Ax Frieda Born, Tom Neuh\"auser, Lukas Muttenthaler, Brett D. Roads, Bernhard Spitzer, Andrew K. Lampinen, Matt Jones, Klaus-Robert M\"uller, Michael C. Mozer 5d ago

Context Sensitivity Improves Human-Machine Visual Alignment

Machine learning method improving alignment between human and model visual perception through context-sensitive embedding representations.

Ax Diego Vallarino 5d ago

Sandpile Economics: Theory, Identification, and Evidence

Economic theory paper analyzing production network fragility and crisis generation in capitalist economies through evolutionary geometry.

Ax Joel Niklaus, Atsuki Yamaguchi, Michal \v{S}tef\'anik, Guilherme Penedo, Hynek Kydl\'i\v{c}ek, Elie Bakouch, Lewis Tunstall, Edward Emanuel Beeching, Thibaud Frere, Colin Raffel, Leandro von Werra, Thomas Wolf 5d ago

How Can We Synthesize High-Quality Pretraining Data? A Systematic Study of Prompt Design, Generator Model, and Source Data

Systematic study of synthetic data generation for LLM pretraining, testing rephrasing strategies, generator models, and source data across one trillion tokens to identify optimal design choices.

Ax Aleksandr Rubashevskii, Dzianis Piatrashyn, Preslav Nakov, Maxim Panov 5d ago

Adaptive Conformal Prediction for Improving Factuality of Generations by Large Language Models

Adaptive conformal prediction method for improving factuality in LLM generations with prompt-dependent uncertainty estimates and statistical guarantees.

Ax Davyd Naveriani, Albert Zeyer, Ralf Schl\"uter, Hermann Ney 5d ago

Diffusion Language Models for Speech Recognition

Exploration of masked and uniform-state diffusion language models for speech recognition rescoring and ASR hypothesis improvement.

Ax Gitesh Malik 5d ago

Hierarchical Reinforcement Learning with Runtime Safety Shielding for Power Grid Operation

Hierarchical RL with runtime safety shielding for automated power grid operations, addressing safety constraints and generalization to unseen topologies.

Ax Lev Razumovskiy, Nikolay Karenin 5d ago

A Comparative Study of Dynamic Programming and Reinforcement Learning in Finite Horizon Dynamic Pricing

Comparative analysis of Fitted Dynamic Programming vs Reinforcement Learning for dynamic pricing across varying complexity levels and demand structures.

Ax Buse \c{S}en, Yifan Hu, Daniel Kuhn 5d ago

Multistage Conditional Compositional Optimization

Multistage conditional compositional optimization framework combining stochastic programming with uncertainty handling. Applied to control and stopping problems.

Ax Xiaofan Zhou, Kyumin Lee 5d ago

ID and Graph View Contrastive Learning with Multi-View Attention Fusion for Sequential Recommendation

Graph neural network with contrastive learning for sequential recommendation systems. Studies e-commerce user preference prediction.

Ax Louie Hong Yao, Vishesh Anand, Yuan Zhuang, Tianyu Jiang 5d ago

Rhetorical Questions in LLM Representations: A Linear Probing Study

Linear probe analysis of how LLMs internally represent rhetorical questions. Studies persuasive language understanding in neural representations.

Ax Itay Itzhak, Eliya Habba, Gabriel Stanovsky, Yonatan Belinkov 5d ago

From Feelings to Metrics: Understanding and Formalizing How Users Vibe-Test LLMs

Formalizes 'vibe-testing' methodology for LLM evaluation. Studies how practitioners informally assess models beyond benchmarks.

Ax Quyen Tran, Hai Nguyen, Hoang Phan, Quan Dao, Linh Ngo, Khoat Than, Dinh Phung, Dimitris Metaxas, Trung Le 5d ago

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

Optimal transport method for class centroid learning in online incremental learning with distribution shift. Addresses multimodal stream learning.

Ax Danrui Qi, Jinglin Peng, Yongjun He, Jiannan Wang 5d ago

Auto-FP: An Experimental Study of Automated Feature Preprocessing for Tabular Data

Automated feature preprocessing pipeline search for tabular machine learning. Studies AutoML approaches for classical model data preparation.

Ax Ebrahim Farahmand, Shovito Barua Soumma, Nooshin Taheri Chatrudi, Hassan Ghasemzadeh 5d ago

Hybrid Attention Model Using Feature Decomposition and Knowledge Distillation for Glucose Forecasting

Hybrid attention model with feature decomposition for continuous glucose monitoring forecasting. Medical domain-specific time series prediction.

Ax Fatih Dinc, Ege Cirakman, Bariscan Kurtkaya, Mert Yuksekgonul, Yiqi Jiang, Mark J. Schnitzer, Hidenori Tanaka 5d ago

A ghost mechanism: An analytical model of abrupt learning in recurrent networks

Ghost mechanism analytical model explaining abrupt learning in RNNs on memory tasks. Studies transient dynamics and computation timescales.

Ax Muhammad Faraz Ul Abrar, Nicol\`o Michelusi 5d ago

Biased Federated Learning under Wireless Heterogeneity

Federated learning framework analysis under wireless heterogeneity. Studies gradient aggregation strategies in distributed learning.

Ax Vansh Kapoor, Jayakrishnan Nair 5d ago

MDPs with a State Sensing Cost

Markov decision processes with state sensing costs, balancing optimal actions against sensing/communication/computation expenses in decision-making.

Ax Mingkuan Feng, Jinyang Wu, Siyuan Liu, Shuai Zhang, Ruihan Jin, Feihu Che, Pengpeng Shao, Zhengqi Wen, Jianhua Tao 5d ago

Two-Stage Regularization-Based Structured Pruning for LLMs

Two-stage regularization-based structured pruning method for reducing LLM parameters while minimizing knowledge loss and retraining requirements.

Ax Zhuochen Liu, Rahul Jain, Quan Nguyen 5d ago

RANDPOL: Parameter-Efficient End-to-End Quadruped Locomotion via Randomized Policy Learning

Randomized Policy Learning approach for quadruped locomotion control with drastically reduced trainable parameters in neural network policies.

Ax Xudong Zhang, Renato Cordeiro de Amorim 5d ago

Scalable unsupervised feature selection via weight stability

Minkowski weighted k-means++ for unsupervised feature selection in high-dimensional clustering by probabilistic centroid selection.

Ax Hanbing Liu, Lang Cao, Yuanyi Ren, Mengyu Zhou, Haoyu Dong, Xiaojun Ma, Shi Han, Dongmei Zhang 5d ago

Not All Tokens Matter: Towards Efficient LLM Reasoning via Token Significance in Reinforcement Learning

Token significance scoring in reinforcement learning to improve LLM reasoning efficiency by identifying which tokens contribute to correctness.

Ax Daniel Jenson, Jhonathan Navott, Piotr Grynfelder, Mengyan Zhang, Makkunda Sharma, Elizaveta Semenova, Seth Flaxman 5d ago

Scalable Spatiotemporal Inference with Biased Scan Attention Transformer Neural Processes

Biased Scan Attention Transformer Neural Processes for scalable spatiotemporal inference across geology, epidemiology, climate and robotics applications.

Ax William Anderson, Seung Whan Chung, Robert Stephany, Youngsoo Choi 5d ago

mLaSDI: Multi-stage latent space dynamics identification

Multi-stage latent space dynamics identification framework for solving PDEs via data-driven reduced-order models using autoencoders and ODEs.

Ax Mathieu Godbout, Audrey Durand 5d ago

On the Fundamental Limitations of Dual Static CVaR Decompositions in Markov Decision Processes

Theoretical analysis of CVaR policy evaluation limitations in MDPs using dual formulations.

Ax Bokeng Zheng, Jianqiang Zhong, Jiayi Liu, Lei Xue, Xu Chen, Xiaoxi Zhang 5d ago

Decentralized Rank Scheduling for Energy-Constrained Multi-Task Federated Fine-Tuning in Edge-Assisted IoV Networks

Federated fine-tuning framework for multi-task adaptation in edge IoV networks with hierarchical rank scheduling.

Ax Aymene Mohammed Bouayed, Samuel Deslauriers-Gauthier, Adrian Iaccovelli, David Naccache 5d ago

Heavy-Tailed Class-Conditional Priors for Long-Tailed Generative Modeling

Class-conditional heavy-tailed priors in VAEs addressing latent space bias for long-tailed generative modeling.

Ax Zhengyan Wan, Yidong Ouyang, Liyan Xie, Fang Fang, Hongyuan Zha, Guang Cheng 5d ago

Discrete Guidance Matching: Exact Guidance for Discrete Flow Matching

Guidance framework for discrete flow matching with exact guidance in discrete state spaces.

Ax Hoang Anh Just, Myeongseob Ko, Ruoxi Jia 5d ago

The Signal is in the Steps: Local Scoring for Reasoning Data Selection

Local scoring method for selecting reasoning data from diverse teachers for efficient distillation into student models.

Ax Xuefeng Xu, Graham Cormode 5d ago

Power Transform Revisited: Numerically Stable, and Federated

Numerically stable implementation of power transforms for data preprocessing with federated learning support.

Ax Alexis Ross, Megha Srivastava, Jeremiah Blanchard, Jacob Andreas 5d ago

Modeling Student Learning with 3.8 Million Program Traces

Student learning model from 3.8M program traces analyzing coding skill development through interaction patterns.

Ax Israel Mason-Williams, Gabryel Mason-Williams, Helen Yannakoudakis 5d ago

A Function-Centric Perspective on Flat and Sharp Minima

Function-centric analysis of flat vs sharp minima in deep networks, showing sharpness is function-dependent.

Ax Mehrzad Samadi, Aleksander Ficek, Sean Narenthiran, Siddhartha Jain, Wasi Uddin Ahmad, Somshubra Majumdar, Vahid Noroozi, Boris Ginsburg 5d ago

Scaling Test-Time Compute to Achieve IOI Gold Medal with Open-Weight Models

Open-weight LLMs achieving IOI gold medal through test-time compute scaling for competitive programming.

Ax Tongkai Lu, Shuai Ma, Chongyang Tao 5d ago

Empowering Targeted Neighborhood Search via Hyper Tour for Large-Scale TSP

Neural method with hyper-tour for targeted neighborhood search solving large-scale TSP instances efficiently.

Ax Amir Noorizadegan, Sifan Wang, Leevan Ling, Juan P. Dominguez-Morales 5d ago

A Practitioner's Guide to Kolmogorov-Arnold Networks

Comprehensive review of Kolmogorov-Arnold Networks covering theory, relationships to MLPs and kernel methods, and applications.

Ax Erle Zhu, Dazhi Jiang, Yuan Wang, Xujun Li, Jiale Cheng, Yuxian Gu, Yilin Niu, Aohan Zeng, Jie Tang, Minlie Huang, Hongning Wang 5d ago

Data-Efficient RLVR via Off-Policy Influence Guidance

Influence-guided data selection for RLVR with theoretical guarantees for improving LLM reasoning efficiency.

Ax Hsiu-Yuan Huang, Chenming Tang, Weijie Liu, Clive Bai, Saiyong Yang, Yunfang Wu 5d ago

Think Outside the Policy: In-Context Steered Policy Optimization

In-context policy optimization for large reasoning models using off-policy exploration to improve RLVR reasoning capabilities.

Ax Jan-Hendrik Ewering, Robin E. Herrmann, Niklas Wahlstr\"om, Thomas B. Sch\"on, Thomas Seel 5d ago

Learning Dynamics from Input-Output Data with Hamiltonian Gaussian Processes

Hamiltonian Gaussian Processes for learning physically consistent dynamics from input-output data without velocity information.

Ax Haipeng Cao, Kaining Zhang, Dacheng Tao, Zhaofeng Su 5d ago

Mitigating Barren Plateaus in Quantum Denoising Diffusion Probabilistic Model

Analysis of barren plateau problem in quantum denoising diffusion models for learning quantum and classical data.

Ax Julian Kleutgens, Claudio Battiloro, Lingkai Kong, Benjamin Grewe, Francesca Dominici, Mauricio Tec 5d ago

Guided Transfer Learning for Discrete Diffusion Models

Transfer learning via classifier guidance for discrete diffusion models in small-data regimes, extending continuous diffusion techniques.

Ax Jeff Smith 5d ago

SHARe-KAN: Post-Training Vector Quantization for Cache-Resident KAN Inference

Vector quantization technique for optimizing Kolmogorov-Arnold Network inference on edge devices with memory constraints.

Ax Felix Lehner, Pasquale Lombardo, Susana Castillo, Oliver Hupe, Marcus Magnor 5d ago

Learning-Based Estimation of Spatially Resolved Scatter Radiation Fields in Interventional Radiology

Neural network approach for estimating scattered radiation fields in interventional radiology with synthetic training datasets.

Ax Haley Rosso, Talea Mayo 5d ago

A Review of Diffusion-based Simulation-Based Inference: Foundations and Applications in Non-Ideal Data Scenarios

Review of diffusion models for simulation-based inference with intractable likelihoods, covering theoretical foundations and applications.

Ax Sumit S. Shevtekar, Chandresh K. Maurya, Gourab Sil 5d ago

Predicting Time Pressure of Powered Two-Wheeler Riders for Proactive Safety Interventions

ML model predicting time pressure effects on motorcycle riders using 129k+ time-series sequences for safety interventions.

Ax Ioannis Anagnostides, Gabriele Farina, Maxwell Fishelson, Haipeng Luo, Jon Schneider 5d ago

Swap Regret Minimization Through Response-Based Approachability

Computationally efficient algorithms for swap regret minimization in online optimization with connections to correlated equilibrium and non-manipulability.

Ax Zhihao Ding, Jinming Li, Ze Lu, Jieming Shi 5d ago

FlexGuard: Continuous Risk Scoring for Strictness-Adaptive LLM Content Moderation

LLM content moderation system with continuous risk scoring that adapts to changing strictness requirements across platforms, replacing fixed binary classification.

Ax Elizabeth W. Miller, Jeffrey D. Blume 5d ago

Diagnostics for Individual-Level Prediction Instability in Machine Learning for Healthcare

Diagnostic methods for measuring prediction instability in overparameterized ML models for healthcare, addressing variability in individual risk estimates.

Ax Chenghan Wu, Zongmin Yu, Boai Sun, Liu Yang 5d ago

Graph In-Context Operator Networks for Generalizable Spatiotemporal Prediction

Systematic comparison of in-context operator learning versus single-operator learning for spatiotemporal prediction using neural networks.

Ax Chihan Huang, Huaijin Wang, Shuai Wang 5d ago

ReproMIA: A Comprehensive Analysis of Model Reprogramming for Proactive Membership Inference Attacks

Comprehensive analysis of model reprogramming techniques for membership inference attacks, evaluating privacy vulnerabilities in deep learning models.

Ax Nida Zamir, I-Hong Hou 5d ago

Restless Bandits with Individual Penalty Constraints: A New Near-Optimal Index Policy and How to Learn It

Near-optimal index policy for restless multi-armed bandits with individual penalty constraints for resource allocation in dynamic wireless networks.

Ax Srinidhi Madabhushi, Pranesh Vyas, Swathi Vaidyanathan, Mayur Kurup, Elliott Nash, Yegor Silyutin 5d ago

From Load Tests to Live Streams: Graph Embedding-Based Anomaly Detection in Microservice Architectures

Graph embedding-based anomaly detection system for microservice architectures using unsupervised learning, applied to Prime Video load testing and live events.