Knowledge catalogue
arXiv:2609.23314v1 Announce Type: new Abstract: Modern LLMs with QK-normalization, gated attention, learned attention sinks, or logit softcapping exhibit weaker persistent attention sinks, on which ex
arXiv:2609.23733v1 Announce Type: new Abstract: Feed-forward visual geometry models such as the Visual Geometry Grounded Transformer (VGGT) have recently enabled direct 3D reconstruction from multi-vi
arXiv:2609.24031v1 Announce Type: new Abstract: In recent years, pre-training has become fundamental to learning effective video representations, enabling strong transfer to downstream tasks. A popula
arXiv:2609.24782v1 Announce Type: new Abstract: A new concept, termed virtual neural networks, is introduced, where the count of trainable parameters is kept constant, and scalability is attained pure
arXiv:2307.00852v3 Announce Type: replace Abstract: The natural language generation domain has witnessed great success thanks to Transformer models. Although they have achieved state-of-the-art genera
arXiv:2606.18389v2 Announce Type: replace Abstract: Large language models (LLMs) have become an effective tool for synthetic data generation, including for low-resource languages, where generated data
arXiv:2609.23016v1 Announce Type: cross Abstract: Deep learning models are powerful but opaque. As quantum machine learning matures, the field faces a defining choice: build quantum models that are eq
arXiv:2609.22145v1 Announce Type: cross Abstract: Diffusion large language models (dLLMs) offer a compelling alternative to autoregressive models, yet they may expose sensitive training data during de
arXiv:2609.24014v1 Announce Type: new Abstract: Reliable quality control (QC) of magnetic resonance imaging (MRI) is essential for reliable diagnostic neuroimaging, yet standard manual assessment is s
arXiv:2509.22367v3 Announce Type: replace Abstract: Large language models (LLMs) reflect politically-slanted opinions in their generated text. Even though it is widely assumed that model behavior stem
arXiv:2609.24691v1 Announce Type: new Abstract: Latent diffusion models now dominate medical image generation, and every such pipeline rests on a tokenizer that compresses images into the latent codes
arXiv:2609.22522v1 Announce Type: new Abstract: Cosine similarity is widely used to analyze transformer representations, implicitly assuming that similarity reflects task-relevant structure. We study
arXiv:2609.23102v1 Announce Type: new Abstract: Diffusion models and transformers have supplanted GANs for multivariate time series imputation, largely on grounds of GAN training instability. R3GAN (N
arXiv:2609.24028v1 Announce Type: new Abstract: Generating coherent meta-reviews from multiple peer reviews is challenging when reviewer evidence conflicts and varies in reliability. Existing approach
arXiv:2609.24819v1 Announce Type: cross Abstract: Mesopic and low-light display transforms require, as their driving signal, a per-pixel scotopic-to-photopic luminance ratio (S/P); the exact spectral
arXiv:2609.24799v1 Announce Type: new Abstract: Post-training quantization (PTQ) enables efficient deployment of large language models, and PTQ methods are usually optimized and evaluated with generic
arXiv:2609.24839v1 Announce Type: new Abstract: Feed-forward 3D reconstruction models enable efficient geometry estimation from sparse images, but their pretrained nature can make them vulnerable to d
arXiv:2609.23673v1 Announce Type: new Abstract: In vision-based off-road navigation, a robot needs to know not only which obstacles to avoid but also which terrain is better. The first is handled by f
arXiv:2609.23117v1 Announce Type: new Abstract: Whitening a foundation-model embedding and using its squared norm as a training-free likelihood surrogate is motivated by the observation that whitened
arXiv:2609.23260v1 Announce Type: new Abstract: Subliminal Learning (SL) is a recently identified phenomenon in which a student model acquires downstream task capabilities by matching seemingly unrela
arXiv:2609.22191v1 Announce Type: cross Abstract: Machine learning is being increasingly used to predict where active wildfires will burn the following day, helping inform evacuation boundaries and co
arXiv:2609.24984v1 Announce Type: new Abstract: Video world models enable interactive exploration of dynamic environments, yet struggle to respect prior observations over long horizons and across view
arXiv:2609.22315v1 Announce Type: new Abstract: Automated segmentation of CT images has become increasingly important to enhance the reliability of simulations through the generation of high fidelity
arXiv:2609.24106v1 Announce Type: new Abstract: Questions scraped from the web are used across academia and industry as a proxy for what people want to know. Across QA training data, retrieval benchma
arXiv:2609.22115v1 Announce Type: new Abstract: Zeroth-order optimization (ZOO) estimates updates from function evaluations, making perturbation queries a primary cost. Fixed budgets spend the same nu
arXiv:2609.21516v1 Announce Type: new Abstract: Active reconstruction requires efficient active view selection to achieve high-quality reconstruction within limited onboard computational resources. Ex
Clean energy isn’t hard to come by, but the pace of large-scale adoption has historically been slow due to bottlenecks — including out-of-date infrastructure, elongated research and development timeli
arXiv:2605.15418v2 Announce Type: cross Abstract: Hybrid optical systems combining refractive and diffractive optical responses have the potential to support new types of optical behavior, but they ar
arXiv:2609.21221v1 Announce Type: new Abstract: Perceptual planning tasks require two key capabilities: accurately perceiving uncertain scenes and planning valid action sequences following logical rul
arXiv:2609.21584v1 Announce Type: new Abstract: Wall-climbing robots capable of scaling vertical surfaces could help automate hazardous or labor intensive tasks such as window washing, inspection, mai
arXiv:2511.16923v1 Announce Type: cross Abstract: Single-cell RNA sequencing (scRNA-seq) enables transcriptomic profiling at cellular resolution but suffers from pervasive dropout events that obscure
arXiv:2509.21653v2 Announce Type: replace-cross Abstract: We propose a conversion scheme that turns regret minimizing algorithms into fixed point iterations, with convergence guarantees following from
arXiv:2609.21017v1 Announce Type: cross Abstract: We study data-driven early stopping for spectral regularisation methods in the classical non-parametric regression setting. Building on the discrepanc
arXiv:2609.22005v1 Announce Type: cross Abstract: Gating the value pathway of attention reportedly improves language model pretraining, and prior studies disagree on why. We argue and provide experime
arXiv:2609.21672v1 Announce Type: new Abstract: Large language models (LLMs) achieve strong performance but suffer from slow and costly inference. Existing acceleration methods often lead to noticeabl
arXiv:2609.21169v1 Announce Type: cross Abstract: Independent control of tonescale regions (e.g., shadows, highlights) is essential for painters, photographers and cinematographers to bring 2D images
arXiv:2609.21821v1 Announce Type: cross Abstract: This paper presents a novel framework integrating Bayesian physiological modeling with optimal control strategies to achieve uncertainty-aware, person
arXiv:2609.20999v1 Announce Type: cross Abstract: Latent variable generative models are commonly fit using simple priors over latent variables, but draws from these priors often fail to produce realis
arXiv:2406.08775v2 Announce Type: replace Abstract: Labels are the cornerstone of supervised machine learning algorithms. Most visual recognition methods are fully supervised, using bounding boxes or
arXiv:2603.22560v4 Announce Type: replace Abstract: Legged robots operate across a wide range of physical scales, but how their designs should be adapted as size changes remains unclear. Here, we tack
arXiv:2609.21309v1 Announce Type: new Abstract: Any lossless compression algorithm (like gzip) may be converted into a machine learning method, via either Normalized Compression Distance or the Minimu
arXiv:2609.21655v1 Announce Type: new Abstract: We propose a framework to analyse how strongly different linguistic relations are linearly encoded in language model embedding spaces. We formalise line
arXiv:2607.17582v2 Announce Type: replace Abstract: Approximate Nearest Neighbor Search (ANNS) plays a pivotal role in modern deep learning pipelines. Recently, many ANNS systems have been proposed to
arXiv:2609.20974v1 Announce Type: new Abstract: In Mixture-of-Experts language models, the router typically selects and weights experts based on the token's hidden state, utilizing limited contextual
arXiv:2609.21284v1 Announce Type: cross Abstract: Long-running AI agents outlive initiating processes through credentials, delegated tasks, queues, callbacks, reservations, and provider-side operation
arXiv:2609.21863v1 Announce Type: new Abstract: Empirical evaluation is central to recommender-systems (RecSys) research, but turning experimental designs into executable code remains a manual and err
arXiv:2609.21377v1 Announce Type: new Abstract: Robotic fabric comparison needs to actively combine visual appearance and tactile cues. Here, we present AVT-Fabric, an RGB-first framework that allocat
arXiv:2609.21743v1 Announce Type: cross Abstract: Entropy minimization is a standard objective for test-time adaptation (TTA), but it can fail in imbalanced binary segmentation. Unlike image classific
arXiv:2609.21694v1 Announce Type: cross Abstract: Context: We developed a probabilistic machine learning method with the aim of performing the O(10)-way classification of low- and high-resolution spec
arXiv:2509.22754v2 Announce Type: replace-cross Abstract: Autonomous driving remains a highly active research domain that seeks to enable vehicles to perceive dynamic environments, predict the future
arXiv:2609.21362v1 Announce Type: new Abstract: Conventional tokenizers represent text as characters or statistically derived subwords, overlooking the internal phonological structure of syllables and
arXiv:2609.21231v1 Announce Type: new Abstract: Reference-based metrics for Grammatical Error Correction (GEC) such as M^2 and ERRANT assume that the reference set enumerates all valid edits, and ther
arXiv:2609.20828v1 Announce Type: new Abstract: ASR systems optimised for Word Error Rate (WER) often miss named entities and filled pauses in accented conversational English, both critical for langua
arXiv:2609.21758v1 Announce Type: new Abstract: Topology optimization (TO) represents a significant step towards automating the design process: given a working simulation, TO can produce a viable prot
arXiv:2609.21422v1 Announce Type: cross Abstract: Deep representation learning often selects hidden features and fits the final predictor on the same sample, so fixed-feature analysis performed after
arXiv:2506.07327v4 Announce Type: replace Abstract: Saliency methods are widely used to visualize which input features are deemed relevant to a model's prediction. However, their visual plausibility c
arXiv:2609.21022v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have shown strong generalization in robotic manipulation by combining semantic knowledge from pretrained vision-lang
arXiv:2609.21887v1 Announce Type: new Abstract: The gold standard datasets for mapping connectomes are electron microscopy volumes of densely labeled neural tissue at nanometer resolution. Yet reconst
arXiv:2609.21872v1 Announce Type: new Abstract: We introduce Chronosphere, a spatio-temporal neural field that learns representations of climate. A central challenge in geographic representation learn
arXiv:2609.21570v1 Announce Type: cross Abstract: Renewable energy communities (RECs) coordinate buildings, photovoltaic generation, batteries, electric vehicles and flexible loads. Controller studies