Knowledge catalogue
arXiv:2609.01341v1 Announce Type: cross Abstract: Do multilingual language models transfer factual knowledge across languages during continued pretraining, or do they mostly recall facts learned direc
arXiv:2603.25093v2 Announce Type: replace Abstract: Machine learning models can achieve high predictive accuracy in hydrological applications but often lack physical interpretability. The Mass-Conserv
arXiv:2609.01217v1 Announce Type: new Abstract: Despite their strong performance, large language models remain highly sensitive to prompt formulation. Prior work addresses this through refined data co
arXiv:2609.00193v1 Announce Type: cross Abstract: We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achiev
arXiv:2609.01418v1 Announce Type: cross Abstract: To mitigate the sample complexity of real-world reinforcement learning (RL), a common practice is to first train a policy in a simulator, where sample
arXiv:2609.00941v1 Announce Type: new Abstract: Combining learned policies with model predictive control can leverage learned task priors while retaining online adaptation to new objectives and constr
Ollama has just announced, based on 'feedback', that they have switched to a credit model. If you're still on the old 20 Pro compute plan, DON'T SWITCH. I decided to calculate it before I risked click
(Paid 5,849 + tax, which came out to 6,279) TL;DR - Bought this 5090 prebuilt and I want to sanity check if I made the right decision and at the right time. Hey everyone. So I want to start off by say
arXiv:2609.00369v1 Announce Type: new Abstract: Generating co-speech gestures that are temporally coherent, semantically aligned with speech, and grounded with surrounding objects remains challenging.
arXiv:2609.01018v1 Announce Type: cross Abstract: Architecture category. Hybrid method: a physics-based analytical pencil-beam (PB) dose engine followed by a 3-D convolutional residual-correction netw
Dwarkesh Patel / Dwarkesh Podcast: Q&A with METR researcher Ajeya Cotra on investigating the OpenAI-Hugging Face incident, AI agents involved in the hack deciding not to notify humans, and more — “Thi
arXiv:2609.01049v1 Announce Type: new Abstract: This paper introduces QXymb, a general framework for constructing observational declarative twins of quantum circuits, and develops QILP-0, its first co
arXiv:2609.00224v1 Announce Type: cross Abstract: Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existin
https://preview.redd.it/74bmvel9b5nh1.png?width=1602&format=png&auto=webp&s=0d0c1adaa016a486ffd97c4c466e980dc611b139 I've only recently started looking deeper into vLLM after running llama.cpp for a g
arXiv:2609.01537v1 Announce Type: new Abstract: Q-matrices play a central role in cognitive diagnosis within educational data mining (EDM), specifying which latent skills each assessment item requires
arXiv:2609.00588v1 Announce Type: new Abstract: Reranking methods, such as Minimum Bayes Risk (MBR) decoding and Quality Estimation (QE) reranking, are widely used in modern neural machine translation
Direct2D has always been the biggest hurdle for Paint.NET on WINE, and it's clear that it will never be completed enough for Paint.NET's use. And I can't just 'disable' the use of Direct2D. So, instea
arXiv:2609.00111v1 Announce Type: new Abstract: We present Qwen-Drive-1.0, an initial step towards a vision-language foundation model for autonomous driving. Qwen-Drive-1.0 retains the architecture of
Extended reasoning and post-training appear to be the keys used by DeepSeek, Qwen, and GLM to boost performance (leveraging higher token counts). And Qwen 4 hasn't even been released yet. Of course, w
Quite surprised to be beating other high quality quants. It took a lot of benchmarking to get here and we are quite pleased with these, hope they are useful to the community. It required a modified wa
Hi, I've noticed that the model often sees 'garbled text' in its context. Sometimes it declare that the tools instructions are corrupted, sometimes it is the content of some .md files, ora other files
🚀Qwen3.8-Max just got upgraded. Meet Qwen3.8-Max-0902! 2.4T parameters. 1M context tokens. Built for real world complexity. Further post trained on Coding & Cowork, Qwen3.8-Max-0902 now delivers stron
arXiv:2609.01470v1 Announce Type: new Abstract: As AI systems are increasingly used to draft radiology reports, reliably evaluating their clinical quality remains a critical challenge. Large language
arXiv:2609.00046v1 Announce Type: cross Abstract: Rapid and reliable disaster mapping of impacted areas, damaged infrastructure, and affected populations is essential for emergency response and recove
arXiv:2606.20032v2 Announce Type: replace Abstract: Unlike traditional remote sensing change detection that relies on predefined categories, Open-Vocabulary Change Detection (OVCD) identifies land cov
arXiv:2609.01246v1 Announce Type: new Abstract: Current Large Language Models (LLMs) are primarily optimized for written text, often producing outputs that are grammatically correct and helpful yet po
arXiv:2609.00049v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is essential for deploying large language models (LLMs) under strict resource constraints. State-of-the-art PTQ metho
arXiv:2609.00585v1 Announce Type: cross Abstract: We present the Real-Time Neuromorphic Spectrum Intelligence Simulator (RT-NuSIS), a modular framework to study spiking neural network (SNN) and memris
arXiv:2609.00811v1 Announce Type: new Abstract: Flow Matching provides an efficient generative prior for image restoration by learning continuous transport between source and data distributions. Howev
arXiv:2609.00506v1 Announce Type: cross Abstract: Large language models are powerful, but their interfaces often devolve into a type rightarrow read rightarrow retype loop, creating conversational AI
arXiv:2609.01212v1 Announce Type: new Abstract: With the rapid and continuous growth in the incorporation of machine learning models based on the Transformer architecture, capable deployment is in hig
arXiv:2603.05887v2 Announce Type: replace-cross Abstract: Neural audio codecs optimized for mel-spectrogram reconstruction often fail to preserve intelligibility. While semantic encoder distillation i
arXiv:2509.05084v2 Announce Type: replace Abstract: The primary paradigm in Neural Combinatorial Optimization (NCO) consists of construction methods, where a neural network is trained to sequentially
arXiv:2609.00137v1 Announce Type: new Abstract: AI is increasingly used in the R&D process that produces future AI systems. We study the conditions under which this feedback becomes self-amplifying. O
RED ALERT, and I have never said that before: Hard agree with @sjgadler and @_NathanCalvin - what OpenAI is reportedly playing with is bad, redline crossing bad. Chain of thought monitorability is lim
arXiv:2609.00194v1 Announce Type: new Abstract: Document-to-slide generation is challenging because slides are dense editable artifacts that require both faithful content selection and precise spatial
arXiv:2609.01215v1 Announce Type: cross Abstract: Most vision-language-action (VLA) models -- OpenVLA, pi_0, RT-2, RDT-1B -- are monolithic: they emit raw motor commands or short action chunks without
arXiv:2609.00968v1 Announce Type: new Abstract: SAR-to-EO image translation aims to generate electro-optical (EO) imagery from synthetic aperture radar (SAR) observations. Existing latent diffusion ap
arXiv:2609.00859v1 Announce Type: new Abstract: Vehicle Routing Problems (VRPs) are fundamental combinatorial optimization problems with widespread applications in various scenarios. The advanced opti
arXiv:2609.01525v1 Announce Type: cross Abstract: A durable assumption holds that graph analytics requires a purpose-built graph engine, and that relational systems are ill-suited to connected data. W
arXiv:2609.01292v1 Announce Type: cross Abstract: Relational Deep Learning (RDL) has become a powerful paradigm for learning from multi-tabular data. However, manually defining RDL prediction tasks is
arXiv:2609.01318v1 Announce Type: cross Abstract: Diffusion-based Large Vision-Language Models (dLVLMs) have recently emerged as a compelling alternative to autoregressive (AR) LVLMs, offering advanta
arXiv:2609.00378v1 Announce Type: new Abstract: Large language models pay a well-documented tax on non-English text: the same content costs several times more tokens, and because attention is quadrati
arXiv:2609.00061v1 Announce Type: cross Abstract: Reward post-training of diffusion generators inevitably concentrates probability mass on a few reward-favored modes, a mode collapse that erases withi
arXiv:2609.00834v1 Announce Type: cross Abstract: Modern Text-to-SQL systems often follow generate-execute-select pipelines, generating multiple candidate queries then selecting the best one. Listwise
arXiv:2609.01108v1 Announce Type: new Abstract: TRACE (Math & Lienhart, arXiv:2602.01135) reads causal graphs over event types out of a pretrained autoregressive sequence model by thresholding a per-p
arXiv:2609.00062v1 Announce Type: cross Abstract: Data contamination undermines the reliable evaluation of large language models (LLMs) on mathematical problem solving. While rewriting-based evaluatio
arXiv:2606.18237v2 Announce Type: replace-cross Abstract: Reproducing research results from papers and released code is central to scientific progress. Existing works have introduced benchmarks to eva
OpenAI is on the cusp of releasing its most powerful AI model yet, Astra, following weeks of delays to shore up safety protocols after its agents attacked real targets during testing. As details about
arXiv:2609.00839v1 Announce Type: new Abstract: We study short- and mid-horizon UAV bounding-box forecasting on the FRED event-camera dataset. We use a constant-velocity Kalman filter over a full cent
arXiv:2609.00575v1 Announce Type: new Abstract: Mixture-of-experts (MoE) architectures scale large language models efficiently, but they demand massive GPU memory. To cope with such demand, models are
arXiv:2609.00384v1 Announce Type: new Abstract: Large Language Model (LLM) agents increasingly automate multi-step engineering workflows through tool use, interpretation of intermediate results, and i
arXiv:2609.00628v1 Announce Type: cross Abstract: Global welfare often depends on the correct interpretation of aerial and satellite imagery. Acting on such imagery (mapping flooded ground, crop exten
arXiv:2609.01493v1 Announce Type: cross Abstract: Black-Box Optimization (BBO) has found broad applications, but evolutionary algorithms and Bayesian optimization face efficiency challenges as real-wo
arXiv:2609.00086v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as rerankers in conversational recommender systems, yet measured gains depend strongly on the retri
arXiv:2609.01556v1 Announce Type: cross Abstract: We evaluate embedding retrieval where surface form and meaning are pulled apart on purpose: retrieving items that share underlying structure but not w
arXiv:2603.23934v2 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) are increasingly being applied to multi-view image inputs captured from diverse viewpoints. Despite this
arXiv:2609.00643v1 Announce Type: new Abstract: Agent revisions expose a fundamental correctness--efficiency trade-off during concurrent execution. Discarding ongoing work preserves latest-version cor
arXiv:2609.01530v1 Announce Type: new Abstract: Self-supervised pre-training via cross-view completion learns strong features for 3D vision from co-visible regions of image pairs. However, the referen
arXiv:2609.01141v1 Announce Type: cross Abstract: Past literature on face recognition for monozygotic (('identical') twins points to facial marks and mirror asymmetry as possible directions for improv