an advantage on downstream tasks where fine-grained detail matters. We
arXiv:2610.09934v1 Announce Type: new Abstract: We describe the Itgan systems for the three ASR subtasks of NADI 2026, namely robust country-level ASR (1.1), mixed-dialect ASR (1.2), and Tunisian code
The tool is built on OpenAI’s Claude Managed Agents and performs code generation inside a cloud sandbox using the Sonnet 5.5 model. Each execution costs roughly US$0.75, and it can be accessed via the
TornadoVM: The Java to CUDA engine: https://github.com/beehive-lab/TornadoVM jitLLM: The inference engine: https://github.com/beehive-lab/jitllm Deep dive talk: https://www.youtube.com/watch?v=HO5CpET
Classification is one of the oldest problems in machine learning. Unlike modern decoding transformers, most classification models were non-autoregressive by nature. Before Jev, the common approaches w
The other week I posted about Jev vs. Kev compared and since then, OpenAI released the decisions endpoint, Cloudflare released Clef and many here asked about Laya as well. This time we compared six po
arXiv:2610.09788v1 Announce Type: new Abstract: Reward modeling often requires jointly representing and reasoning over multiple evaluation criteria, yet verbalizing this process token by token can inc
arXiv:2610.10473v1 Announce Type: new Abstract: Cell viability assessment is a core requirement in cell culture systems, with critical applications in biopharmaceutical manufacturing and drug developm
arXiv:2610.09079v1 Announce Type: cross Abstract: Large language models equipped with development environments have moved code generation toward repository-scale construction, yet building complete re
CrowdStrike report: https://www.crowdstrike.com/en-us/blog/unknown-threat-actor-uses-artex-to-target-south-korean-finance/ From: Andrew Curran on 𝕏: https://x.com/AndrewCurran_/status/2108108695876092
arXiv:2610.09702v1 Announce Type: new Abstract: Ordinary prompt-based editing can cause latent watermark detection to fail without explicitly targeting the watermark. We benchmark eight watermark meth
arXiv:2610.09058v1 Announce Type: new Abstract: LLMs are released at a rapid pace, raising a natural question: how do two independently trained models relate, both in which layers correspond and in ho
arXiv:2610.09898v1 Announce Type: cross Abstract: Assessing compound weather risks requires forecasts representing dependence between variables. CLARA (Calibrated Advection-Routing Attention) learns j