Search: “research”

P1-KAN: an effective Kolmogorov-Arnold network with application to hydraulic valley optimization

arXiv:2410.03801v5 Announce Type: replace Abstract: A new Kolmogorov-Arnold network (KAN) is proposed to approximate potentially irregular functions in high dimensions. We provide error bounds for thi

Research

P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats

DGX agent

arXiv:2511.06838v4 Announce Type: replace-cross Abstract: The substantial memory bandwidth and computational demands of large language models (LLMs) present critical challenges for efficient inference

researcharxiv-cs-lg

5 May 2026

Page image classification for content-specific data processing

arXiv:2507.21114v3 Announce Type: replace-cross Abstract: Digitization projects in humanities often generate vast quantities of page images from historical documents, presenting significant challenges

ParaRNN: An Interpretable and Parallelizable Recurrent Neural Network for Time-Dependent Data

arXiv:2605.02692v1 Announce Type: cross Abstract: The proliferation of large-scale and structurally complex data has spurred the integration of machine learning methods into statistical modeling. Recu

Perturb and Correct: Post-Hoc Ensembles using Affine Redundancy

arXiv:2605.01632v1 Announce Type: new Abstract: Models that are indistinguishable on in-distribution data can behave very differently under distribution shift. We introduce Perturb-and-Correct (P&C),

Phase-map synthesis from magnitude-only MR images using conditional score-based diffusion models with application in training of accelerated MRI reconstruction models

arXiv:2605.01185v1 Announce Type: new Abstract: Accelerated magnetic resonance imaging (MRI) enabled by the training of deep learning (DL)-based image recon. models requires large and diverse raw k-sp

phi-Table: A Statistical Explanation for Global SHAP

arXiv:2512.07578v3 Announce Type: replace-cross Abstract: Global SHAP explanations are typically presented as feature-importance rankings, which identify variables that matter to a black-box model but

Physiology-Aware Masked Cross-Modal Reconstruction for Biosignal Representation Learning

arXiv:2605.00973v1 Announce Type: new Abstract: Biosignals acquired from different locations on the body often provide temporally ordered views of the same underlying physiological process. However, m

Pi-Change: A Prior-Informed Multiple Change Point Detection Algorithm

arXiv:2605.01003v1 Announce Type: cross Abstract: Statistical change point (CP) detection methods typically rely on likelihood-based inference and ignore contextual information about plausible CP loca

Pixel Perfect: Relational Image Quality Assessment with Spatially-Aware Distortions

arXiv:2605.02863v1 Announce Type: new Abstract: Traditional image quality assessment (IQA) methods rely on mean opinion scores (MOS), which are resource-intensive to collect and fail to provide interp

Polynomial-Time Optimal Group Selection via the Double-Commutator Eigenvalue Problem

arXiv:2605.00834v1 Announce Type: new Abstract: The algebraic diversity framework replaces temporal averaging over multiple observations with algebraic group action on a single observation for second-

Poodle: Seamlessly Scaling Down Large Language Models with Just-in-Time Model Replacement

arXiv:2512.05525v2 Announce Type: replace-cross Abstract: Businesses increasingly rely on large language models (LLMs) to automate simple repetitive tasks instead of developing custom machine learning

Pretraining on Sleep Data Improves non-Sleep Biosignal Tasks

arXiv:2605.02500v1 Announce Type: new Abstract: Sleep foundation models have recently demonstrated strong performance on in-domain polysomnography tasks, including sleep staging, apnea detection, and

Principles and Guidelines for Randomized Controlled Trials in AI Evaluation

arXiv:2605.02050v1 Announce Type: cross Abstract: This work establishes a foundational framework for standardizing AI evaluation RCTs (sometimes called human uplift studies). Drawing on established ex

Probabilistic Modeling of Multi-rater Medical Image Segmentation for Diversity and Personalization

arXiv:2512.00748v2 Announce Type: replace Abstract: Lesion segmentation is inherently influenced by imaging uncertainty, arising from ill-defined lesion boundaries and inter-observer variability in di

Progress Ratio Embeddings: An Impatience Signal for Robust Length Control in Neural Text Generation

arXiv:2512.06938v2 Announce Type: replace Abstract: Modern neural language models achieve high accuracy in text generation, yet precise control over generation length remains underdeveloped. In this p

Provable Benefit of Curriculum in Transformer Tree-Reasoning Post-Training

arXiv:2511.07372v3 Announce Type: replace Abstract: Recent curriculum techniques in the post-training stage of LLMs have been empirically observed to outperform non-curriculum approaches in improving

Pruning Federated Models through Loss Landscape Analysis and Client Agreement Scoring

arXiv:2405.10271v4 Announce Type: replace Abstract: The practical deployment of Federated Learning (FL) on resource-constrained devices is fundamentally limited by the high cost of training large mode

PubMed-Ophtha: An open resource for training ophthalmology vision-language models on scientific literature

arXiv:2605.02720v1 Announce Type: cross Abstract: Vision-language models hold considerable promise for ophthalmology, but their development depends on large-scale, high-quality image-text datasets tha

Q-RAG: Long Context Multi-step Retrieval via Value-based Embedder Training

arXiv:2511.07328v2 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) methods enhance LLM performance by efficiently filtering relevant context for LLMs, reducing hallucinations and

Quantifying and Predicting Disagreement in Graded Human Ratings

arXiv:2605.01168v1 Announce Type: new Abstract: It is increasingly recognized that human annotators do not always agree, and such disagreement is inherent in many annotation tasks. However, not all in

Quantum-inspired Techniques in Tensor Networks for Industrial Contexts

arXiv:2404.11277v2 Announce Type: replace-cross Abstract: In this paper we present a study of the applicability and feasibility of quantum-inspired algorithms and techniques in tensor networks for ind

Quasi-Static Control of Discrete Cosserat Rod

arXiv:2605.01395v1 Announce Type: cross Abstract: In this paper, we design feedback control laws for soft robots modelled using the Cosserat rod, which is spatially discretised using the Piecewise Con

researcharxiv-cs-ro

Random-Effects Algorithm for Random Objects in Metric Spaces

arXiv:2605.02693v1 Announce Type: cross Abstract: Across many scientific disciplines, multiple observations are collected from the same experimental units, and in modern datasets these observations of

Recall to Predict: Grounding Motion Forecasting in Interpretable Motion Bank

arXiv:2605.01393v1 Announce Type: new Abstract: Motion forecasting often requires trading interpretability for predictive accuracy. Standard anchor-based architectures rely on opaque latent queries th

Reconstructing conformal field theoretical compositions with Transformers

arXiv:2605.01072v1 Announce Type: cross Abstract: We study the use of transformers to reconstruct the compositions of tensor products of two-dimensional rational conformal field theories (RCFTs) based

Reconstruction Interval Z-Phase Dependence of AI Detection Sensitivity in CT Lung Nodule Screening

arXiv:2605.00971v1 Announce Type: cross Abstract: Background: Sensitivity of AI-assisted lung nodule detection systems is known to vary with CT acquisition parameters including radiation dose, reconst

Recurrent Graph Neural Networks and Arithmetic Circuits

arXiv:2603.05140v2 Announce Type: replace-cross Abstract: We characterise the computational power of recurrent graph neural networks (GNNs) in terms of arithmetic circuits over the real numbers. Our n

Referring Multiple Regions with Large Multimodal Models via Contextual Latent Steering

arXiv:2605.01827v1 Announce Type: new Abstract: Large Multimodal Models (LMMs) have recently demonstrated their proficiency in holistic visual comprehension. However, most of them struggle to tackle r

Refracting Reality: Generating Images with Realistic Transparent Objects

arXiv:2511.17340v3 Announce Type: replace Abstract: Generative image models can produce convincingly real images, with plausible shapes, textures, layouts and lighting. However, one domain in which th

ReFRAME or Remain: Unsupervised Lexical Semantic Change Detection with Frame Semantics

arXiv:2602.04514v3 Announce Type: replace Abstract: The majority of contemporary computational methods for lexical semantic change (LSC) detection are based on neural embedding distributional represen

Rethink MAE with Linear Time-Invariant Dynamics

arXiv:2605.00915v1 Announce Type: new Abstract: Standard representation probing for visual models relies on mathematically permutation-invariant operations like Global Average Pooling (GAP) or CLS tok

Rethinking Low-Light Image Enhancement: A Log-Domain Intensity--Chromaticity Decoupling Perspective

arXiv:2605.02627v1 Announce Type: new Abstract: Explicit reconstruction constraints derived from the decoupled representation are further imposed to suppress abnormal channel amplification and chromat

Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

arXiv:2605.01965v1 Announce Type: new Abstract: A classical vector retrieval problem typically considers a single query embedding vector as input and retrieves the most similar embedding vectors from

Revisiting Map Relations for Unsupervised Non-Rigid Shape Matching

arXiv:2310.11420v2 Announce Type: replace Abstract: We propose a novel unsupervised learning approach for non-rigid 3D shape matching. Our approach improves upon recent state-of-the art deep functiona

Revisiting Semantic Role Labeling: Efficient Structured Inference with Dependency-Informed Analysis

arXiv:2605.02505v1 Announce Type: new Abstract: Semantic Role Labeling (SRL) provides an explicit representation of predicate-argument structure, capturing linguistically grounded relations such as wh

Rhamba: Region-Aware Hybrid Attention-Mamba Framework for Self-Supervised Learning in Resting-State fMRI

arXiv:2605.01240v1 Announce Type: new Abstract: Self-supervised pretraining is promising for large-scale neuroimaging, yet the impact of region-aware masking and hybrid sequence modeling remains under

Riemannian Generative Decoder

arXiv:2506.19133v3 Announce Type: replace Abstract: Euclidean representations distort data with intrinsic non-Euclidean structure. While Riemannian representation learning offers a solution by embeddi

Robust and Fast Training via Per-Sample Clipping

arXiv:2605.02701v1 Announce Type: cross Abstract: We propose a robust gradient estimator based on per-sample gradient clipping and analyze its properties both theoretically and empirically. We show th

Robust Conditional Conformal Prediction via Branched Normalizing Flow

arXiv:2605.01868v1 Announce Type: new Abstract: Conformal prediction (CP) constructs prediction sets with marginal coverage guarantees under the assumption that the calibration and test distributions

Robust Linear Dueling Bandits with Post-serving Context under Unknown Delays and Adversarial Corruptions

arXiv:2605.01752v1 Announce Type: new Abstract: We study linear dueling bandits in volatile environments characterized by the simultaneous presence of post-serving contexts, delayed feedback, and adve

Robustness of Transformer-Based Fluence Map Prediction Under Clinically Realistic Perturbations

arXiv:2605.00904v1 Announce Type: new Abstract: Learning-based fluence map prediction offers a fast alternative to iterative inverse planning in intensity-modulated radiation therapy (IMRT), but its r

Rule Extraction in Machine Learning: Chat Incremental Pattern Constructor

arXiv:2208.00335v4 Announce Type: replace Abstract: Rule extraction is a central problem in interpretable machine learning because it seeks to convert opaque predictive behavior into human-readable sy

SAIL: Structure-Aware Interpretable Learning for Anatomy-Aligned Post-hoc Explanations in OCT

arXiv:2605.02707v1 Announce Type: new Abstract: Optical coherence tomography (OCT), a commonly used retinal imaging modality, plays a central role in retinal disease diagnosis by providing high-resolu

SaLF: Sparse Local Fields for Multi-Sensor Rendering in Real-Time

arXiv:2507.18713v2 Announce Type: replace Abstract: High-fidelity sensor simulation of light-based sensors such as cameras and LiDARs is critical for safe and accurate autonomy testing. Neural radianc

Sample-wise Adaptive Weighting for Transfer Consistency in Adversarial Distillation

arXiv:2512.10275v2 Announce Type: replace Abstract: Adversarial distillation in the standard min-max adversarial training framework aims to transfer adversarial robustness from a large, robust teacher

Sampling-Based Control via Entropy-Regularized Optimal Transport

arXiv:2605.02147v1 Announce Type: new Abstract: Sampling-based model predictive control methods like MPPI and CEM are essential for real-time control of nonlinear robotic systems, particularly where d

researcharxiv-cs-ro

Scaling Sequence-to-Sequence Generative Neural Rendering

arXiv:2510.04236v3 Announce Type: replace Abstract: We present Kaleido, a family of generative models designed for photorealistic, unified object- and scene-level neural rendering. Kaleido operates on