Knowledge catalogue
this is … odd. the whole problem with agentic code is that people wind up with hard to debug redundancies, security holes, deleted databases, etc., which is exactly why you need roadmaps and code revi
This is really well thought out. Filesystems are the new default abstraction for agents to interact with documents (the new RAG stack in 2026). The issue is actually figuring out how to productize thi
The San Francisco–based startup Goodfire just released a new tool, called Silico, that lets researchers and engineers peer inside an AI model and adjust its parameters—the settings that determine a mo
arXiv:2604.26946v1 Announce Type: new Abstract: Breakthrough progress in vision-based navigation through unknown environments has been achieved by using multimodal large language models (MLLMs). These
arXiv:2505.13963v3 Announce Type: replace Abstract: Quantization methods are widely used to accelerate inference and streamline the deployment of large language models (LLMs). Although quantization's
arXiv:2603.08182v2 Announce Type: replace-cross Abstract: Large language models often underperform in many European languages due to the dominance of English and a few high-resource languages in train
Reuters: Tim Cook says iPhone sales, which slightly missed Q2 estimates, were held back by chip supply constraints, as “demand was off the charts” — Apple (AAPL.O) on Thursday reported results that be
arXiv:2505.24867v2 Announce Type: replace-cross Abstract: Recent advances in vision-language models (VLMs) have made impressive strides in understanding spatio-temporal relationships in videos. Howeve
arXiv:2409.01115v5 Announce Type: replace Abstract: This article presents a new approach based on MiniRocket, called SelF-Rocket, for fast time series classification (TSC). Unlike existing approaches
arXiv:2604.26247v1 Announce Type: cross Abstract: Multimodal recommendation improves user modeling by integrating collaborative signals with heterogeneous item content. In real applications, user inte
arXiv:2503.04872v3 Announce Type: replace-cross Abstract: The challenge of reducing the size of Large Language Models (LLMs) while maintaining their performance has gained significant attention. Howev
arXiv:2604.26553v1 Announce Type: cross Abstract: Large language models (LLMs) demonstrate strong multilingual capabilities, yet often fail to consistently generate responses in the intended language,
Today we announced a multi-agent system built with SMBC, one of Japan’s largest banks. It handles complex corporate strategy proposals, reducing a one to two week workflow down to just a few hours. ht
Today we’re announcing the full rebuild of our advertising platform, the most ambitious in X’s 20-year history. This is classic X and xAI: bold, fast, and built for advertisers. I’m incredibly proud o
Today we’re releasing Qwen-Scope 🔭, an open suite of sparse autoencoders for the Qwen model family. It turns SAE features into practical tools： 🎯 Inference — Steer model outputs by directly manipulati
I cannot verify the authenticity of this post or its specific claims about Grok 4.3's performance metrics. The source appears to reference xAI's Grok model improving significantly on benchmark leaderb
arXiv:2510.14703v2 Announce Type: replace Abstract: Large language models (LLMs) excel at function calling, but inference scaling has been explored mainly for unstructured generation. We propose an in
arXiv:2604.26370v1 Announce Type: new Abstract: Vision-language models have shown strong performance, but they often generalize poorly to specialized domains. While semi-supervised vision-language lea
arXiv:2509.23980v2 Announce Type: replace Abstract: Diffusion models have recently shown promising results for video super-resolution (VSR). However, directly adapting generative diffusion models to V
Train a TensorFlow object detection model – then deploy it on a robot 🤖 Iulia Feroli (@iuliaferoli) shows how to turn a notebook into a real-time object detection app. This tutorial works for any proj
arXiv:2604.26020v1 Announce Type: cross Abstract: Usability testing with experts and potential users can assess the effectiveness, efficiency, and user satisfaction of graphical user interfaces (GUIs)
arXiv:2601.03423v3 Announce Type: replace-cross Abstract: Adapting language models to the clinical domain through continued pretraining and instruction tuning requires costly retraining for each new m
arXiv:2511.22972v3 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance across diverse tasks but suffer from high inference latency due to their autoregressive gene
arXiv:2604.26597v1 Announce Type: cross Abstract: Timely and reliable multilingual communication is critical during natural and human-induced disasters, but developing effective solutions for crisis c
arXiv:2604.07692v2 Announce Type: replace Abstract: Large Multimodal Models (LMMs) achieve state-of-the-art performance in high-stakes domains like healthcare, yet their reasoning remains opaque. Curr
arXiv:2604.26501v1 Announce Type: cross Abstract: Generating sports game reports from structured tables is a complex table-to-text task that demands both precise data interpretation and fluent narrati
✨🧠 Tribe v2, our latest model of human brain responses to sound, sight and language can now be (partly) explored on your phone📱: ▶️demo: https://aidemos.atmeta.com/tribev2/ 📄paper: https://ai.meta.com
President Trump nominated radiologist and Fox News contributor Dr. Nicole Saphier for surgeon general , replacing Dr. Casey Means whose nomination stalled in the Senate over questions about her experi
Trump's war on science. The Trump administration has downsized US science by historic margins — but it's not just via grant or workforce cuts. Our new @nature analysis reveals the government has cut m
Clem Delangue shares his experience using OpenAI's GPT 5.5 within an ML internship context for practical machine learning tasks including dataset creation, model training, and model optimization, as w
arXiv:2604.26951v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer parallel decoding and bidirectional context, but state-of-the-art dLLMs require billions of parameters f
tweeted about this yesterday and Cursor already dropped the alpha today! 🚀very cool to see how us, them, and others have converged on good design patterns in Agent + Harness Engineering: 1. Tuning dif
Reinhardt Krause / Investor's Business Daily: Twilio reports Q1 revenue up 20% YoY to 1.41B, vs. 1.34B est., and forecasts Q2 revenue above estimates; TWLO jumps 17%+ after hours — Twilio (TWLO) stock
Two Heads Are Better Than One: Async Knowledge Injection for Speech AI with Tandem Architecture Blog: https://pub.sakana.ai/kame/ 🐢 KAME: Tandem Architecture for Enhancing Knowledge in Real-Time Speec
arXiv:2412.10679v3 Announce Type: replace Abstract: Blood pressure (BP) measurement is crucial for daily health assessment. Remote photoplethysmography (rPPG), which extracts pulse waves from face vid
arXiv:2506.16742v3 Announce Type: replace Abstract: To be adopted in safety-critical domains like medical image analysis, AI systems must provide human-interpretable decisions. Variational Information
arXiv:2604.26873v1 Announce Type: new Abstract: We propose UAPAR, an Uncertainty-Aware Pedestrian Attribute Recognition framework. To the best of our knowledge, this is the first EDL-based uncertainty
arXiv:2604.26836v1 Announce Type: new Abstract: Predictive safety filters (PSFs) leverage model predictive control to enforce constraint satisfaction during deep reinforcement learning (RL) exploratio
arXiv:2604.26360v1 Announce Type: cross Abstract: Reinforcement learning (RL) systems typically optimize scalar reward functions that assume precise and reliable evaluation of outcomes. However, real-
arXiv:2604.26489v1 Announce Type: new Abstract: DNNs have gained widespread adoption in feature interaction recommendation models. However, there has been a longstanding debate on their roles. On one
arXiv:2604.26694v1 Announce Type: cross Abstract: We propose X-WAM, a Unified 4D World Model that unifies real-time robotic action execution and high-fidelity 4D world synthesis (video + 3D reconstruc
arXiv:2604.26411v1 Announce Type: new Abstract: Runtime monitoring is essential to ensure the safety of ML applications in safety-critical domains. However, current research is fragmented, with indepe
arXiv:2604.26837v1 Announce Type: new Abstract: Long-context LLM serving is bottlenecked by the cost of attending over ever-growing KV caches. Dynamic sparse attention promises relief by accessing onl
This post demonstrates how agentic AI assistant from Amazon Quick transform data analytics into a self-service capability by using Amazon Simple Storage Service (Amazon S3) as a storage, Amazon SageMa
This article describes how to integrate SAP business context and semantic metadata with Databricks using Delta Sharing, enabling organizations to share and analyze SAP data while preserving business m
arXiv:2604.26216v1 Announce Type: new Abstract: This paper addresses the problem of anomaly detection in accounting subject association structures, proposing a structured modeling and unsupervised dis
v0.22.1-rc1 is a pre-release version of Ollama that includes improvements to MLX sampler batching, tokenizer BPE offset handling, NVIDIA TensorRT Model Optimizer support, and fixes for desktop app sta
arXiv:2512.03992v2 Announce Type: replace-cross Abstract: Vision-Language Models (VLMs) are essential for embodied AI and safety-critical applications, such as robotics and autonomous systems. However
arXiv:2601.00545v3 Announce Type: replace Abstract: Many problems in robotics involve both continuous and discrete components, and modeling them together for estimation tasks has been a long standing
Spotify is launching a new verification program to combat spam, fakes, and AI. Some artists will now have a 'Verified by Spotify' badge and a green checkmark on their profile, indicating that the comp
arXiv:2602.03412v2 Announce Type: replace Abstract: As large language model agents tackle increasingly complex long-horizon tasks, effective post-training becomes critical. Prior work faces fundamenta
arXiv:2508.07852v2 Announce Type: replace-cross Abstract: Recent research on learnable neural representations has been widely adopted in the field of 3D scene reconstruction and neural rendering appli
arXiv:2509.09870v2 Announce Type: replace-cross Abstract: Large language models (LLMs) enable conversational agents (CAs) to express distinctive personalities, raising new questions about how such des
arXiv:2604.26218v1 Announce Type: new Abstract: Brain encoding models not only serve to decipher how visual stimuli are transformed into neural responses, but also represent a critical step toward vis
arXiv:2604.26806v1 Announce Type: cross Abstract: Transformer-based architectures have established a dominant paradigm in global semantic perception; however, they remain fundamentally constrained by
arXiv:2603.05811v2 Announce Type: replace Abstract: Current video generation models suffer from high computational latency, making real-time applications prohibitively costly. In this paper, we addres
arXiv:2505.22897v2 Announce Type: replace Abstract: While bias in large language models (LLMs) is well-studied, similar concerns in vision-language models (VLMs) have received comparatively less atten
arXiv:2604.26781v1 Announce Type: new Abstract: Surgical training involves didactic teaching, mentor-led learning, surgical skills laboratories, and direct exposure to surgery; however, increasing cli
arXiv:2505.20032v3 Announce Type: replace Abstract: Tactile sensing provides local essential information that is complementary to visual perception, such as texture, compliance, and force. Despite rec
arXiv:2603.07080v3 Announce Type: replace-cross Abstract: Vision-and-Language Navigation (VLN) increasingly relies on large vision-language models, but their inference cost conflicts with real-time de