Knowledge catalogue
arXiv:2501.00745v3 Announce Type: replace-cross Abstract: The increasing integration of Large Language Model (LLM) based search engines has transformed the landscape of information retrieval. However,
arXiv:2606.10698v1 Announce Type: cross Abstract: In this paper, we use machine learning to discover a new seeding strategy for integration-by-parts reduction of Feynman integrals, which is a frequent
arXiv:2606.11149v1 Announce Type: new Abstract: We study the problem of learning a drifting concept in the presence of Massart noise. In this framework, an online learner has access to a history of in
arXiv:2606.10596v1 Announce Type: cross Abstract: This work proves that an n-dimensional hybrid system can be embedded into an m-dimensional Euclidean space equipped with a continuous vector field on
arXiv:2606.10113v1 Announce Type: cross Abstract: This paper investigates whether LLM translations exhibit identifiable emotional profiles and how post-editing reshapes them toward human-like norms. W
arXiv:2603.02673v2 Announce Type: replace-cross Abstract: Functional ANOVA offers a principled framework for interpretability by decomposing a model's prediction into main effects and higher-order int
arXiv:2606.10380v1 Announce Type: cross Abstract: Real-world crisis intervention is inherently conversational, yet existing research largely focuses on static texts.Real-world crisis intervention is i
arXiv:2606.11075v1 Announce Type: new Abstract: Aligning text-to-image flow matching models with human preferences via direct reward backpropagation is sample-efficient but hampered by two well-known
arXiv:2606.10944v1 Announce Type: new Abstract: We introduce a new tool, Express, for converting a non-causal attention approximation into a causal approximation with matching approximation guarantees
arXiv:2606.10671v1 Announce Type: new Abstract: Autoregressive video generators synthesize long videos by generating successive temporal segments, but their historical KV cache grows with video length
arXiv:2606.10124v1 Announce Type: cross Abstract: Federated learning (FL) is often subject to aggregation variance if clients do not consistently participate in training rounds. While reusing stale mo
arXiv:2606.10450v1 Announce Type: new Abstract: DiffC provides a principled way to reuse pre-trained diffusion models for lossy compression, but its encoding and decoding procedures remain slow becaus
arXiv:2509.16518v2 Announce Type: replace Abstract: Using diffusion transformers for media generation may require evaluating attention over extremely long sequences, with attention layers accounting f
arXiv:2606.11138v1 Announce Type: new Abstract: We introduce First-Order Trajectory Matching (FTM), a surrogate-modeling method that learns the first-order local transport of probability mass from tra
arXiv:2606.10543v1 Announce Type: cross Abstract: Designing functional biological sequences requires navigating vast discrete spaces under strict evolutionary and biophysical constraints. Discrete Flo
arXiv:2606.10167v1 Announce Type: new Abstract: Recent learning-based path planners use neural networks to process visual map representations and approximate heuristics for classical search algorithms
arXiv:2606.10406v1 Announce Type: cross Abstract: We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch
arXiv:2606.10298v1 Announce Type: new Abstract: When large language models generate from retrieved or augmented contexts, conflicts between external context and parametric priors remain a central reli
arXiv:2606.10595v1 Announce Type: cross Abstract: Federated Learning (FL) has emerged as a promising solution for data hunger in centralized learning. This paradigm enables privacy with multiple clien
arXiv:2606.09543v2 Announce Type: replace Abstract: This short paper introduces a stylometric interpretation method inspired by genome-wide association studies (GWAS). Each 'gene' token's association
arXiv:2606.10378v1 Announce Type: new Abstract: Accurate segmentation of carotid arteries in ultrasound imaging is critical for stroke risk assessment. However, speckle noise, low contrast, and blurre
arXiv:2606.10166v1 Announce Type: new Abstract: Current cross-view localization methods predominantly rely on satellite imagery as the aerial modality. Although recent work explores planimetric maps (
arXiv:2606.09944v1 Announce Type: cross Abstract: GDP per capita is the default lens through which governibng bodies track the economic prosperity and consequences of economic events , yet it is blind
arXiv:2606.10612v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) is a powerful technique for creating high-fidelity 3D assets. However, the widespread sharing and iterative modification of
arXiv:2606.11044v1 Announce Type: cross Abstract: Conformal predictive systems (CPS) output calibrated bands of CDFs under exchangeability. We extend generalized CPS to non-exchangeable settings by en
arXiv:2606.11037v1 Announce Type: new Abstract: Generative design of robots requires navigating a vast search-space, encompassing physical configurations and behavioural parameters. Evolutionary Algor
arXiv:2606.10942v1 Announce Type: cross Abstract: As artificial intelligence and machine learning (AI/ML) models become integral to network operations, their lack of transparency poses a significant b
arXiv:2504.17080v3 Announce Type: replace Abstract: In this paper, we present an impedance control framework on the SE(3) manifold, which enables force tracking while guaranteeing passivity. Building
arXiv:2606.10835v1 Announce Type: cross Abstract: Periodic hard target updates are among the most common stabilization devices in modern deep Q-learning. Recent studies suggest that target updates can
arXiv:2606.09963v1 Announce Type: cross Abstract: Aerodynamic simulation is a key component of engineering shape design, where core quantities such as the surface pressure coefficient strongly depend
arXiv:2603.20850v2 Announce Type: replace Abstract: Understanding hand-object interaction (HOI) is fundamental to computer vision, robotics, and AR/VR. However, conventional hand videos often lack ess
arXiv:2606.10841v1 Announce Type: new Abstract: Inverse Optimal Control (IOC) aims to recover the cost function that explains observed trajectories as solutions of an optimal control problem. Classica
arXiv:2606.11066v1 Announce Type: new Abstract: Neural population activity models can recover rich temporal structure from binned spikes, but their read-in and readout layers often remain tied to a fi
arXiv:2606.10541v1 Announce Type: new Abstract: Terrestrial Laser Scanning (TLS) point clouds captured in urban environments frequently suffer from glass-induced reflection artifacts, severely degradi
arXiv:2602.22352v2 Announce Type: replace-cross Abstract: With the continuous growth of neural network scales, low-precision quantization is widely used in edge accelerators. Classic multi-threshold a
arXiv:2606.09951v1 Announce Type: new Abstract: During the training of large Transformer models, attention masks regulate the scope and direction of information flow across a sequence. Numerous mask v
arXiv:2606.09896v1 Announce Type: cross Abstract: In modern online advertising platforms, Guaranteed Delivery (GD) contracts coexist and bid with Real-Time Bidding (RTB) auctions. Recent approaches ei
arXiv:2606.10646v1 Announce Type: cross Abstract: Token-level credit assignment remains a key obstacle for reinforcement learning (RL) in large language models (LLMs), where RL recipes typically treat
arXiv:2606.10906v1 Announce Type: cross Abstract: We study models for human-AI teaming through the lens of statistical calibration. We assume the team consists of an AI model and human -- both of whic
arXiv:2606.10238v1 Announce Type: cross Abstract: Neural population geometry shapes downstream computation. Recent empirical findings in neurobiology suggest that a hyperbolic structure underlies popu
arXiv:2606.10068v1 Announce Type: cross Abstract: Hyperparameter Optimization (HPO) is essential for building high-performing ML/DL models, yet conventional optimizers often struggle in high-dimension
arXiv:2602.19393v2 Announce Type: replace Abstract: Steck, Ekanadham, and Kallus [arXiv:2403.05440] demonstrate that cosine similarity of learned embeddings from matrix factorization models can be ren
arXiv:2606.10046v1 Announce Type: cross Abstract: Flow-matching transformers achieve strong audio separation, yet their attention dynamics are opaque. We adapt established causal-intervention principl
arXiv:2606.10197v1 Announce Type: cross Abstract: Integral field unit (IFU) spectroscopy provides spatially resolved spectra across galaxies, offering crucial insights into their evolution. However, i
arXiv:2503.19158v3 Announce Type: replace Abstract: Type 1 Diabetes (T1D) management is a complex task due to many variability factors. Artificial Pancreas (AP) systems have alleviated patient burden
arXiv:2606.09950v1 Announce Type: new Abstract: Averaging a neural network over its random parameters and marginalizing a Gaussian sector are the same operation, the Schur complement of the eliminated
arXiv:2606.09940v1 Announce Type: cross Abstract: Dictionary learning methods like Sparse Autoencoders (SAEs) and crosscoders attempt to explain a model by decomposing its activations into independent
arXiv:2606.10029v1 Announce Type: cross Abstract: Language models increasingly serve as the backbone of text-to-speech (TTS) systems, yet we understand little about the representations they build when
arXiv:2601.21543v3 Announce Type: replace Abstract: Mixup generates augmented samples by linearly interpolating inputs and labels with a controllable ratio. However, since it operates at the latent em
arXiv:2601.22763v3 Announce Type: replace Abstract: Current state-of-the-art multi-class unsupervised anomaly detection (MUAD) methods rely on training encoder--decoder models to reconstruct anomaly-f
arXiv:2606.11151v1 Announce Type: new Abstract: Assistive mobility and manipulation platforms have received increasing attention as a means of restoring independence to individuals with disabilities.
arXiv:2606.10295v1 Announce Type: cross Abstract: The Gromov--Wasserstein (GW) distance provides a framework for comparing metric measure spaces, regardless of their underlying structure or geometry.
arXiv:2606.10358v1 Announce Type: cross Abstract: Learning Bayesian network (BN) structure from sparse discrete data is hard: when each instance records only a few variables, most variable pairs lack
arXiv:2606.10531v1 Announce Type: cross Abstract: Quantization-aware training (QAT) is essential for extremely low-bit large language models (LLMs). Current QAT methods are mainly based on scalar quan
arXiv:2606.09949v1 Announce Type: cross Abstract: Data-driven PDE surrogates are trained with data produced by numerical PDE solvers. However, when the surrogate's goal is to generalize across a wide
arXiv:2606.10579v1 Announce Type: new Abstract: Designing dynamically feasible trajectories for rigid bodies is a fundamental problem in robotics. While direct methods are widely used, the existing co
arXiv:2606.11104v1 Announce Type: new Abstract: We investigate limitations of learning anh neural networks from point evaluations under finite-precision computations and L^p accuracy guarantees, build
arXiv:2606.10294v1 Announce Type: cross Abstract: Deploying neural networks on unconventional hardware demands architectures that co-optimize task accuracy and platform-specific constraints such as en
arXiv:2606.09907v1 Announce Type: cross Abstract: Multimodal clinical learning is increasingly important for integrating diverse patient data, including imaging, text, and personalised health records.
arXiv:2511.10234v3 Announce Type: replace-cross Abstract: While promising, graph reasoners based on Large Language Models (LLMs) lack built-in invariance to symmetries in graph representations. Operat