Knowledge catalogue
As enterprises move from debating artificial intelligence adoption to deploying it, AI governance has become the harder question. Autonomous agents now run around the clock across a sprawl of platform
arXiv:2610.12571v1 Announce Type: new Abstract: Most systems trained by equilibrium propagation or coupled learning are in the same class as multi-layer perceptrons: while they may be universal functi
arXiv:2610.13931v1 Announce Type: cross Abstract: The expressivity of a neural network Phi describes the class of functions that a network can express. The term topological expressivity refers to a fa
deepagents just hit 30k stars on github! deepagents is great for building agents that do complex work. they manage context well and use a durable runtime. though inspired by coding agent design, deepa
arXiv:2610.13767v1 Announce Type: cross Abstract: Low-bit inference on accelerators with native 4-bit support requires quantizing both weights and activations to realize the full throughput gains thes
arXiv:2610.13328v1 Announce Type: new Abstract: Serving a Mixture-of-Experts (MoE) model pays for expert precision twice: the resident footprint pays for every expert the router can reach, while each
arXiv:2610.12998v1 Announce Type: new Abstract: Creativity benchmarks for large language models (LLMs) vary widely in task and metric design. This raises the question of whether they capture a common
arXiv:2610.13066v1 Announce Type: cross Abstract: The optimization objective for e-commerce advertising creatives has shifted from aesthetic quality to online business metrics like click-through rate
arXiv:2506.09956v2 Announce Type: replace-cross Abstract: Indirect prompt injection attacks exploit a fundamental weakness of LLMs: executing unauthorized tasks from untrusted sources. Despite the pra
Must-read paper on the effectiveness of multi-agent systems and persistent memory. We have recently seen many viral examples of multi-agent systems scaled via persistent memory. This work takes a clos
arXiv:2610.13134v1 Announce Type: new Abstract: We present Neurograf v1, an experimental end-to-end Romanian-first language-model pipeline developed to investigate the feasibility of training language
Over the last few months at @river_ai_inc we’ve developed what we believe is the best system in the world for building your own internal custom models, driven by 10 years of experience training top mo
arXiv:2610.13166v1 Announce Type: new Abstract: Terminal agents are moving beyond local operations toward completing real-world professional tasks. Short trajectories can demonstrate commands and tool
separating artifacts from the agent makes sense for sharing and cross-AI collaboration No vendor lock-in for your artifacts. Sites, decks, 3D games, reports, dashboards and galleries. Artifacts on Fly
arXiv:2610.12975v1 Announce Type: new Abstract: We present SmartSalesBench, the first multi-turn conversational benchmark explicitly designed to evaluate large language model (LLM) sales agents agains
arXiv:2610.13626v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly used throughout the software development lifecycle. This growing reliance on LLMs raises concerns about
arXiv:2610.13810v1 Announce Type: cross Abstract: Large language models (LLMs) are now a standard source of query expansion terms but they hallucinate. They inject non existent entities and off-topic
worth noting the trend here --> @harvey post-trained an open weight model for legal work + now @coinbase for fraud narrow task + proprietary data + open weights seems to beat frontier on cost & speed
Zai recently launched a domain‑specific language model called **GLM Legal**. According to a tweet posted at 4:13 PM on Oct 12, 2026, GLM Legal became the leading open‑weight model on both **Harvey’s L
I'm trying to figure out the best long-term upgrade path for my setup. Right now my GPUs are spread across several consumer PCs: Main: 5900X, 32GB DDR4, 2× RTX 3090 24GB. Secondary: i3-10320, 16GB DDR
Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap
Achint Srivastava / Command Line: Microsoft unveils Microsoft-Decision-1, a fast decision-scoring model trained on Qwen3.5-9B, and says it will soon rebase it on MAI, OpenAI, and other models — Decisi
This will be my third update on the bc-250 cluster and for my first forray into local ai I have been having a blast. This has turned from a weekend experiment into something I think I will use in the
Bloomberg: A look at differing revenue calculations of Anthropic and OpenAI, as Anthropic books gross sales through cloud partners, while OpenAI records only its net share — When measuring the race be
For what it's worth. I'm a mechanical engineer by education and software engineer in practice over the past ~20 years. Playing around with local models has been a recent hobby. Today I decided to do a
Introducing Anatomy Describe a machine in one line. Claude brings it to life. - Interactive isometric wireframes you can rotate, inspect and explore - WebGL shaders for fire, water, plasma and more -
arXiv:2610.11022v1 Announce Type: cross Abstract: Skillful prediction of biomass-burning activity several days in advance is important for air-quality forecasting and aerosol prediction. Two operation
arXiv:2610.12265v1 Announce Type: new Abstract: Accurate workload forecasting is critical for elastic resource provisioning in web-scale cloud services, where distribution shifts driven by viral conte
arXiv:2604.03672v2 Announce Type: replace-cross Abstract: Government agencies must register, classify and route every citizen appeal within statutory time limits, and much of this work is still done b
arXiv:2610.11792v1 Announce Type: cross Abstract: We present AuraLuxMuse, a novel system for automated aesthetic stage lighting design that integrates expert knowledge, representation learning, and pr
arXiv:2610.11128v1 Announce Type: new Abstract: A verified reference solution provides a correct trajectory for training a reasoning model. Alternatively, a prefix of the reference can guide the model
Banger paper from Meta Superintelligence Labs on self-improving agents. (bookmark it) It's hard to know exactly what drives self-improvement, since so many variables are at play (notes, skills, tool c
arXiv:2610.12247v1 Announce Type: cross Abstract: Topological Deep Learning extends graph-based learning to higher-order domains, such as hypergraphs, cellular, and simplicial complexes. These domains
arXiv:2610.11853v1 Announce Type: new Abstract: Modern neural networks are heavily over-parameterized. This redundancy incurs substantial compute and memory overhead during training and inference. Exi
arXiv:2610.11539v1 Announce Type: cross Abstract: As leading LLMs improve on capability evaluations, their limitations in producing creative outputs on design tasks remain insufficiently characterised
arXiv:2610.11694v1 Announce Type: cross Abstract: Existing reaction models primarily learn molecular transformations, whereas enzy- matic reactions depend jointly on molecular structure and catalytic
arXiv:2610.11399v1 Announce Type: new Abstract: Many applications of language models hinge not on individual samples but on the expectation of a test functional under the model. Estimating such expect
arXiv:2610.10809v1 Announce Type: new Abstract: Instance-specific rubrics are common in AI benchmarks where reliable evaluation requires specific expert knowledge. This approach is difficult to scale,
arXiv:2610.12463v1 Announce Type: cross Abstract: In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths
arXiv:2610.11270v1 Announce Type: cross Abstract: Personalized conversational AI relies on long-term memory systems that extract facts from user utterances and store them in persistent vector stores.
arXiv:2610.11302v1 Announce Type: new Abstract: Training-free sparse attention offers a practical acceleration solution to Diffusion Transformers (DiTs) via reducing computations without fine-tuning.
arXiv:2603.25015v2 Announce Type: replace-cross Abstract: System prompt instructions that cooperate in English compete in Spanish, with the same semantic content, but opposite interaction topology. We
arXiv:2610.10920v1 Announce Type: cross Abstract: E-commerce search pages are critical touchpoints for millions of online shoppers. While traditional search engines return a ranked list of results, mo
arXiv:2610.11000v1 Announce Type: new Abstract: The intermittent and variable nature of precipitation makes its accurate estimation over extended domains difficult, yet its spatiotemporal structure su
arXiv:2610.11146v1 Announce Type: new Abstract: Cold-start credit scoring -- deploying models with scarce labeled data, weak features, or minimal capacity -- is a recurring problem in financial machin
ik ik 'another harness D:'. so... i spent the last 6 months of my life building and ironing out every single detail and bug through almost every route with extensive testing across 3 machines, daily,
arXiv:2610.10933v1 Announce Type: cross Abstract: Spiking language models face a tradeoff between representing continuous semantic features over short temporal windows and retaining costly nonlinear a
arXiv:2610.10871v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong performance across many domains, but their efficiency is limited by the quadratic cost of attention with res
arXiv:2610.10942v1 Announce Type: new Abstract: Reinforcement learning environments are now a primary lever for improving large language model (LLM) capabilities in post-training, yet most agentic ben
arXiv:2610.10560v1 Announce Type: cross Abstract: AI foundation models pretrained on weather and climate data are increasingly fine-tuned to Earth science tasks well beyond weather forecasting. Their
The challenge for Google post-Gemini 4 will be what they do with a good model. Anthropic & OpenAI show we are moving towards a single interface for many tasks with orchestrator agents. The Gemini 3 er
arXiv:2610.11504v1 Announce Type: new Abstract: Modern autonomous driving systems rely on bird's-eye-view (BEV) perception models that fuse camera and LiDAR inputs to detect objects in 3D space. These
Figure 1b from our paper Disclosure: I'm one of the authors (Microsoft). The paper, code, dataset are public and ThinkingBox is on Hugging Face OpenEnv as well. Raw evaluation trajectories are not rel
arXiv:2610.12242v1 Announce Type: new Abstract: Large language model (LLM) routing distributes inference work across different models, advancing the cost-quality Pareto frontier of LLM serving. While
arXiv:2610.11561v1 Announce Type: new Abstract: LLM-based agents now interact with their environments continuously, shaped by such organizational channels as user instructions, peer messages, and long
Preamble and disclaimer, Sample size: 8, at any size of form this research is just screwing around being writing it down. This was just a little,(well... big), curiosity test I wanted to run to see wh
Aisha Malik / TechCrunch: AI hardware startup Natura unveils Interface, a 99 smart ring that connects to AI agents and apps, including Claude, ChatGPT, Muse, Grok Bot, and Instinct — Meet Interface, a
arXiv:2610.09003v1 Announce Type: new Abstract: Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and l
arXiv:2412.08843v3 Announce Type: replace-cross Abstract: Allocation stability is often used to justify Gaussian inference from bandit data, but when is it necessary? In this paper, we address this qu
arXiv:2610.09206v1 Announce Type: new Abstract: Loss-difference conditional mutual information (ld-CMI) uses the smallest of the standard observations in the supersample hierarchy of generalization bo