Quoting Jeremy Howard
Easy solution to slow down recursive AI self improvement: The lab with the top-ranked model must agree THEY must not use it for working on frontier AI But everyone else should have access to it. By de
Knowledge catalogue
Easy solution to slow down recursive AI self improvement: The lab with the top-ranked model must agree THEY must not use it for working on frontier AI But everyone else should have access to it. By de
arXiv:2606.10324v1 Announce Type: new Abstract: The analogy between deep neural network forward passes and renormalization group (RG) flows has been repeatedly noted in the literature, but existing tr
arXiv:2606.10908v1 Announce Type: cross Abstract: We introduce a spoofing countermeasure architecture conditioned on speaker-reference recordings, but observe that it converges to a solution that effe
arXiv:2606.10794v1 Announce Type: new Abstract: As agentic applications increasingly route user tasks through official and third-party LLM APIs, provenance becomes an operational question: which model
arXiv:2606.10694v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly expected to interact with users over long time horizons. However, due to their finite context window, LLMs
Really enjoyed reading the Microsoft MAI-Thinking-1 'Building a Hill Climbing Machine' paper. Amazing they publicly released all the info needed to train a frontier model, down to hparams. I also thou
arXiv:2606.10254v1 Announce Type: new Abstract: While Large Language Models (LLMs) have achieved near-perfect performance in solving high-school mathematics, their ability to evaluate the diverse reas
arXiv:2606.11164v1 Announce Type: new Abstract: Long chain-of-thought (CoT) trajectories in large language model (LLM) reasoning cause severe inference bottlenecks due to rapid key-value (KV) cache gr
arXiv:2606.10949v1 Announce Type: new Abstract: Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time. We show they also make models less correct by systematica
arXiv:2606.10929v1 Announce Type: cross Abstract: Task vectors, LoRA, activation steering, and random search around pretrained weights all suggest that learned behaviour can be controlled by linear di
arXiv:2606.10813v1 Announce Type: cross Abstract: Users rely on execution traces to observe agent behavior, diagnose failures, and ensure accountability. These traces contain rich procedural detail, i
arXiv:2606.10359v1 Announce Type: new Abstract: AI agents in supply chains face a fundamental epistemic gap: large language models (LLMs) interpret policies but lack physical grounding, while reinforc
arXiv:2510.07061v2 Announce Type: replace Abstract: While automatic metrics drive progress in Machine Translation (MT) and Text Summarization (TS), existing metrics have been developed and validated a
arXiv:2510.14828v3 Announce Type: replace Abstract: Improving the reasoning capabilities of embodied agents is crucial for robots to complete complex human instructions in long-view manipulation tasks
arXiv:2605.06234v2 Announce Type: replace Abstract: Embodied AI is a prominent research topic in both academia and industry. Current research centers on completing tasks based on explicit user instruc
arXiv:2606.09873v1 Announce Type: cross Abstract: Reasoning models achieve strong performance on challenging tasks by generating explicit intermediate reasoning traces before producing a final answer.
arXiv:2604.01993v2 Announce Type: replace-cross Abstract: Multi-hop QA benchmarks often reward Large Language Models (LLMs) for spurious correctness, where models reach correct answers through invalid
arXiv:2606.09926v1 Announce Type: cross Abstract: Sampling from the sequence-level power distribution p^alpha elicits RL-level reasoning from base language models without any parameter updates, but th
arXiv:2606.10305v1 Announce Type: new Abstract: Fine-tuning vision-language-action (VLA) policies for long-horizon manipulation still relies heavily on behavior cloning, which requires costly high-qua
arXiv:2606.10804v1 Announce Type: new Abstract: Controlled character animation requires transferring motion from a driving sequence to a reference character. Prior works heavily rely on intermediate r
arXiv:2512.17629v4 Announce Type: replace-cross Abstract: Prescriptive Process Monitoring (PresPM) recommends interventions during running business processes to optimize key performance indicators (KP
arXiv:2606.09886v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the
arXiv:2606.10228v1 Announce Type: cross Abstract: Safe exploration is a prerequisite for deploying reinforcement learning (RL) agents in safety-critical domains. In this paper, we approach safe explor
arXiv:2606.09924v1 Announce Type: cross Abstract: Deploying deep neural networks on memory-constrained edge accelerators is bottlenecked by per-inference off-chip weight transfer rather than computati
arXiv:2606.10286v1 Announce Type: new Abstract: Open-pit mine scheduling is a critical process for maximizing economic return under complex geotechnical and operational constraints. While Mixed-Intege
arXiv:2606.10388v1 Announce Type: cross Abstract: Agent skill libraries are becoming routable software assets: a retrieved skill can contribute instructions, scripts, resource bindings, and execution
arXiv:2606.10610v1 Announce Type: new Abstract: Parameter-Efficient Fine-Tuning (PEFT) has become essential for adapting foundation models to downstream NLP tasks. However, current PEFT methods often
Tom Warren / The Verge: Sources: Microsoft is restricting employees from using Claude Fable 5 because of Anthropic's new 30-day data retention requirements — Microsoft's legal teams are evaluating Ant
arXiv:2606.09868v1 Announce Type: cross Abstract: As Multimodal Large Language Models (MLLMs) face growing privacy risks and regulatory constraints, machine unlearning (MU) has emerged as a crucial so
arXiv:2606.09917v1 Announce Type: new Abstract: Multivariate time series forecasting requires capturing the continuously evolving correlation structure among interacting variables. Existing state-spac
arXiv:2606.10021v1 Announce Type: new Abstract: Lumbar spine conditions are a leading cause of disability worldwide, yet reliable quantification of degeneration from MRI remains challenging. In clinic
arXiv:2606.10617v1 Announce Type: new Abstract: Low-Rank Adaptation (LoRA) merging can efficiently combine diverse generative capabilities from multiple trained LoRAs for a diffusion model. However, e
arXiv:2606.10394v1 Announce Type: new Abstract: Large language models are increasingly used to power personal agents for everyday applications, but evaluating these agents remains a challenge. Existin
arXiv:2606.09877v1 Announce Type: cross Abstract: LLM wiki systems compile knowledge into pre-filled KV caches for efficient inference, but assume a static corpus -- an assumption that fails whenever
arXiv:2606.11015v1 Announce Type: new Abstract: Tuning controllers for strongly coupled multi-input multi-output (MIMO) industrial processes is hard: decentralized classical auto-tuning ignores loop i
arXiv:2606.11070v1 Announce Type: cross Abstract: Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However,
arXiv:2606.09959v1 Announce Type: cross Abstract: Precipitation nowcasting is increasingly being approached with deep learning models that learn directly from recent radar observations. Although such
arXiv:2606.10071v1 Announce Type: cross Abstract: We introduce Temporal Sheaf Neural Networks (TSNN), a temporal link prediction framework that equips each node with a time-varying orthogonal frame an
arXiv:2606.09885v1 Announce Type: new Abstract: Mixture-of-Experts large language models (LLMs) scale efficiently through sparse activation, yet their deployment is fundamentally constrained by the la
arXiv:2606.10894v1 Announce Type: new Abstract: This paper presents an overview of the inaugural PortraitCraft Challenge, held as one of the official competitions at CVPR 2026. The challenge focuses o
arXiv:2601.20970v3 Announce Type: replace-cross Abstract: The maximum-entropy remote sampling problem (MERSP) is to select a subset of s random variables from a set of n random variables, so as to max
arXiv:2606.09844v1 Announce Type: cross Abstract: Large Language Models (LLMs) alter their privacy behavior based on the perceived identity of their interlocutor. While safety mechanisms typically pre
arXiv:2606.10327v1 Announce Type: new Abstract: Automated Essay Scoring (AES) systems must judge interdependent discourse elements (e.g., lead, claim, evidence, conclusion), yet most approaches treat
the paper is long (30 pages), but have your AI read it: https://arxiv.org/abs/2606.10241 here's a simple interactive tutorial on the topic that claude made: https://claude.ai/public/artifacts/038db6cf
arXiv:2606.11082v1 Announce Type: new Abstract: This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large language models (LLMs) subjected to sustained advers
“They have been running literally the same play for seven years: scare, hype (evoking media interest), and (eventually) release. Scare, hype, release. And repeat. Is it that hard to see?” 👇🏼 - @GaryMa
This is a great article on how startups/frontier labs can coexist. Another way to look at this is task complexity - the number of bits of information needed to specify a task such that AI can solve th
arXiv:2606.09927v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is one of the most practical ways to reduce the serving cost of Large Language Models (LLMs), but activation quantiza
arXiv:2606.10860v1 Announce Type: cross Abstract: Production LLMs receive instructions from sources with very different levels of trust, yet attend to every token with uniform architectural privilege.
arXiv:2606.09898v1 Announce Type: new Abstract: Cancer treatment planning requires decisions across multiple clinical dimensions at once. Clinicians must determine whether a patient should receive tar
arXiv:2606.11032v1 Announce Type: new Abstract: Existing deep learning models for Positron Emission Tomography (PET) image denoising often suffer from severe performance degradation under distribution
arXiv:2606.10382v1 Announce Type: new Abstract: Real-robot evaluation is essential for understanding whether learned manipulation policies can operate reliably outside curated demonstrations. This nee
arXiv:2606.09958v1 Announce Type: cross Abstract: In mixed-traffic environments where autonomous and human-driven vehicles may co-exist, motion planning for autonomous vehicles requires anticipating t
arXiv:2606.09570v2 Announce Type: replace Abstract: As AI assistants serve millions of users daily, evaluating user experience (UX) beyond general model capability has become increasingly important. W
arXiv:2512.11995v2 Announce Type: replace-cross Abstract: While many vision-language models (VLMs) are developed to answer well-defined, straightforward questions with highly specified targets, as in
arXiv:2606.10393v1 Announce Type: new Abstract: Credit-card fraud detection is difficult because fraudulent transactions are rare, costly, and unevenly distributed. Strong gradient-boosted tree models
Want to learn more about the Far-Field ASR benchmark? Join Treble's webinar tomorrow, June 11th, with @shinjiw_at_cmu, Cohere's @Julianfmack, and other industry leaders discussing the future of far-fi
We need more real time data on how AI may be impacting the economy - this is a really useful addition. Today, the Stanford @DigEconLab launches the AI Economic Indicators, a new platform for tracking
arXiv:2606.10423v1 Announce Type: new Abstract: Autonomous web navigation remains challenging for LLM agents, and the strongest generalist systems rely on proprietary reasoning models whose inference
arXiv:2606.10229v1 Announce Type: cross Abstract: We study whether demonstration-curation metrics that detect defective training episodes also improve the downstream behavior-cloning policy that train