Knowledge catalogue
arXiv:2610.05744v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) has been widely adopted in recent large language model (LLM) architectures. However, scaling up MoE in LLM training introduces
arXiv:2610.04020v1 Announce Type: new Abstract: Sparse Autoencoders (SAEs) began as an unsupervised tool for decomposing neural representations into sparse, interpretable features, and are increasingl
arXiv:2610.06829v1 Announce Type: cross Abstract: Open-source web agents are now strong enough to execute realistic browser tasks, but training them with reinforcement learning still depends on weak s
arXiv:2610.06679v1 Announce Type: new Abstract: Tabular foundation models perform in-context learning (ICL) by conditioning predictions on labeled training examples provided as context. Unlike traditi
arXiv:2610.06138v1 Announce Type: new Abstract: Graph Convolutional Networks (GCNs) have emerged as a powerful framework for learning from graph-structured data, yet their deployment on resource-const
arXiv:2610.05913v1 Announce Type: new Abstract: Task-fMRI connectomes reveal state-dependent neural reconfigurations, yet conventional methods marginalize these signals by aggregating distinct conditi
arXiv:2610.05936v1 Announce Type: cross Abstract: One of the major transformative factors in 6G will be the integration of Artificial Intelligence (AI) to become a native part of Radio Access Network
arXiv:2511.19453v2 Announce Type: replace-cross Abstract: Autonomous vehicles continuously generate large volumes of heterogeneous sensor and state data streams. While this data supports real-time aut
arXiv:2610.04605v1 Announce Type: new Abstract: Many visual explanation methods in computer vision highlight pixel importance but struggle to link these low-level cues to semantically meaningful conce
arXiv:2610.04239v1 Announce Type: cross Abstract: Uncertainty quantification (UQ) for large language models (LLMs) aims to provide reliable measures of predictive confidence, yet current methods are o
arXiv:2610.04143v1 Announce Type: new Abstract: Most feature-based choice models, classical and deep, score items and apply a single softmax. We introduce consideration circuits (CC), feature-based mo
arXiv:2610.04427v1 Announce Type: new Abstract: Neural operators offer an efficient alternative to classical PDE solvers, but most learn a monolithic map per equation family and discretization. Real s
arXiv:2610.06663v1 Announce Type: new Abstract: A significant problem in endoscopic image analysis is that the machine learning (ML) models used for this purpose usually underperform when applied on i
arXiv:2610.04553v1 Announce Type: cross Abstract: The long observational record of He I 10830 {AA} offers a means to investigate solar morphology before modern extreme-ultraviolet (EUV) imaging. We ad
arXiv:2610.05559v1 Announce Type: new Abstract: Industrial sequential recommender systems operate over massive item catalogs (e.g., 10^5--10^7 items). Multi-label recommendation models are trained wit
arXiv:2610.04286v1 Announce Type: cross Abstract: Distributed Energy Resource (DER) environments rely on network communication protocols to coordinate control commands, measurements, and device states
arXiv:2610.04938v1 Announce Type: new Abstract: We propose D-DOIT (Discrete Doob-Oriented Inference-time Transformation), a training-free and efficient adaptation method for discrete diffusion models
arXiv:2610.05678v1 Announce Type: new Abstract: Most humanoid loco-manipulation controllers require human motion data to learn whole-body coordination and posture, leaving policies reliant on external
arXiv:2610.06726v1 Announce Type: new Abstract: Electroencephalography (EEG) offers millisecond temporal resolution, but inferring underlying neural sources is a severely ill-posed spatial inverse pro
arXiv:2504.06470v2 Announce Type: replace-cross Abstract: Ensuring fairness is essential as machine learning increasingly informs consequential decisions. However, many fairness-aware methods focus on
arXiv:2610.03739v1 Announce Type: cross Abstract: The SWOT (Surface Water Ocean Topography) mission is currently providing unpreceded high-resolution measurements of Sea Surface Height (SSH), revealin
arXiv:2610.06823v1 Announce Type: new Abstract: Large longitudinal cohorts often contain wrist accelerometry without optical heart-rate sensing, motivating recovery of cardiac information from motion
arXiv:2506.04619v2 Announce Type: replace Abstract: Image matching, which establishes correspondences between two images to recover 3D structure and camera geometry, is a cornerstone of computer visio
arXiv:2610.04596v1 Announce Type: new Abstract: On-policy distillation (OPD) has emerged as a widely used paradigm for post-training large language models, reducing the train--test mismatch of convent
arXiv:2610.05071v1 Announce Type: new Abstract: Learning population dynamics from unpaired temporal marginals is an ill-posed inverse problem that requires structural assumptions on the underlying dyn
arXiv:2610.03765v1 Announce Type: new Abstract: Discrete motion tokenizers encode motion as atomic units and are widely used for co-speech gesture generation. It remains unclear which motion propertie
arXiv:2610.04278v1 Announce Type: new Abstract: Deep remaining-useful-life (RUL) models on NASA C-MAPSS are now routine, and so are heatmaps that colour sensors and timesteps. A heatmap that looks mec
arXiv:2610.04540v1 Announce Type: new Abstract: We introduce DreamFormer, a model-based agent that acquires language-conditioned, multi-task skills by imitating expert demonstrations within the latent
arXiv:2610.04494v1 Announce Type: cross Abstract: Testing deep reinforcement learning (DRL) agents in cyber-physical systems aims to uncover diverse failures before deployment, but each execution can
arXiv:2610.05839v1 Announce Type: cross Abstract: Robotic ultrasound couples a high-rate contact-force loop with slower, delayed image feedback, so image-guided ultrasound probe rotation can perturb c
arXiv:2610.04138v1 Announce Type: new Abstract: Account takeover (ATO) fraud is a growing threat to digital banking, requiring effective detection while minimizing friction for legitimate customers. P
arXiv:2610.04044v1 Announce Type: new Abstract: The quadratic attention cost of Vision Transformers (ViTs) forces a trade-off between spatial resolution and rollout horizon, particularly for fine-scal
arXiv:2610.03942v1 Announce Type: new Abstract: When using diffusion models to target image restoration problems, diffusion inversion is typically employed to retain relevant image information from th
arXiv:2610.05796v1 Announce Type: new Abstract: Optimisation-based parking planners usually impose collision constraints only at the time samples, so a vehicle corner can cut an obstacle between sampl
arXiv:2610.05048v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) provides dense token-level supervision without a second model: one network acts as teacher with the reference solutio
arXiv:2508.14086v4 Announce Type: replace Abstract: Electroencephalography (EEG) is a critical tool for monitoring brain activity and diagnosing neurological disorders such as epilepsy. However, learn
arXiv:2610.06147v1 Announce Type: new Abstract: Vision-language models (VLMs) achieve strong zero-shot transferability but remain vulnerable to target-domain shifts at inference time. Test-time adapta
arXiv:2511.19935v3 Announce Type: replace Abstract: Deploying domain-specialized large language models on resource-constrained hardware motivates reducing both adaptation cost and the number of retain
arXiv:2607.09701v2 Announce Type: replace Abstract: The enduring vision of general-purpose robots serving humanity hinges fundamentally on policy steerability. However, prevailing paradigms of learnin
arXiv:2610.05607v1 Announce Type: new Abstract: Emergency obstacle avoidance requires a mobile robot to brake or change its heading within the available distance. This paper investigates the dependenc
arXiv:2510.23087v2 Announce Type: replace Abstract: In robot-assisted minimally invasive surgery, accurate 3D reconstruction from endoscopic video is vital for downstream tasks and improved outcomes.
arXiv:2610.03772v1 Announce Type: new Abstract: The rapid growth of deep learning has substantially increased the energy consumption associated with model training, making energy efficiency an increas
arXiv:2610.04864v1 Announce Type: new Abstract: Long-video embedding requires capturing sparse query-relevant evidence under a limited visual-token budget. Uniform sampling can miss brief events in vi
arXiv:2312.00113v4 Announce Type: replace Abstract: We present ContinuityCam, a novel approach to generate a continuous video from a single static RGB image and an event camera stream. Conventional ca
arXiv:2610.05418v1 Announce Type: cross Abstract: Most vision-language-action (VLA) models rely on current observations and lose task-relevant evidence once it leaves view, limiting performance on lon
arXiv:2610.06090v1 Announce Type: new Abstract: Continuous asynchronous replanning is essential for real-time generative robot policies, but independent stochastic initialization can cause mode switch
arXiv:2610.04805v1 Announce Type: cross Abstract: Three-dimensional perception is critical for robotic manipulation, particularly for high-precision tasks, as recovering metric depth and precise 3D ob
arXiv:2610.05353v1 Announce Type: cross Abstract: Fluorescence microscopy reveals where proteins localize, but only a limited number of proteins can be imaged in the same cell; generating these images
arXiv:2610.03980v1 Announce Type: new Abstract: Text-to-video (T2V) diffusion models can reproduce copyrighted, violent, or explicit content, which motivates concept erasure: removing designated conce
arXiv:2610.05897v1 Announce Type: new Abstract: Training a small projector between a frozen vision encoder and language model is an established approach to multimodal learning. As the parameter count
arXiv:2610.04767v1 Announce Type: cross Abstract: Latent world models enable robots to plan by predicting the consequences of actions. Planning long tasks with control-rate actions requires many predi
arXiv:2610.05639v1 Announce Type: new Abstract: Autonomous robots operating over long periods must keep their environmental memory up to date as the world changes between visits. In semi-static enviro
arXiv:2603.08433v2 Announce Type: replace Abstract: The Foret Montmorency (FoMo) dataset is a comprehensive multi-season data collection, recorded over the span of one year in a boreal forest. Featuri
arXiv:2610.03755v1 Announce Type: new Abstract: The magnitude of the generalized Euclidean cross product is a Gram volume whose degree under common scaling is fixed by the integer dimension of the spa
arXiv:2610.04372v1 Announce Type: cross Abstract: Transferring visual representations pretrained on human videos to robot manipulation requires learning reliable correspondences between human and robo
arXiv:2610.05734v1 Announce Type: new Abstract: Online control of execution speed is essential for deploying robot policies in real-world scenarios, as robots may need to speed up under time constrain
arXiv:2610.06287v1 Announce Type: cross Abstract: Industrial content moderation must process massive message streams under tight latency constraints, yet most abusive language (AL) detection systems r
arXiv:2503.17589v3 Announce Type: replace Abstract: Kinematic motion planners are among the most widely used control approaches in robotic applications. By modeling the robot as a first-order system,
arXiv:2610.05964v1 Announce Type: new Abstract: Natural face-to-face human--robot interaction requires a robot to understand an evolving social situation, decide when to engage, and express its intent
arXiv:2610.04585v1 Announce Type: new Abstract: Joint-embedding predictive architectures (JEPAs) for world modeling train an encoder so a predictor maps a current embedding and action to the next fram