Knowledge catalogue
Today I re-iterate: I hate MoEs and we are wasting time on them.... Let's unite and call a global ban on MoEs please. Please 1M+ salary researchers: do better... credits to @IlysMoutawwakil for the gr
Today we open sourced many of OpenAI's monitorability evaluations. We hope that the research community and other model developers can build upon them and use them to evaluate the monitorability of the
Tomorrow live on the show, we have Brandon Middleton, our new Head of Educational Partnerships. He's building what's next for Replit and education. Plus Content Challenge Week 4 winner @rizwanahmedmp4
Tool Attention Is All You Need // Tool Attention Is All You Need // New research proposes a practical fix for the hidden 'MCP tax.' The work introduces a dynamic tool gating mechanism built on an Inte
arXiv:2604.21816v1 Announce Type: new Abstract: The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on s
arXiv:2603.24111v3 Announce Type: replace-cross Abstract: The Industrial Internet of Things (IIoT) introduces significant security challenges as resource-constrained devices become increasingly integr
arXiv:2604.21197v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) enable multiple parties to collaboratively fine-tune LLMs without sharing raw data, addressing challenges of l
arXiv:2604.20895v1 Announce Type: cross Abstract: Safety and security are essential for the admission and acceptance of automated and autonomous vehicles. Deep neural networks (DNNs) are widely used f
arXiv:2510.03247v2 Announce Type: replace-cross Abstract: Active learning (AL) is a principled strategy to reduce annotation cost in data-hungry deep learning. However, existing AL algorithms focus al
arXiv:2604.21696v1 Announce Type: new Abstract: Tabular foundation models aim to learn universal representations of tabular data that transfer across tasks and domains, enabling applications such as t
arXiv:2604.21057v1 Announce Type: new Abstract: The field of Language Reasoning Models (LRMs) has been very active over the past few years with advances in training and inference techniques enabling L
arXiv:2604.21840v1 Announce Type: cross Abstract: Modern phishing campaigns increasingly evade snapshot-based URL classifiers using interaction gates (e.g., checkbox/slider challenges), delayed conten
Ananya Bhattacharya / Rest of World: Tracxn: global edtech funding fell from 16.7B in 2021 to 2.6B in 2025, while the number of startups launched dropped from 10,491 in 2021 to just 645 in 2025 — Vent
arXiv:2604.02832v2 Announce Type: replace-cross Abstract: Accurate forecasting of recovery rates (RR) is central to credit risk management and regulatory capital determination. In many loan portfolios
arXiv:2604.21761v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) have garnered significant interest for their potential in solving partial differential equations (PDEs) that go
arXiv:2604.21657v1 Announce Type: new Abstract: Machine learning methods that predict initial guesses from molecular geometry can reduce this cost, but matrix-prediction models fail when extrapolating
arXiv:2511.03232v2 Announce Type: replace Abstract: Recently, Mamba-based super-resolution (SR) methods have demonstrated the ability to capture global receptive fields with linear complexity, address
arXiv:2604.21860v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This pape
arXiv:2604.21093v1 Announce Type: cross Abstract: We introduce TravelFraudBench (TFG), a configurable benchmark for evaluating graph neural networks (GNNs) on fraud ring detection in travel platform g
The Trump administration and congressional Republicans have spent the last year attempting to weaken the Endangered Species Act, but one major effort faced a significant setback when Republicans in th
🔴 Trump vient de publier sur Truth Social un monologue de 1 500 mots sur le droit du sol, l'ACLU, les Indiens, les Chinois et la 'Savage Nation'. Ce texte inhabituellement long, inhabituellement cohér
arXiv:2604.21193v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable fluency and versatility across a wide range of NLP tasks, yet they remain prone to factual ina
arXiv:2604.21349v1 Announce Type: cross Abstract: Self-supervised learning (SSL) is a standard approach for representation learning in aerial imagery. Existing methods enforce invariance between augme
arXiv:2604.21263v1 Announce Type: new Abstract: extbf{Background:} Regulatory frameworks for AI in healthcare, including the EU AI Act and FDA guidance on AI/ML-based medical devices, require clinical
Cognition AI announced an early preview opportunity for Devin integrated with GPT-5.5 Agent capabilities, inviting users to test the combination at devin.ai. This likely represents an update to Devin'
arXiv:2512.08216v3 Announce Type: replace-cross Abstract: Accurate segmentation of lung tumors from 3D computed tomography (CT) scans is essential for automated treatment planning and response assessm
arXiv:2512.03465v3 Announce Type: replace-cross Abstract: In this study, we more rigorously evaluated our attack script extit{TraceTarnish}, which leverages adversarial stylometry principles to anonym
arXiv:2509.10897v2 Announce Type: replace Abstract: Balancing spectral, spatial, and temporal resolutions is a key challenge in spectral imaging. The Dual-Camera Coded Aperture Snapshot Spectral Imagi
arXiv:2604.21227v1 Announce Type: new Abstract: Facial action unit (AU) detection remains challenging because it involves heterogeneous, AU-specific uncertainties arising at both the representation an
arXiv:2512.20288v2 Announce Type: replace-cross Abstract: Recent advances in deep learning have led to its widespread adoption across diverse domains, including medical imaging. This progress is drive
arXiv:2604.21471v1 Announce Type: new Abstract: Infrastructure-based localization enhances road safety and traffic management by providing state estimates of road users. Development is hindered by fra
arXiv:2604.21435v1 Announce Type: new Abstract: Ultra-High-Resolution (UHR) imagery has become essential for modern remote sensing, offering unprecedented spatial coverage. However, detecting small ob
arXiv:2604.21534v1 Announce Type: new Abstract: This paper presents our system developed for SemEval-2026 Task 2. The task requires modeling both current affect and short-term affective change in chro
arXiv:2604.21549v1 Announce Type: new Abstract: Estimating the prevalence of a category in a population using imperfect measurement devices (diagnostic tests, classifiers, or large language models) is
arXiv:2604.21327v1 Announce Type: cross Abstract: Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization sig
arXiv:2604.21904v1 Announce Type: new Abstract: In recent years, significant progress has been made in both image generation and generated image detection. Despite their rapid, yet largely independent
arXiv:2604.21032v1 Announce Type: new Abstract: Multi-spectral imagery is a valuable input signal for Remote Sensing applications, such as land-use and land-cover classification and environmental moni
arXiv:2604.21713v1 Announce Type: new Abstract: Feed-forward visual geometry estimation has recently made rapid progress. However, an important gap remains: multi-frame models usually produce better c
arXiv:2604.21238v1 Announce Type: new Abstract: Multi-table entity matching (MEM) addresses the limitations of dual-table approaches by enabling simultaneous identification of equivalent entities acro
arXiv:2604.04685v2 Announce Type: replace-cross Abstract: We propose a data-adaptive probabilistic intensity remapping framework for structure-preserving transformation of grayscale images. The sugges
arXiv:2604.20925v1 Announce Type: new Abstract: While current deep learning models achieve high performance by learning statistical correlations from vast datasets,which stands in stark contrast to hu
arXiv:2508.15840v5 Announce Type: replace-cross Abstract: When using a public communication channel--whether formal or informal, such as commenting or posting on social media--end users have no expect
This post discusses upgrading from SDXL in ComfyUI workflows, specifically comparing which newer AI image generation models offer full support for ControlNet (spatial control), IPAdapter (image prompt
A U.S. special forces soldier who was part of the operation to capture Venezuelan President Nicolás Maduro has been arrested and charged for allegedly betting on the operation in the prediction market
arXiv:2604.21603v1 Announce Type: cross Abstract: We explore the use of answer set programming (ASP) and its extension with quantifiers, ASP(Q), for inconsistency-tolerant querying of prioritized data
arXiv:2604.21144v1 Announce Type: cross Abstract: Situated dialogue requires speakers to maintain a reliable representation of shared context rather than reasoning only over isolated utterances. Curre
Ollama v0.21.2 improved reliability of the OpenClaw onboarding flow in ollama launch, made recommended models appear in a fixed canonical order, and bundled Ollama's web search plugin in OpenClaw inte
I was unable to find specific information about v0.21.3-rc0 in the search results—the latest release information shows v0.21.2. Based on the version numbering and Ollama's release pattern, v0.21.3-rc0
arXiv:2604.20921v1 Announce Type: new Abstract: We evaluated whether a glaucoma risk assessment (GRA) model trained on All of Us national data can identify patients at high probability of glaucoma usi
arXiv:2604.20995v1 Announce Type: new Abstract: Alignment faking, where a model behaves aligned with developer policy when monitored but reverts to its own preferences when unobserved, is a concerning
arXiv:2604.21450v1 Announce Type: cross Abstract: Recent advancements in visual autoregressive models (VAR) have demonstrated their effectiveness in image generation, highlighting their potential for
arXiv:2604.21599v1 Announce Type: cross Abstract: Machine Learning (ML) Engineering is a growing field that necessitates an increase in the rigor of ML development. It draws many ideas from software e
Very cool demo by @Box how progressive skill loading works in practice 👀 The agent walks through onboarding step-by-step: load employee → load skill → scoped search → synthesize Instead of one giant p
arXiv:2510.18457v3 Announce Type: replace Abstract: The performance of Latent Diffusion Models (LDMs) is critically dependent on the quality of their visual tokenizers. While recent works have explore
arXiv:2604.21502v1 Announce Type: new Abstract: In real-world scenarios, continual changes in weather, illumination, and imaging conditions cause significant domain shifts, leading detectors trained o
arXiv:2604.21396v1 Announce Type: cross Abstract: The advancement of Large Vision-Language Models (LVLMs) requires precise local region-based reasoning that faithfully grounds the model's logic in act
arXiv:2411.16771v3 Announce Type: replace Abstract: Vision Large Language Models (VLLMs) are widely acknowledged to be prone to hallucinations. Existing research addressing this problem has primarily
arXiv:2604.21915v1 Announce Type: new Abstract: We present Vista4D, a robust and flexible video reshooting framework that grounds the input video and target cameras in a 4D point cloud. Specifically,
arXiv:2604.21914v1 Announce Type: new Abstract: Recently, end-to-end robotic manipulation models have gained significant attention for their generalizability and scalability. However, they often suffe
arXiv:2604.03956v2 Announce Type: replace-cross Abstract: Vision-language-action (VLA) models are emerging as embodied foundation models for robotic manipulation, but their deployment introduces a new