Knowledge catalogue
The best way to learn AI is to build with agents. To help with that, we've launched hands-on labs and a new series on Agentic Engineering. First topic: Agent Skills. Next in the pipeline: planning, co
arXiv:2605.21882v1 Announce Type: new Abstract: Vision-language models (VLMs) often fail under low illumination because their visual grounding is learned predominantly from RGB imagery, whereas therma
arXiv:2605.22705v1 Announce Type: new Abstract: We introduce Tokenization with Split Trees (ToaST), a subword tokenization method that directly optimizes compression under a new recursive inference pr
arXiv:2605.22192v1 Announce Type: new Abstract: Blind image quality assessment (BIQA) for ultrahighdefinition (UHD) images remains challenging because native-resolution inference is computationally ex
arXiv:2602.02112v2 Announce Type: replace-cross Abstract: Masked diffusion models (MDMs) are a potential alternative to autoregressive models (ARMs) for language generation, but generation quality dep
arXiv:2602.00122v2 Announce Type: replace Abstract: In recent years, image editing models have made significant progress, enabling users to manipulate visual content in a flexible and interactive mann
arXiv:2605.22096v1 Announce Type: new Abstract: Capsule endoscopy event detection is challenging because clinically relevant findings are sparse, visually heterogeneous, and evaluated at the event lev
arXiv:2605.21807v1 Announce Type: new Abstract: Across medical specialties, clinical practice is anchored in evidence-based guidelines that codify best studied diagnostic and treatment pathways. These
arXiv:2602.06995v2 Announce Type: replace-cross Abstract: This paper surveys the state-of-the-art in the nexus of SLAM and Wireless Communications, attributing the bidirectional impact of each with a
arXiv:2605.22201v1 Announce Type: new Abstract: Zero-shot temporal action localization (ZS-TAL) consists of classifying and localizing actions in untrimmed videos, where action classes are unseen at t
arXiv:2605.20495v1 Announce Type: new Abstract: Deep-learning pipelines for microscopy image classification often require expensive, labor- and time-intensive expert annotation to produce high-quality
arXiv:2605.20988v1 Announce Type: new Abstract: We study transformers' generalization behavior on boolean domains from the perspective of the Fourier Spectra of their target functions. In contrast to
arXiv:2605.20530v1 Announce Type: cross Abstract: Large language model agents now act on codebases, browsers, operating systems, calendars, files, and tool ecosystems, but the benchmarks used to evalu
arXiv:2605.21083v1 Announce Type: cross Abstract: Materials discovery and biomedical translation increasingly require models that can reason across composition, processing, structure, biological respo
arXiv:2605.21481v1 Announce Type: cross Abstract: Recent advances in artificial intelligence (AI) have accelerated the growth of both human-authored and AI-generated research outputs, placing increasi
Always read the fine print: Anthropic is projecting its first (slightly) profitable quarter ever, which is amazing—assuming it actually happens —but if it does it will be in no small part because they
arXiv:2602.19320v2 Announce Type: replace Abstract: Agentic memory systems enable large language model (LLM) agents to maintain state across long interactions, supporting long-horizon reasoning and pe
arXiv:2605.20249v1 Announce Type: new Abstract: Gaussian Process (GP) kernels are central to Bayesian optimization (BO), yet designing effective kernels for high-dimensional problems still relies on e
Release b9270 adds support for the HybridDNATokenizer used by the Carbon-3B model family, implementing a new BPE pre-type for tokenizing DNA sequences. The tokenizer handles DNA k-mers with fixed 6-me
arXiv:2605.20684v1 Announce Type: new Abstract: Corporate credit underwriting requires analysts to extract actionable evidence from long, heterogeneous financial documents spanning hundreds of pages a
arXiv:2506.04042v2 Announce Type: replace Abstract: Knowledge editing is pivotal for efficiently updating the parametric memory of Large Language Models (LLMs), enabling them to function as evolving a
arXiv:2605.20796v1 Announce Type: new Abstract: We introduce a manifold-based framework for addressing optimization problems with equality and inequality constraints found in robotics. Our approach tr
arXiv:2602.02304v2 Announce Type: replace-cross Abstract: Large-scale foundation models exhibit behavioral shifts when subjected to interventions such as scaling, fine-tuning, reinforcement learning w
arXiv:2605.20936v1 Announce Type: cross Abstract: Hybrid attention architectures are becoming an increasingly important paradigm for improving LLM inference efficiency while preserving model quality,
arXiv:2605.21308v1 Announce Type: new Abstract: State Space Models (SSMs) have emerged as a powerful and efficient alternative to Transformers, demonstrating linear-time complexity and exceptional seq
arXiv:2605.20856v1 Announce Type: cross Abstract: Language-conditioned manipulation policies typically process instructions and observations through shared network parameters. This task-state entangle
arXiv:2605.20405v1 Announce Type: cross Abstract: Class imbalance is a fundamental challenge in medical image segmentation, where frequent classes typically dominate training at the expense of rare cl
arXiv:2601.03019v4 Announce Type: replace-cross Abstract: DNA language models are increasingly used to represent genomic sequence, yet their effectiveness depends critically on how raw nucleotides are
arXiv:2605.20678v1 Announce Type: new Abstract: Non-stationary time series forecasting is challenged by evolving distribution shifts that static models struggle to capture. While Mixture-of-Experts (M
arXiv:2605.20470v1 Announce Type: new Abstract: Cone-beam CT (CBCT) is routinely acquired during radiotherapy for patient setup, but its quantitative reliability is degraded by scatter, noise, and rec
arXiv:2605.21485v1 Announce Type: new Abstract: Equivariant graph neural network (GNN) methods for antibody complementarity-determining region (CDR) design achieve the highest sequence recovery but su
arXiv:2601.18696v4 Announce Type: replace Abstract: Hardware trojans are malicious circuits which compromise the functionality and security of an integrated circuit (IC). These circuits are manufactur
Gated DeltaNet-2 is here. 🚀 🔥 New paper: Gated DeltaNet-2: Decoupling Erase and Write in Linear Attention Gated DeltaNet-2 outperforms KDA and Mamba-3, the latest and best recurrent architectures, hea
arXiv:2605.20896v1 Announce Type: cross Abstract: Defending against today's increasingly sophisticated cyberattacks requires security analysts to continuously translate evolving attacker tradecraft in
arXiv:2605.20435v1 Announce Type: cross Abstract: Make America Healthy Again (MAHA) is a national health movement that encompasses a striking mix of beliefs, from broadly accepted concerns about good
arXiv:2605.20997v1 Announce Type: new Abstract: Integrating machine learning (ML) with physical models (PM) has emerged as a promising way of retrieving geophysical parameters from remote sensing data
arXiv:2605.21309v1 Announce Type: new Abstract: Cooperative perception enabled by Vehicle-to-Everything (V2X) communication enhances autonomous driving safety by creating a unified environmental repre
arXiv:2605.21431v1 Announce Type: new Abstract: Video Virtual Try-On (VVT) aims to seamlessly replace a garment on a person in a video with a new one. While existing methods have made significant stri
arXiv:2605.20904v1 Announce Type: new Abstract: We propose JFAA, a JEPA-based Future Action Anticipation method for the EPIC-KITCHENS-100 (EK-100) Action Anticipation task. Inspired by the representat
arXiv:2603.23531v2 Announce Type: replace Abstract: Political polarization emerges from a complex interplay of beliefs about policies, figures, and issues. However, most computational analyses reduce
arXiv:2601.22292v2 Announce Type: replace-cross Abstract: Multi-agent social dilemmas, such as the tragedy of the commons, capture settings where individual incentives conflict with collective well-be
arXiv:2603.14324v3 Announce Type: replace-cross Abstract: Learning-to-Defer routes each input to the expert that minimizes expected cost, but it assumes that the information available to every expert
arXiv:2605.20297v1 Announce Type: new Abstract: Medical image segmentation faces a fundamental challenge in continual learning: data arrives sequentially from heterogeneous sources, yet effective cont
arXiv:2605.20948v1 Announce Type: new Abstract: Scaling conditional memory offers a promising way to increase language-model capacity, but existing methods such as Engram learn large memory tables fro
arXiv:2603.27309v2 Announce Type: replace-cross Abstract: We present MeshTailor, the first mesh-native generative framework for synthesizing edge-aligned seams on 3D surfaces. Unlike prior optimizatio
arXiv:2605.20668v1 Announce Type: new Abstract: With the advancement of AI capabilities, AI reviewers are beginning to be deployed in scientific peer review, yet their capability and credibility remai
arXiv:2605.20941v1 Announce Type: new Abstract: We present PaintCopilot, a co-creative neural painting assistant that models painting as an open-ended autoregressive artistic behavior conditioned on e
arXiv:2605.21207v1 Announce Type: new Abstract: The rapid evolution of generative AI, from GANs to modern diffusion models, has resulted in increasingly subtle discriminative clues. These fine-grained
arXiv:2603.23890v2 Announce Type: replace-cross Abstract: As the modern microservice architecture for cloud applications grows in popularity, cloud services are becoming increasingly complex and more
arXiv:2605.20867v1 Announce Type: cross Abstract: Multimodal sarcasm detection requires reasoning over cross-modal incongruities between literal expression and intended meaning, yet the specific analy
arXiv:2605.21454v1 Announce Type: new Abstract: We introduce ProtoPathway, an interpretable-by-design multimodal framework for cancer survival prediction that unifies whole slide imaging and transcrip
arXiv:2605.20813v1 Announce Type: new Abstract: Inference in diffusion large language models (dLLMs) is computationally expensive, as full self-attention must be repeatedly executed at each step of th
arXiv:2605.20404v1 Announce Type: new Abstract: The rapid adoption of Generative AI, including LLM-based chatbots like ChatGPT, has highlighted the need for accessible ways to support public understan
arXiv:2605.21257v1 Announce Type: new Abstract: Planning through crowded environments under uncertain obstacle motions remains difficult, as stochastic interactions often induce overly conservative be
arXiv:2605.21088v1 Announce Type: new Abstract: Modern deep-learning models have achieved remarkable success in time-series forecasting. Yet, their performance degrades in long-term prediction due to
arXiv:2605.21411v1 Announce Type: new Abstract: Existing video-language models can generate factual descriptions of road events but lack control over how these events are expressed: their tone, urgenc
arXiv:2605.20433v1 Announce Type: new Abstract: Contact-rich manipulation tasks such as tight-clearance insertion, connector mating, polishing, and surface-conforming wiping remain difficult for data-
arXiv:2605.21333v1 Announce Type: new Abstract: Natively trained spiking language models struggle to combine Transformer-like language quality, stable multi-domain pre-training, and high activation sp
arXiv:2603.21033v2 Announce Type: replace-cross Abstract: Geotechnical site characterisation relies on sparse, heterogeneous borehole data, where uncertainty quantification and interpretability matter
arXiv:2506.08277v3 Announce Type: replace-cross Abstract: Recent voxel-wise multimodal brain encoding studies have shown that multimodal large language models (MLLMs) exhibit a higher degree of brain