Search: “research”

Optimal Representations for Generalized Contrastive Learning with Imbalanced Datasets

arXiv:2605.11291v1 Announce Type: new Abstract: In this paper, we provide a computable characterization of the geometry of optimal representations in Contrastive Learning (CL) when the classes are imb

Optimistic Dual Averaging Unifies Modern Optimizers

DGX agent

arXiv:2605.11172v1 Announce Type: new Abstract: We introduce SODA, a generalization of Optimistic Dual Averaging, which provides a common perspective on state-of-the-art optimizers like Muon, Lion, Ad

researcharxiv-cs-lg

13 May 2026

ORBIT: Preserving Foundational Language Capabilities in GenRetrieval via Origin-Regulated Merging

arXiv:2605.12419v1 Announce Type: new Abstract: Despite the rapid advancements in large language model (LLM) development, fine-tuning them for specific tasks often results in the catastrophic forgetti

Oscillators Are All You Need: Irregular Time Series Modelling via Damped Harmonic Oscillators with Closed-Form Solutions

arXiv:2602.12139v2 Announce Type: replace Abstract: Transformers excel at time series modelling through attention mechanisms that capture long-term temporal patterns. However, they assume uniform time

OTT-Vid: Optimal Transport Temporal Token Compression for Video Large Language Models

arXiv:2605.11803v1 Announce Type: new Abstract: As Video Large Language Models (Video-LLMs) scale to longer and more complex videos, their inference cost grows rapidly due to the large volume of visua

Overparametrized models with posterior drift

arXiv:2506.23619v2 Announce Type: replace-cross Abstract: This paper investigates the impact of posterior drift on out-of-sample forecasting accuracy in overparametrized machine learning models. We do

PairDropGS: Paired Dropout-Induced Consistency Regularization for Sparse-View Gaussian Splatting

arXiv:2605.12072v1 Announce Type: new Abstract: Dropout-based sparse-view 3D Gaussian Splatting (3DGS) methods alleviate overfitting by randomly suppressing Gaussian primitives during training. Existi

Parabolic Position Encoding: Vision-Centric, Principled, Extrapolatable, General

arXiv:2602.01418v2 Announce Type: replace Abstract: We propose Parabolic Position Encoding (PaPE), a parabola-based position encoding for vision modalities in attention-based architectures. Given a se

Partial Model Sharing Improves Byzantine Resilience in Federated Conformal Prediction

arXiv:2605.11684v1 Announce Type: new Abstract: We propose a Byzantine-resilient federated conformal prediction (FCP) method that leverages partial model sharing, where only a subset of model paramete

Partition Tree: Conditional Density Estimation over General Outcome Spaces

arXiv:2602.04042v2 Announce Type: replace Abstract: We propose Partition Tree, a novel tree-based framework for conditional density estimation over general outcome spaces that supports both continuous

PENEX: AdaBoost-Inspired Neural Network Regularization

arXiv:2510.02107v4 Announce Type: replace Abstract: AdaBoost sequentially fits so-called weak learners to minimize an exponential loss, which penalizes misclassified data points more severely than oth

Physics Aware Neural Networks: Denoising for Magnetic Navigation

arXiv:2602.13690v2 Announce Type: replace Abstract: Magnetic-anomaly navigation, leveraging small-scale variations in the Earth's magnetic field, is a promising alternative when GPS is unavailable or

Pion: A Spectrum-Preserving Optimizer via Orthogonal Equivalence Transformation

arXiv:2605.12492v1 Announce Type: new Abstract: We introduce Pion, a spectrum-preserving optimizer for large language model (LLM) training based on orthogonal equivalence transformation. Unlike additi

PointCaM: Cut-and-Mix for Open-Set Point Cloud Learning

arXiv:2212.02011v3 Announce Type: replace Abstract: Point cloud learning is receiving increasing attention. However, most existing point cloud models lack the practical ability to deal with the unavoi

Predicting Disagreement with Human Raters in LLM-as-a-Judge Difficulty Assessment without Using Generation-Time Probability Signals

arXiv:2605.12422v1 Announce Type: new Abstract: Automatic generation of educational materials using large language models (LLMs) is becoming increasingly common, but assigning difficulty levels to suc

Pretraining Strategies and Scaling for ECG Foundation Models: A Systematic Study

arXiv:2605.12241v1 Announce Type: cross Abstract: Specialized foundation models are beginning to emerge in various medical subdomains, but pretraining methodologies and parametric scaling with the siz

Principle-Guided Supervision for Interpretable Uncertainty in Medical Image Segmentation

arXiv:2605.10984v1 Announce Type: new Abstract: Uncertainty quantification complements model predictions by characterizing their reliability, which is essential for high-stakes decision making such as

Principled Design of Diffusion-based Optimizers for Inverse Problems

arXiv:2605.11506v1 Announce Type: new Abstract: Score-based diffusion models achieve state-of-the-art performance for inverse problems, but their practical deployment is hindered by long inference tim

Principled Latent Diffusion for Graphs via Laplacian Autoencoders

arXiv:2601.13780v3 Announce Type: replace Abstract: Graph diffusion models achieve state-of-the-art performance in graph generation but suffer from quadratic complexity in the number of nodes -- and m

Pure Exploration Beyond Reward Feedback: The Role of Post-Action Context

arXiv:2502.03061v2 Announce Type: replace Abstract: We introduce the problem of best arm identification (BAI) with post-action context, a new BAI problem in a stochastic multi-armed bandit environment

Quantifying Rodda and Graham Gait Classification from 3D Makerless Kinematics derived from a Single-view Video in a Heterogeneous Pediatric Clinical Cohort

arXiv:2605.11314v1 Announce Type: new Abstract: Cerebral Palsy (CP) is a neurological disorder of movement and the most common cause of lifelong physical disability in childhood. Approximately 75% of

Read, Extract, Classify: A Tool for Smarter Requirements Engineering

arXiv:2605.11045v1 Announce Type: cross Abstract: This paper presents the ReXCL tool, which automates the extraction and classification processes in requirements engineering, enhancing the software de

ReAD: Reinforcement-Guided Capability Distillation for Large Language Models

arXiv:2605.11290v1 Announce Type: new Abstract: Capability distillation applies knowledge distillation to selected model capabilities, aiming to compress a large language model (LLM) into a smaller on

RealDiffusion: Physics-informed Attention for Multi-character Storybook Generation

arXiv:2605.11927v1 Announce Type: new Abstract: While modern diffusion models excel at generating diverse single images, extending this to sequential generation reveals a fundamental challenge: balanc

ReasonEdit: Editing Vision-Language Models using Human Reasoning

arXiv:2602.02408v4 Announce Type: replace Abstract: Model editing aims to correct errors in large, pretrained models without altering unrelated behaviors. While some recent works have edited vision-la

Regret minimization in Linear Bandits with offline data via extended D-optimal exploration

arXiv:2508.08420v3 Announce Type: replace Abstract: We consider the problem of online regret minimization in linear bandits with access to prior observations (offline data) from the underlying bandit

Remarks on stochastic cloning and delayed-state filtering

arXiv:2508.21260v2 Announce Type: replace Abstract: Many estimation problems in aerospace navigation and robotics involve measurements that depend on prior states. A prominent example is odometry, whi

RETUYT-INCO at BEA 2026 Shared Task 2: Meta-prompting in Rubric-based Scoring for German

arXiv:2605.11242v1 Announce Type: new Abstract: In this paper, we present the RETUYT-INCO participation at the BEA 2026 shared task 'Rubric-based Short Answer Scoring for German'. Our team participate

RevealLayer: Disentangling Hidden and Visible Layers via Occlusion-Aware Image Decomposition

arXiv:2605.11818v1 Announce Type: new Abstract: Recent diffusion-based approaches have made substantial progress in image layer decomposition. However, accurately decomposing complex natural images re

ReVision: Scaling Computer-Use Agents via Temporal Visual Redundancy Reduction

arXiv:2605.11212v1 Announce Type: new Abstract: Computer-use agents~(CUAs) rely on visual observations of graphical user interfaces, where each screenshot is encoded into a large number of visual toke

Revisiting GAN with Bayes-Optimal Discrimination

arXiv:2510.25609v3 Announce Type: replace Abstract: We propose an alternative to the standard GAN training approach, in which the discriminator is a binary classifier trained by cross-entropy to disti

RNA-FM: Flow-Matching Generative Model for Genome-wide RNA-Seq Prediction

arXiv:2605.11622v1 Announce Type: new Abstract: Histopathology whole-slide images (WSIs) are routinely acquired in clinical practice and contain rich tissue morphology but lack direct molecular archit

Robust Biomedical Publication Type and Study Design Classification with Knowledge-Guided Perturbations

arXiv:2605.11502v1 Announce Type: new Abstract: Accurately and consistently indexing biomedical literature by publication type and study design is essential for supporting evidence synthesis and knowl

Rollbot: a Spherical Robot Driven by a Single Actuator

arXiv:2404.05120v2 Announce Type: replace Abstract: Spherical robots typically require at least two actuators to achieve controlled 2D planar motion. Here we present Rollbot, the first spherical robot

Rotary Masked Autoencoders are Versatile Learners

arXiv:2505.20535v3 Announce Type: replace Abstract: Applying Transformers to irregular time-series typically requires specializations to their baseline architecture, which can result in additional com

Rotation-Preserving Supervised Fine-Tuning

arXiv:2605.10973v1 Announce Type: new Abstract: Supervised fine-tuning (SFT) improves in-domain performance but can degrade out-of-domain (OOD) generalization. Prior work suggests that this degradatio

RT-Transformer: The Transformer Block as a Spherical State Estimator

arXiv:2605.11007v1 Announce Type: new Abstract: We show that the core components of the Transformer block -- attention, residual connections, and normalization -- arise naturally from a single geometr

Sampling-Based Follow-the-Leader Motion Planning for Manipulator-Mounted Continuum Robots

arXiv:2605.11618v1 Announce Type: new Abstract: Follow-the-leader (FTL) motion exploits the unique morphology of continuum robots (CRs) to navigate confined spaces by having the body retrace the path

Scalable Token-Level Hallucination Detection in Large Language Models

arXiv:2605.12384v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but they still frequently produce hallucinations. These hallucinations are diffi

ScaleMoGen: Autoregressive Next-Scale Prediction for Human Motion Generation

arXiv:2605.11704v1 Announce Type: new Abstract: We present ScaleMoGen, a scale-wise autoregressive framework for text-driven human motion generation. Unlike conventional autoregressive approaches that

ScribbleDose: Scribble-Guided Dose Prediction in Radiotherapy

arXiv:2605.11555v1 Announce Type: new Abstract: Anatomical structure masks are widely adopted in radiotherapy dose prediction, as they provide explicit geometric constraints that facilitate structure-

See the past: Time-Reversed Scene Reconstruction from Thermal Traces Using Visual Language Models

arXiv:2510.05408v2 Announce Type: replace Abstract: Recovering the past from present observations is an intriguing challenge with potential applications in forensics and scene analysis. Thermal imagin

Self-Distilled Trajectory-Aware Boltzmann Modeling: Bridging the Training-Inference Discrepancy in Diffusion Language Models

arXiv:2605.11854v1 Announce Type: new Abstract: Diffusion Language Models (DLMs) have recently emerged as a promising alternative to autoregressive language models, offering stronger global awareness

Semi-Supervised Bayesian GANs with Log-Signatures for Uncertainty-Aware Credit Card Fraud Detection

arXiv:2509.00931v3 Announce Type: replace-cross Abstract: We present a novel deep generative semi-supervised framework for credit card fraud detection, formulated as time series classification task. A

Shapley Value Approximation Based on k-Additive Games

arXiv:2502.04763v2 Announce Type: replace-cross Abstract: The Shapley value is the prevalent solution for fair division problems in which a payout is to be divided among multiple agents. By adopting a

ShardTensor: Domain Parallelism for Scientific Machine Learning

arXiv:2605.11111v1 Announce Type: cross Abstract: Scientific Machine Learning (SciML) faces unique challenges for extreme-resolution data, with mitigations that often fail to scale or degrade the accu

Single-Shot HDR Recovery via a Video Diffusion Prior

arXiv:2605.11628v1 Announce Type: new Abstract: Recent generative methods for single-shot high dynamic range (HDR) image reconstruction show promising results, but often struggle with preserving fidel

Smooth-Rigid-Body Contact as a ReLCP: A Recursively Generated Linear Complementarity Problem

arXiv:2506.14097v2 Announce Type: replace Abstract: This paper reformulates complementarity-based time-stepping for frictionless nonsmooth contact between smooth rigid bodies as a recursively generate