Knowledge catalogue
arXiv:2606.08282v1 Announce Type: new Abstract: We consider a problem arising in proof-of-stake blockchain environments, where agents called nominators select validators - entities responsible for mai
arXiv:2602.02431v2 Announce Type: replace-cross Abstract: It is folklore that reusing training data more than once can improve the statistical efficiency of gradient-based learning. While this phenome
arXiv:2603.27493v2 Announce Type: replace Abstract: Spiking Neural Networks (SNNs), characterized by their event-driven computation and low power consumption, have shown great potential for energy-eff
arXiv:2606.07560v1 Announce Type: cross Abstract: Function-vector (FV) heads (Todd et al., 2024) are typically identified by the magnitude of their causal contribution to in-context rule tasks, under
arXiv:2606.08866v1 Announce Type: new Abstract: CNN-based semantic segmentation networks usually rely on context heads such as ASPP, PPM, or attention modules to enlarge the receptive field. These hea
arXiv:2509.21925v2 Announce Type: replace-cross Abstract: This paper investigates the theoretical behavior of generative models under finite training populations. Within the stochastic interpolation g
arXiv:2606.08360v1 Announce Type: cross Abstract: Peer-referral recruitment systems such as respondent-driven sampling are critical for studying and intervening on hidden populations affected by infec
arXiv:2606.08303v1 Announce Type: new Abstract: This paper investigates a novel concept of time series geolocalization, where the goal is to infer the geographic origin of each raw time series. Succes
arXiv:2509.11485v3 Announce Type: replace-cross Abstract: Labyrinthine stripe patterns are common in many physical systems, yet their lack of long-range order makes quantitative characterization chall
arXiv:2602.16015v2 Announce Type: replace Abstract: Conformal prediction gives finite-sample coverage guarantees for regression, but most standard constructions are designed for Euclidean output space
arXiv:2606.08404v1 Announce Type: new Abstract: Cortical folding reflects coordinated neurodevelopmental processes and is increasingly recognized as a sensitive marker of neurological disease. However
arXiv:2606.07725v1 Announce Type: cross Abstract: Displacement time series from Global Navigation Satellite Systems (GNSS) are essential for a wide range of applications, including monitoring tectonic
arXiv:2606.09476v1 Announce Type: new Abstract: Hindsight relabeling usually turns achieved future states into exact goals, which can overconstrain offline robot learning when task success depends onl
arXiv:2603.10395v2 Announce Type: replace Abstract: Graph generation is a fundamental task with broad applications, such as drug discovery. Recently, discrete flow matching-based graph generation, aka
arXiv:2606.09432v1 Announce Type: new Abstract: Modeling interacting dynamical systems requires capturing spatial interactions alongside long-range temporal dependencies. Graph neural networks (GNNs)
arXiv:2606.08440v1 Announce Type: cross Abstract: Robotic grasping is a fundamental capability in robotic manipulation. Yet grasping remains challenging under partial observations. Reliable grasping d
arXiv:2606.08133v1 Announce Type: new Abstract: Ground contact forces acting on the human body, are crucial for biomechanics studies or sport performance analysis. Prior methods rely on force plates o
arXiv:2606.08302v1 Announce Type: new Abstract: Visual Autoregressive (VAR) models adopt a next-scale prediction paradigm, offering high-quality generation with substantially fewer decoding steps. How
arXiv:2505.07833v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) improves the reliability of large language models by integrating external knowledge, but serving RAG pipe
arXiv:2606.08403v1 Announce Type: cross Abstract: Text-centered prompt-injection defenses assume that the malicious signal is visible in one of the inspected text views. We study a reproducible LLM01-
arXiv:2601.06599v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) often encode whether a statement is true as a vector in their residual stream activations. These vectors, also kn
arXiv:2606.08218v1 Announce Type: cross Abstract: Compositional priors describe the generic properties of layered functions in deep Bayesian models, where deep neural networks with random weights are
arXiv:2606.08777v1 Announce Type: cross Abstract: Visual Language Models (VLMs) are known to produce hallucinated predictions that are not grounded in visual evidence, yet existing approaches lack a p
arXiv:2606.08164v1 Announce Type: new Abstract: MRI preprocessing defines the input distribution seen by brain MRI foundation models, yet it is usually treated as routine data cleaning rather than a m
arXiv:2603.13259v2 Announce Type: replace-cross Abstract: When a decoder-only transformer is forced to process matched correct and incorrect single-token continuations of a factual query, the two path
arXiv:2504.02983v3 Announce Type: replace-cross Abstract: Metaphor and humor share a lot of common ground, and metaphor is one of the most common humorous mechanisms. This study focuses on the humorou
arXiv:2504.05349v4 Announce Type: replace-cross Abstract: Network pruning is used to reduce inference latency and power consumption in large neural networks. However, most methods focus on empirical r
arXiv:2606.08076v1 Announce Type: cross Abstract: Large Language Models (LLMs) can generate high-quality arguments, yet their ability to engage in nuanced and persuasive communicative actions remains
arXiv:2606.09589v1 Announce Type: cross Abstract: AI minidramas (also known as fruit dramas) are short, algorithmically distributed generative AI video series featuring anthropomorphized characters th
arXiv:2606.09347v1 Announce Type: new Abstract: Synthetic aperture radar (SAR)-assisted optical cloud removal aims to recover surface information obscured by clouds in optical remote sensing images by
arXiv:2606.07914v1 Announce Type: cross Abstract: We study component recovery and mixing-matrix estimation from unlabeled finite mixtures whose observable distributions share the same latent component
arXiv:2606.09111v1 Announce Type: new Abstract: Unmanned Aerial Vehicle (UAV) multispectral point clouds (MPC) provide high-dimensional spatial-spectral data for sub-canopy target detection; however,
arXiv:2606.08144v1 Announce Type: new Abstract: Composed Video Retrieval (CVR) is designed to retrieve a target video that matches a reference video modified by a modification text. While existing met
arXiv:2606.07525v1 Announce Type: cross Abstract: Causal graphs in text are typically populated by observable, predefined events. In contrast, we study implicit causal graph construction from text by
arXiv:2602.03682v2 Announce Type: replace-cross Abstract: We analyze the Accelerated Noisy Power Method, an algorithm for Principal Component Analysis in the setting where only inexact matrix-vector p
arXiv:2606.09154v1 Announce Type: new Abstract: Decentralized SGD is a fundamental algorithm in decentralized learning, although the influence of an underlying network topology on its convergence beha
arXiv:2606.07801v1 Announce Type: new Abstract: Multimodal reasoning requires a path that retains integrity over a wide range of constraints, from visual grounding to logic consistency. However, the c
arXiv:2601.05261v2 Announce Type: replace-cross Abstract: Online consumer reviews are important decision-support resources in e-commerce, yet the increasing volume of reviews often creates information
arXiv:2606.09664v1 Announce Type: new Abstract: Bayesian optimization (BO) is a central tool for sample-efficient design, and latent-space Bayesian optimization (LSBO) extends it to structured objects
arXiv:2606.08831v1 Announce Type: new Abstract: Large language models (LLMs) increasingly perform multi-step reasoning, where intermediate claims form implicit directed acyclic graphs whose node corre
arXiv:2606.08479v1 Announce Type: new Abstract: Inferring the forces that drive a dynamical system from partial observations is a fundamental challenge across physics, particularly when distinct under
arXiv:2606.07588v1 Announce Type: cross Abstract: We consider the black-box optimization problem on a sphere. Two information-geometric optimization flows (IGO flows) are designed with rigorous calcul
arXiv:2606.09052v1 Announce Type: cross Abstract: Self-evolution offers a scalable path to stronger reasoning: a pretrained language model improves itself with only minimal external supervision. Yet e
arXiv:2602.18695v2 Announce Type: replace Abstract: Existing insertion-based masked diffusion models that generate sequences by interleaving token insertion with unmasking use fixed schedules that are
arXiv:2606.07865v1 Announce Type: cross Abstract: Scientific machine learning is limited less by model size than by the data it is trained on. Observational data records what happened but not why; tem
arXiv:2603.08630v2 Announce Type: replace Abstract: We derive integral formulas that simplify the Vector Signal Tensor Product recently introduced by Xie et al., which generalizes the Gaunt tensor pro
arXiv:2606.09558v1 Announce Type: cross Abstract: Motivation: Transformer-based models are increasingly applied to large-scale single-cell transcriptomics, showing strong performance through self-supe
arXiv:2606.08858v1 Announce Type: cross Abstract: The automatic processing of handwritten forms remains a challenging task, wherein detection and subsequent classification of handwritten characters ar
arXiv:2606.09289v1 Announce Type: new Abstract: Understanding tactical organisation of association football, hereafter referred to as football, requires identifying distinct match phases. Yet in-posse
arXiv:2606.08850v1 Announce Type: cross Abstract: Inference-Time Scaling (ITS) has largely succeeded in verifiable domains like math and coding, where cheap verification enables scalable output select
arXiv:2402.13425v3 Announce Type: replace-cross Abstract: It is becoming increasingly common in regression to train neural networks that model the entire distribution even if only the mean is required
arXiv:2603.16020v2 Announce Type: replace Abstract: Adaptive agents operating under uncertainty must do more than optimize task outputs: they must maintain a workable internal state under noise, pertu
arXiv:2606.07819v1 Announce Type: new Abstract: Recently, the efficiency of Large Language Models (LLMs) deployment has become a critical concern in practical applications. While post-training quantiz
arXiv:2606.08816v1 Announce Type: cross Abstract: Predicting the effect of an unseen gene knockout perturbation on transcriptomic gene expression remains a highly challenging problem for virtual cell
arXiv:2510.09783v2 Announce Type: replace-cross Abstract: Oversampling is one of the most widely used approaches for addressing imbalanced classification. The core idea is to generate additional minor
arXiv:2506.20573v4 Announce Type: replace-cross Abstract: Public datasets, crucial for modern machine learning and statistical inference, often contain low-quality or contaminated samples that can har
arXiv:2606.09131v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) commonly inherit the deep, symmetric Transformer backbone designed for unimodal text modeling, and apply the sa
arXiv:2606.09828v1 Announce Type: new Abstract: Video world models that maintain 3D spatial consistency across generated frames typically rely on explicit point cloud memory constructed in RGB space.
arXiv:2606.08001v1 Announce Type: new Abstract: Semantic image segmentation assigns a predefined category label to each pixel, has achieved significant progress lately. Open-Vocabulary Segmentation (O
arXiv:2606.09744v1 Announce Type: new Abstract: We study feed-forward ReLU networks with fixed readout and quadratic loss. The aim is to rewrite gradient descent not primarily as a dynamics in weight