Knowledge catalogue
arXiv:2510.14925v4 Announce Type: replace Abstract: High-confidence errors in large language models are often treated as fragile failures. We study an alternative: some errors may be false fixed point
arXiv:2605.24710v1 Announce Type: new Abstract: We establish four structural results for feature learning in wide two-layer neural networks under the Maximal Update Parametrization (muP). First, we pr
arXiv:2605.24057v1 Announce Type: cross Abstract: Neural networks acquire structured representations at specific moments during training, yet identifying these transitions typically relies on retrospe
arXiv:2603.05143v3 Announce Type: replace Abstract: Understanding reasoning in large language models is complicated by evaluations that conflate multiple reasoning types. We isolate analogical reasoni
arXiv:2605.24062v1 Announce Type: cross Abstract: Human-body communication (HBC) is a promising physical substrate for wearable body-area networks because it can localize communication around the body
arXiv:2501.19389v4 Announce Type: replace Abstract: Fine-tuning large language models (LLMs) on resource-constrained clients remains a challenging problem. Recent works have fused low-rank adaptation
arXiv:2605.24386v1 Announce Type: cross Abstract: Fermi-Dirac machines were proposed recently as an approach to solving semidefinite optimization problems on quantum computers. Here, we reinterpret th
arXiv:2603.06218v2 Announce Type: replace Abstract: Accurate physics simulation is essential for robotic learning and control, yet analytical simulators often fail to capture complex contact dynamics,
arXiv:2510.10921v3 Announce Type: replace-cross Abstract: Fine-grained vision-language understanding requires precise alignment between visual content and linguistic descriptions, a capability that re
Financial Times: Filing: Monzo reports its “refer a friend” payouts grew 40% YoY to £29.5M for the 12 months ending March 2026, as part of a broader £143M marketing spend — London-based fintech record
arXiv:2605.24192v1 Announce Type: cross Abstract: The neural-network denoising functions which form the backbone of image diffusion models are remarkably consistent in their generalization behaviour a
arXiv:2605.25645v1 Announce Type: cross Abstract: We present the first end-to-end demonstration of fine-tuning and serving Google's Gemma 4 31B model on TPU hardware, providing an empirical comparison
arXiv:2602.02605v2 Announce Type: replace-cross Abstract: Evaluating true metacognition in Large Language Models (LLMs) is difficult due to biases and heuristics. This paper presents a framework to me
arXiv:2510.01384v4 Announce Type: replace Abstract: A natural desideratum for generative models is self-correction--detecting and revising low-quality tokens at inference. While Masked Diffusion Model
arXiv:2605.25816v1 Announce Type: cross Abstract: Personally identifiable information (PII) detection systems are frequently trained within narrow source or domain boundaries, limiting coverage when d
Firecrawl, a web scraping and data extraction tool, has been integrated into the Vercel Marketplace, enabling developers to easily incorporate its capabilities into their Vercel-hosted projects. This
Fireworks is coming to Tech Week, and we're doing it across multiple cities. Boston is up first. We're co-hosting a Founder Skybar Social with @fin_ai and @TrustVanta. Follow along via #BOSTechWeek In
Yohei Nakajima announced the first arXiv citation of ActiveGraph, positioning it as a complementary runtime tool. The announcement included a working bridge example in the repository, indicating pract
arXiv:2605.25258v1 Announce Type: cross Abstract: Recommender systems generally optimises user engagement, but this approach is dangerous in mental health contexts. When vulnerable users show signs of
arXiv:2511.03548v2 Announce Type: replace Abstract: Understanding the generalization behavior of learning algorithms is a central goal of learning theory. A recently emerging explanation is that learn
arXiv:2602.09620v2 Announce Type: replace Abstract: Constraint Answer Set Programming (CASP) is a hybrid paradigm that enriches Answer Set Programming (ASP) with numerical constraint processing, a cru
arXiv:2605.25717v1 Announce Type: new Abstract: Most of the world's offshore wind resource lies in waters too deep for fixed-bottom foundations, making floating offshore wind turbines (FOWTs) essentia
arXiv:2507.07644v4 Announce Type: replace Abstract: We introduce FloorplanQA, a diagnostic benchmark for evaluating spatial reasoning in large language models (LLMs). FloorplanQA is grounded in struct
arXiv:2506.09199v2 Announce Type: replace-cross Abstract: Integrating Low-Rank Adaptation (LoRA) into federated learning offers a promising solution for parameter-efficient fine-tuning of Large Langua
arXiv:2605.24503v1 Announce Type: cross Abstract: As AI-powered compliance monitoring becomes increasingly important in public governance and industrial safety, the ability to provide verifiable evide
for ActiveGraph, i'm using Cofounder by @intelligenceco as my... cofounder I'm working on the repo, doing research. Cofounder built the website, manages newsletter/blog, and when I do a new blog or ha
Forecasting Scientific Progress with Artificial Intelligence https://arxiv.org/abs/2605.22681 Turns out AI is just as bad at forecasting biology and physics breakthroughs as we are. To be fair, most b
arXiv:2306.02216v3 Announce Type: replace Abstract: Federated Learning (FL) enables collaborative model training across distributed clients while preserving user privacy. Recently, Federated Unlearnin
arXiv:2605.26097v1 Announce Type: new Abstract: Models trained on a new task typically degrade on prior tasks, a phenomenon known as forgetting. Traditionally, mitigating forgetting has required repla
arXiv:2605.26007v1 Announce Type: new Abstract: Dementia detection from spontaneous speech offers a scalable approach to cognitive screening, yet NLP systems remain predominantly English-centric. This
arXiv:2605.24432v1 Announce Type: new Abstract: Large Language Model (LLM) interactions are typically underspecified, with users clarifying all necessary details across multiple conversational turns.
arXiv:2605.25371v1 Announce Type: new Abstract: We present the first approach to build hierarchical task-driven 3D scene graphs of arbitrary indoor or outdoor environments using an uncalibrated monocu
arXiv:2605.24278v1 Announce Type: new Abstract: We present an improved neural field architecture for solving partial differential equations (PDEs). Current physics-informed neural networks (PINNs) pro
arXiv:2502.01184v2 Announce Type: replace-cross Abstract: Molecular representation learning methods typically tokenize molecules as individual atoms or use rigid, rule-based fragment decompositions, l
arXiv:2507.06038v4 Announce Type: replace-cross Abstract: Building on our previous work on Fredholm Neural Networks (Fredholm NNs/ FNNs) for solving integral equations, we extend the framework to inve
Clem Delangue advocates for the release of a 100 billion parameter Gemma 4 Mixture of Experts model, suggesting that Gemini Flash 3.5's release creates an opportunity for this larger model to be made
arXiv:2603.16105v3 Announce Type: replace-cross Abstract: Post-training model compression is essential for enhancing the portability of Large Language Models (LLMs) while preserving their performance.
arXiv:2605.25854v1 Announce Type: new Abstract: The expansion of data centers (DCs) drives a sustained increase in electricity demand and associated water withdrawals at generation sites. These withdr
arXiv:2605.23955v1 Announce Type: new Abstract: Deploying machine learning in regulated financial environments -- credit risk, fraud detection, and anti-money laundering -- exposes critical vulnerabil
arXiv:2605.25226v1 Announce Type: new Abstract: Large language models are widely deployed in high-stakes NLP tasks, yet risks such as bias, hallucination, adversarial vulnerability and unreliable gene
arXiv:2605.25526v1 Announce Type: cross Abstract: We study the geometry of determinantal point processes (DPPs) through the spectral decomposition L=ULambda U^{op}. The spectrum Lambda governs the car
arXiv:2605.25693v1 Announce Type: new Abstract: While role-playing agents excel in short-term interactions, long-term conversations overwhelm context windows, motivating external memory frameworks. Cu
Building an AI app shouldn’t require a PhD in machine learning (ML) or months of wrestling with complex architectures. Yet that’s exactly what happens when you try to orchestrate multiple API calls, m
arXiv:2605.23962v1 Announce Type: cross Abstract: This research aims to leverage machine learning to improve stock price prediction and support informed investment decisions related to buying, selling
arXiv:2602.00491v2 Announce Type: replace Abstract: Public health reasoning requires population level inference grounded in scientific evidence, expert consensus, and safety constraints. However, it r
arXiv:2605.25939v1 Announce Type: cross Abstract: We here study whether training biases can make hidden neurons specialize in minimal one-hidden-layer MLPs, and whether such specialization improves pr
arXiv:2605.26112v1 Announce Type: new Abstract: This paper studies the next major bottleneck in agentic AI as system scaling, not only model scaling: the design of auditable, persistent, modular, and
arXiv:2507.10644v4 Announce Type: replace Abstract: The Web of Agents (WoA) transforms the document-centric Web into an environment of autonomous agents acting on users' behalf, a vision newly tractab
arXiv:2605.24316v1 Announce Type: new Abstract: Scaling laws provide compact descriptions of how prediction error varies with compute, model size, and data, but existing theory mainly treats single-sa
arXiv:2510.23008v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated promising performance in generating diagnostic conclusions from imaging findings, thereby supporting
arXiv:2506.11027v3 Announce Type: replace-cross Abstract: Generating accurate and executable code using Large Language Models (LLMs) remains a significant challenge for underrepresented programming la
arXiv:2605.25459v1 Announce Type: cross Abstract: Language models are pretrained as passive predictors with no incentive to model the consequences of their own outputs. Post-training changes this: a m
arXiv:2505.05371v2 Announce Type: replace-cross Abstract: Automation of sleep analysis, including both macrostructural (sleep stages) and microstructural (e.g., sleep spindles) elements, promises to e
arXiv:2605.24771v1 Announce Type: cross Abstract: Classical noisy-label theory predicts that downstream performance under weak supervision is bounded above by the labeler's accuracy, implying a sharp
arXiv:2605.25246v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used for optimization modeling and solver-code generation, yet practical operations research and optimizat
arXiv:2605.05759v2 Announce Type: replace Abstract: It is well established that spectral graph neural networks (GNNs) can universally approximate node signals; however, their expressive power remains
arXiv:2605.24727v1 Announce Type: new Abstract: While large-scale models such as LLMs and diffusion models have achieved practical success, public institutions have emphasized the importance of explai
arXiv:2603.18454v2 Announce Type: replace-cross Abstract: Fundamental limits on the performance of feedback controllers are essential for benchmarking algorithms, guiding sensor selection, and certify
arXiv:2412.07333v2 Announce Type: replace-cross Abstract: Pose-Guided Person Image Synthesis (PGPIS) aims to generate human images in specified poses while preserving the identity and appearance of a
arXiv:2605.25239v1 Announce Type: new Abstract: We present FusionCore, an open-source ROS 2 sensor fusion package that fuses IMU, wheel encoder odometry, GPS, and Visual SLAM pose into a single 100 Hz