Knowledge catalogue
arXiv:2606.10799v1 Announce Type: new Abstract: Large Language Models (LLMs) struggle to rigorously verify complex mathematical proofs. Standard global evaluation approaches suffer from 'context poiso
Everyone Operating At The Frontier Satya Nadella, Chairman & CEO, Microsoft, interviewed by @saranormous & @eladgil (No Priors) and @swyx (Latent Space) Crossover special at Microsoft Build 2026. Summ
everything your agents do, in a bucket you own. private by default. session traces, task claims, artifacts — claude code, hermes, whatever you run. and make your agents friends via messaging https://h
arXiv:2606.10380v1 Announce Type: cross Abstract: Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.Real-world crisis intervention is i
arXiv:2606.10086v1 Announce Type: new Abstract: This paper develops a theory of exploratory adaptation under AI-assisted optimization. The central argument is that the long-run adaptive effects of AI
arXiv:2506.09171v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are increasingly capable, but LLM agents still struggle to plan effectively in interactive, partially observable,
arXiv:2606.11106v1 Announce Type: cross Abstract: A global shortage of trained sonographers limits prenatal ultrasound screening in low- and middle-income countries, where over half of pregnant women
arXiv:2606.09884v1 Announce Type: cross Abstract: We study two reproducible failure modes of deep multi-agent reinforcement learning in continuous-time pricing markets: (i) tacit cartel formation betw
arXiv:2606.09878v1 Announce Type: new Abstract: Standard benchmarks report aggregate accuracy, but practitioners need to know which specific capabilities a model lacks. We introduce FailureScope, a be
arXiv:2606.10196v1 Announce Type: cross Abstract: Parameter-efficient fine-tuning (PEFT) aims to adapt pretrained models with a small trainable parameter subset, however, most existing methods choose
arXiv:2606.11166v1 Announce Type: cross Abstract: Large Language Models (LLMs) are increasingly described as performing at the level of human experts on knowledge economy tasks. These claims are prima
arXiv:2505.16319v3 Announce Type: replace Abstract: Accurate demand estimation is critical for the retail business in guiding the inventory and pricing policies of perishable products. However, it fac
LSEG (London Stock Exchange Group) is implementing trusted AI systems to enhance decision-making processes across its financial services operations. The article likely discusses how LSEG is leveraging
arXiv:2606.10703v1 Announce Type: cross Abstract: Interpretability methods routinely use population-level summary statistics over observed model behaviour to license claims about the effects of target
arXiv:2606.10778v1 Announce Type: new Abstract: Foundation Models (FMs) have recently redefined the state-of-the-art in histopathology by providing robust representations for whole-slide image (WSI) a
arXiv:2606.10933v1 Announce Type: new Abstract: LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories. These benc
arXiv:2606.10159v1 Announce Type: cross Abstract: AI is increasingly used to support scientific peer review, from manuscript screening, reviewer assistance to editorial triage. Although such systems p
arXiv:2606.10611v1 Announce Type: cross Abstract: Traditional heuristic solvers for the 2D irregular nesting problem share a fundamental limitation: they are blind to polygon geometry, relying on guid
arXiv:2603.09979v2 Announce Type: replace Abstract: Persian poetry plays an active role in Iranian cultural practice, where verses by canonical poets such as Hafez are frequently quoted, paraphrased,
arXiv:2606.09935v1 Announce Type: cross Abstract: AI-powered agents are increasingly embedded in continuous integration and continuous delivery/deployment (CI/CD) pipelines to autonomously review pull
The Keyword: Google introduces DiffusionGemma, an experimental 26B-parameter open model that uses text diffusion for faster text generation compared to autoregressive models — Our newest open experime
Google LLC’s newest artificial intelligence tool promises to bring real-time translation to every smartphone user, enabling more natural and fluid conversations between speakers of different languages
arXiv:2507.14725v4 Announce Type: replace-cross Abstract: Prompt-based continual learning (CL) offers a parameter-efficient way to adapt large language models (LLMs) across task sequences. However, ex
Grok Build is pretty good at optimizing my code in one shot. Prompt: I want you to optimize it entirely on GPU to speed it up. Measure two metrics: the result must compare with the golden image (CPU)
arXiv:2606.10839v1 Announce Type: new Abstract: Current identity-consistent video generation methods struggle to preserve appearance fidelity under large viewpoint changes. While introducing multi-vie
Simon Willison demonstrated Fable's pelican illustrations generated at different Claude API thinking effort levels, showcasing how increased computational investment affects output quality and cost. T
HISTORY LESSON: In 1968 the US, USSR, UK, France, and China signed the Nuclear Non-Proliferation Treaty, declaring nuclear weapons too dangerous for any more countries to build. All five already had t
arXiv:2510.09801v3 Announce Type: replace Abstract: While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of re
arXiv:2606.09880v1 Announce Type: new Abstract: Large-scale dynamic weighted directed networks (DWDNs) are widely used to model time-varying interactions among nodes. Latent factorization of tensors (
I argued, publicly, AGAINST each of these foolish predictions– and got endless shit for it. Moral: on X, you probably shouldn’t trust the “wisdom” of the crowds. Remember all the AI predictions people
I too have felt the latest Claude's to be too smart its bored. Glad others are noticing the same Claude Fable 5 thinks document parsing is beneath it It is absolutely crushing on all reasoning-intensi
arXiv:2606.09908v1 Announce Type: cross Abstract: Large language models (LLMs) are becoming widely deployed as personal AI assistants with access to sensitive user data, making privacy a major challen
If Claude Fable stops helping you, you'll never know Jonathon Ready highlights one of the more eyebrow-raising details from the 319 page system card for Fable 5 and Mythos 5. Here's a longer excerpt,
arXiv:2606.10392v1 Announce Type: new Abstract: Financial named-entity recognition (NER) is essential for translating unstructured financial reports and news into structured knowledge graphs. However,
arXiv:2606.09916v1 Announce Type: cross Abstract: Multi-turn LLM agents fan short queries into long trajectories of tool calls, search results, and intermediate reasoning. Both KV memory and KV read b
arXiv:2501.04339v2 Announce Type: replace-cross Abstract: We introduce the Deep Convolutional Interpreter for Time Series (DCIts), a deep-learning architecture for nonlinear multivariate time series t
arXiv:2606.10088v1 Announce Type: new Abstract: Reduced facial expressivity is a common motor manifestation of Parkinson's disease (PD), often described as hypomimia or facial bradykinesia. This paper
arXiv:2606.11001v1 Announce Type: new Abstract: Zinc-based alloys are indispensable emerging absorbable metallic biomaterials, and their macroscopic performance is governed by microstructural characte
arXiv:2606.10136v1 Announce Type: new Abstract: Semantic segmentation in remote sensing requires costly pixel-level annotations, and nearly every problem demands a new dataset since models rarely tran
arXiv:2606.10852v1 Announce Type: cross Abstract: LLM deception is often evaluated through direct markers such as fabricated claims, explicit lies, or strategic concealment. However, many real-world m
arXiv:2606.09964v1 Announce Type: cross Abstract: The NISQ era places stringent constraints on quantum computation, where noise and decoherence fundamentally limit performance. In classical deep learn
arXiv:2606.10403v1 Announce Type: new Abstract: Math reasoning benchmarks have proliferated, yet most lack a per-item difficulty signal grounded in actual human performance. We introduce KCSAT-ML, a d
arXiv:2606.10651v1 Announce Type: new Abstract: We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding
arXiv:2606.10460v1 Announce Type: cross Abstract: Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can b
arXiv:2506.03672v2 Announce Type: replace-cross Abstract: Combinatorial Optimization problems are widespread in domains such as logistics, manufacturing, and drug discovery, yet their NP-hard nature m
arXiv:2606.10209v1 Announce Type: new Abstract: Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can ca
arXiv:2606.09900v1 Announce Type: cross Abstract: Long-term memory is the missing layer for LLM agents: across sessions they forget, and the common workaround -- replaying the whole history into the p
The Texas Tribune: Letter: Texas Governor Greg Abbott released regulatory recommendations for state lawmakers to ensure that data centers shoulder the costs of their growth — The recommendations for l
arXiv:2606.10862v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models achieve strong performance on standard manipulation benchmarks, but most evaluations assume that task-relevant obj
arXiv:2606.09865v1 Announce Type: new Abstract: Privacy and data sharing are often in tension. Many organizations use synthetic data to reduce privacy risk and still share useful data. For tabular dat
arXiv:2606.09852v1 Announce Type: cross Abstract: High-quality source code documentation is vital yet often neglected, especially in critical domains like healthcare where reliability and maintainabil
arXiv:2606.10173v1 Announce Type: cross Abstract: As AI systems move into operating systems, privacy no longer turns only on whether a model runs locally. A local assistant may assemble email, calenda
arXiv:2606.10349v1 Announce Type: cross Abstract: We present a magnetic extension of the Hierarchically Interacting Particle Neural Network (HIP-NN) that enables large-scale simulations of electron-me
Me, 2024. LLMs will be commodity; (except for Nvdia) profits will be hard to squeeze out. Techbros: Shut up, Gary. GPT-5 is gonna be AGI. Today: LLMs are commodity; (except for Nvidia) profits have be
Meet DiffusionGemma! An experimental open model that explores a fast approach to text generation, released under an Apache 2.0 license. Moving beyond sequential, token-by-token processes to generate e
arXiv:2606.10742v1 Announce Type: cross Abstract: External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However,
Anthropic released Claude Fable, its first Mythos-class AI model, yesterday and it's already causing concerns inside Microsoft. Sources tell me that Microsoft is limiting the use of Claude Fable 5 for
arXiv:2606.10956v1 Announce Type: new Abstract: The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade p
arXiv:2606.10304v1 Announce Type: new Abstract: When LLM agents are coerced into covertly encoding sensitive data (Base64, ROT13, acrostic, synonym chains, and beyond), the resulting outputs evade out
arXiv:2404.09101v3 Announce Type: replace-cross Abstract: Operator-learning systems are not governed solely by total parameter count; for one query, the relevant bottleneck can be the model that must