Knowledge catalogue
New research from Google DeepMind. (bookmark it) SkillSmith treats model weights as an additional modality the LLM reads natively. The augmented model ingests existing prefix weights alongside rich te
To address the limits of deep learning and avoid stalling, the field of AI started by applying patch (1), which started being demoed 9 months later in December 2024 and has now become completely ubiqu
We're starting to leave the territory where you'd test an LLM by e.g. 'create an svg of pelican on a bicycle'. As one idea to generalize it, I was interested what Opus 5 would do if I gave it the firs
arXiv:2607.27634v1 Announce Type: new Abstract: Generating high-quality 360-degree dynamic human assets from text prompts is challenging. Existing methods usually synthesize monocular or multi-view vi
arXiv:2607.27501v1 Announce Type: new Abstract: We present a lightweight approach to foundation modeling (extbf{NEXUS}) that leverages pre-trained learning from collider physics data towards out-of-do
arXiv:2607.27565v1 Announce Type: new Abstract: Pattern-recognition control promises a myoelectric prosthesis that responds to many intended gestures rather than one or two, but the promise has stayed
arXiv:2607.26102v1 Announce Type: cross Abstract: Mathematical chain of thought (CoT) evaluation is commonly reduced to whether the final answer matches a reference. This conflates producing a correct
arXiv:2607.27735v1 Announce Type: new Abstract: Speculative decoding alleviates the memory-bandwidth bottleneck in large language model inference, but its acceleration is jointly constrained by drafti
arXiv:2508.03105v3 Announce Type: replace Abstract: We analyze the convergence behavior of stochastic gradient descent with momentum (SGDM) under dynamic learning-rate and batch-size schedules by intr
arXiv:2607.28320v1 Announce Type: new Abstract: Monocular UAV videos provide valuable observations for dynamic reconstruction of complex urban scenes. However, such scenes exhibit pronounced spatiotem
arXiv:2607.28617v1 Announce Type: cross Abstract: System prompts are instructions configured by developers to govern the behaviors of foundation models in AI applications. They are used throughout com
arXiv:2607.27301v1 Announce Type: cross Abstract: Isotonic regression is a canonical tool for estimating monotone functions and calibrating probabilistic predictors. We provide a fully sharp finite-sa
arXiv:2403.06494v2 Announce Type: replace-cross Abstract: This paper introduces a novel, lightweight method to solve the visibility problem for 2D grids. The proposed method evaluates the existence of
arXiv:2511.11970v2 Announce Type: replace Abstract: Robotic exploration in extreme environments, such as caves, oceans, and extraplanetary surfaces, poses significant challenges, specifically locomoti
arXiv:2607.27627v1 Announce Type: new Abstract: Unmanned aerial vehicle (UAV) relay networks can restore connectivity after communication infrastructure is damaged. Urban relay placement is difficult
arXiv:2607.27749v1 Announce Type: new Abstract: Building interactive digital twins requires recovering both 3D geometry and the kinematic structures that govern how objects articulate. Yet existing me
arXiv:2607.26472v1 Announce Type: cross Abstract: Audio deepfake detectors often degrade when generators, corpora, or recording conditions change. We use a Diffusion Transformer (DiT), trained only on
arXiv:2607.27611v1 Announce Type: new Abstract: Corporate annual reports contain weakly structured evidence about foreign-exchange risk management, derivative use, natural hedging, and explicit non-us
arXiv:2508.07044v2 Announce Type: replace-cross Abstract: Modern music retrieval runs on vector embeddings, and once these embeddings are shared for search or matching they can be copied, probed, or u
arXiv:2607.28439v1 Announce Type: new Abstract: Generative UI (GenUI) lets large language models synthesize a complete, renderable interface directly from a natural-language instruction, but evaluatin
arXiv:2607.28007v1 Announce Type: new Abstract: Pathology foundation models (FMs) are models trained on vast amounts of typically unlabeled data and have been shown to yield regularized latent spaces
arXiv:2607.28285v1 Announce Type: new Abstract: Monocular depth estimation (MDE) faces challenges with non-Lambertian surfaces and adverse weather conditions due to the visual ambiguities inherent in
arXiv:2607.27700v1 Announce Type: new Abstract: Large Vision-Language Models (VLMs) suffer from prohibitive inference overhead due to long sequences of visual tokens. However, existing visual token re
arXiv:2607.28212v1 Announce Type: new Abstract: Causal discovery in multivariate time series data is challenging due to complex interactions, high dimensionality, and nonlinear dependencies among vari
arXiv:2607.15404v2 Announce Type: replace-cross Abstract: Interleaving mitigates burst errors but introduces decoding delay and removes temporal error structure that a channel-aware decoder could expl
arXiv:2607.28130v1 Announce Type: new Abstract: We propose a novel collaborative approach for face super-resolution (SR) and robust person re-identification from sequential or multi-view facial images
arXiv:2607.27370v1 Announce Type: new Abstract: Sybil attackers are Blockchain actors that adopt the characteristics of regular users to exploit airdrops or influence governance. Current methods of Sy
arXiv:2512.18921v5 Announce Type: replace Abstract: The present paper introduces concurrency-driven enhancements to the training algorithm for the Kolmogorov-Arnold networks (KANs) that is based on th
arXiv:2607.26236v1 Announce Type: cross Abstract: AI-generated counterspeech offers a scalable and effective strategy to mitigate online toxicity by promoting more constructive dialogue. Yet, existing
arXiv:2603.12055v3 Announce Type: replace Abstract: Continual learning of pretrained vision-language models (VLMs) is prone to catastrophic forgetting, yet current approaches adapt to new tasks withou
arXiv:2607.27904v1 Announce Type: new Abstract: Concept-based explanations are a prevalent way to explain the decisions of complex black-box methods through semantically meaningful, human-interpretabl
arXiv:2607.28132v1 Announce Type: new Abstract: We propose a convolutional neural shading (CNS), a novel pipeline to reconstruct high-quality 3D shapes from multi-view images. Several recent studies h
arXiv:2607.28460v1 Announce Type: new Abstract: A major issue in Security Operations Centers (SOCs) is alert fatigue, as the number of detections reported is more than staff can triage in a given day.
arXiv:2504.04128v3 Announce Type: replace Abstract: In decision-level fusion tasks involving heterogeneous sources with unequal precision and potential anomalies, evidence deviating from the majority
arXiv:2607.28005v1 Announce Type: new Abstract: Declining insect populations make reliable biodiversity monitoring increasingly urgent, yet monitoring of insect biodiversity is hampered by a lack of s
arXiv:2607.10099v2 Announce Type: replace Abstract: Gust disturbances, dynamic vertical inflow and ground effect are key adverse aerodynamic phenomena that induce variations in the forces acting on a
arXiv:2511.14117v2 Announce Type: replace Abstract: Supervised classifiers output a distribution over classes but are typically trained against a single label obtained by collapsing multiple annotator
arXiv:2607.28567v1 Announce Type: cross Abstract: Longitudinal causal studies often record histories as irregular functional fragments: laboratory values, physiologic signals, sensor streams, and imag
arXiv:2607.27990v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs) communicate through sparse binary spike events rather than dense activations, enabling energy-efficient inference on ne
arXiv:2607.28020v1 Announce Type: new Abstract: Learned video compression relies on accurate temporal modeling to remove redundancy between adjacent frames. However, most existing codecs infer motion
arXiv:2607.28338v1 Announce Type: new Abstract: Clustered Federated Learning (CFL) addresses data heterogeneity in federated settings by grouping clients with similar data distributions to enable effe
arXiv:2607.27825v1 Announce Type: cross Abstract: Reconstructing dynamic surgical scenes is crucial for robot-assisted minimally invasive surgery; however, it continues to be difficult because of tiss
arXiv:2603.05950v2 Announce Type: replace Abstract: Visual token reduction is critical for accelerating Vision-Language Models (VLMs), since visual inputs are represented as token sequences that intro
arXiv:2607.27723v1 Announce Type: cross Abstract: Engression (Shen and Meinshausen, 2024) learns a conditional distribution by fitting a generative model Y = f(X,arepsilon) under the energy score, a s
arXiv:2607.27681v1 Announce Type: new Abstract: Transient-stability assessment determines whether a power system can recover after a disturbance and is therefore essential to preventing generator trip
arXiv:2607.27522v1 Announce Type: new Abstract: As decision-making processes grow more complex, machine learning tools have become essential for tackling business and societal challenges. However, man
arXiv:2607.28129v1 Announce Type: new Abstract: Face-and-voice association learning is one of the most challenging tasks in deep learning. In this paper, we propose a simple but powerful cross-modal f
arXiv:2607.27463v1 Announce Type: new Abstract: Dimensionality Reduction (DR) is a fundamental tool for high-dimensional data exploration, reducing the complexity of latent spaces of machine learning
arXiv:2607.27800v1 Announce Type: new Abstract: Existing invisible watermark removal methods often struggle to accurately capture the watermark-bearing features, leading to an unfavorable trade-off be
arXiv:2607.28127v1 Announce Type: new Abstract: Recent advances in Generative AI have substantially improved financial sentiment analysis through post-trained financial large language models (LLMs). H
arXiv:2607.27389v1 Announce Type: new Abstract: Learning-to-optimize (L2O) methods accelerate repeated optimization by training models to predict solutions, warm starts, branching decisions, or other
arXiv:2607.27975v1 Announce Type: new Abstract: We derive finite-sample generalization bounds for Transformers trained with dynamic programming recursions. Building on the doubly lifted, measure-value
arXiv:2607.28505v1 Announce Type: new Abstract: The rise of generative artificial intelligence (GenAI) in academic writing and publishing (AWP) raises questions about linguistic inclusivity and the le
arXiv:2607.28082v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities in structured query generation, making them a natural choice for Text-to-SPARQL, whic
arXiv:2607.28397v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) over knowledge graphs requires retrievers that can effectively capture both graph structure and semantic informat
arXiv:2603.02291v2 Announce Type: replace Abstract: We investigate an integrated sensing and communication (ISAC)-enabled BS for the unmanned aerial vehicle (UAV) obstacle avoidance task, and propose
arXiv:2602.14649v2 Announce Type: replace Abstract: Large Language Models (LLMs) exhibit strong reasoning abilities, but their high computational costs limit their practical deployment. Recent studies
arXiv:2607.27823v1 Announce Type: new Abstract: Large vision-language models (LVLMs) often hallucinate objects that are absent from an image. Despite recent progress, existing mitigation methods still
arXiv:2607.28394v1 Announce Type: new Abstract: Hand-object interaction (HOI) modeling remains challenging because it requires joint reasoning about hand articulation, object geometry, contact, semant
arXiv:2607.27532v1 Announce Type: cross Abstract: Heavy tails weaken high-confidence control for the empirical mean. Geometric median-of-means (MOM) also lacks a threshold that moves toward mean effic