Ax Niccol\`o Maria Rizzi, Eugenio Lomurno, Alberto Archetti, Matteo Matteucci 11d ago

A Filtered Mixture-of-Generators for Fully Synthetic Survival Training

Mixture-of-generators approach for synthesizing survival analysis training data in privacy-constrained clinical settings.

Ax Yong Yi Bay, Kathleen A. Yearick 11d ago

GRPO, Dr. GRPO, and DAPO Are Three Operations on One Number: The Group-Standard-Deviation Identity

Analysis showing GRPO, Dr. GRPO, and DAPO LLM training methods adjust a single metric: standard deviation of model disagreement.

Ax AbdElRahman ElSaid, Damir Pulatov 11d ago

EVOTS: Evolutionary Transformer Search for Time Series Forecasting

Neural architecture search framework using evolutionary algorithms to design task-adaptive Transformer models for time-series forecasting.

Ax Tom Saliencro, Maya Lindqvist, Rohan Desai, Priya Nair, Daniel Whitmore 11d ago

FRAME: Learning the Adaptation Domain with a Mixture of Fractional-Fourier Experts

Parameter-efficient fine-tuning method using mixture-of-experts with learned transformation domains for model adaptation.

Ax Sadanand Singh, Allam Reddy, Manan Chopra 11d ago

Verifiable Rewards for Calibrated Probabilistic Forecasting

Reinforcement learning approach using verifiable scoring rules to train calibrated probabilistic forecasting models.

Ax Andrew G. Moore 11d ago

Scaling Up Thermodynamic AI Models

Scalable training algorithm for Ising-model-based thermodynamic computing devices for low-power AI inference.

Ax Radhakrishna Achanta, Will Reed 11d ago

TallyTrain: Communication-Efficient Federated Distillation

Federated learning optimization reducing communication bandwidth for model parameter averaging and knowledge distillation across distributed peers.

Ax Andrzej Bia{\l}ecki, Adam Mastalerz, Han Zhou 11d ago

Play Like Champions: Counterfactual Feedback Generation in Latent Space

Generates counterfactual feedback from superhuman game agents by analyzing latent geometry of expert performance.

Ax Bharat Srikishan, Javier E. Santos, Nikhil Muralidhar, Charles D. Young 11d ago

TRIE: An Evaluation Framework for Stochastic PDE Surrogates

TRIE evaluation framework measures whether stochastic PDE surrogates reproduce invariant statistical measures.

Ax Haroon Gharwi, Yue Dai, Kai Shu 11d ago

StateFlow: Dual-State Recurrent Modeling for Long-Horizon Time Series Forecasting

StateFlow dual-state recurrent model tracks variability for long-horizon multivariate time series forecasting.

Ax Geeling Chau, Ran Liu, Juri Minxha, Wenhui Cui, Erdrin Azemi, Ellen L. Zippi, Behrooz Mahasseni, Christopher M. Sandino 11d ago

Device Passport: Enabling Spatio-Temporal Pretrained Models to Generalize Across Input Layouts

Device Passport channel embedding technique enables biosignal foundation models to generalize across hardware layouts.

Ax Naren Sarayu Manoj, Kumar Kshitij Patel 11d ago

Distributionally Robust Linear Regression With Block Lewis Weights

Algorithm for group distributionally robust least squares using block Lewis weights with improved complexity bounds.

Ax Max Kreider, John Harlim, Daning Huang 11d ago

Learning dynamical systems from noisy data with Weak-form Kernel Ridge Regression

Weak-form kernel ridge regression approach improves noise robustness for learning complex dynamical systems.

Ax Maxime M\'eloux, Tiago Pimentel, Fran\c{c}ois Portet, Maxime Peyrard 11d ago

Validating Causal Abstraction Metrics on Simulated Complex Systems

Benchmark for validating causal abstraction metrics across ten complex systems with ground-truth explanations.

Ax Krishna Harsha Kovelakuntla Huthasana, Alireza Olama, Andreas Lundell 11d ago

Entropy-Regularized Probabilistic Gates for Sparse Model Discovery in Scarce-Data Federated Learning

Entropy-regularized probabilistic gates learn sparse models in federated learning under data heterogeneity.

Ax Dong Zhang 11d ago

Testing Frontier Large Language Models' Physics Literacy in Parallel Physical Worlds

Four-stage diagnostic evaluates LLM physics reasoning through induction, formulation, prediction, and review in unfamiliar frameworks.

Ax Yufei Wu, Daniel Schmierer 11d ago

Understanding Guest Preferences and Optimizing Two-sided Marketplaces: Airbnb as an Example

Airbnb optimization case study on pricing tools and guest preference personalization in two-sided marketplaces.

Ax Zewen Liu 11d ago

EPC: A Standardized Protocol for Measuring Evaluator Preference Dynamics in LLM Agent Systems

EPC protocol standardizes measurement of evaluator preference coupling in LLM agent feedback loops.

Ax Zewen Liu 11d ago

Mapping the Evaluation Frontier: An Empirical Survey of the Bias-Reliability Tradeoff Across Eleven Evaluator-Agent Conditions

Empirical survey of 11 evaluator-agent conditions exploring bias-reliability tradeoff in LLM evaluation systems.

Ax John Kirchenbauer, Brian R. Bartoldson, Bhavya Kailkhura, Tom Goldstein 11d ago

Watermarking for Proprietary Dataset Protection

Uses output watermarking techniques to make training data membership inference more tractable for generative language models.

Ax Gil Pasternak 11d ago

K-Inverse-RFM: A Modified RFM that Bridges the Gap to Neural Networks for Data-Corrupted Mathematical Tasks

K-Inverse-RFM modifies recursive feature machines to improve performance on corrupted mathematical tasks compared to neural networks.

Ax Xin Zhou, Xiang Zhang, Hao Deng, Lijun Yin 11d ago

PRISM: Prioritized Channel Importance with Semi-supervised Domain Adaptation for Cross-Subject EEG Emotion Recognition

PRISM framework combines channel prioritization and semi-supervised domain adaptation for cross-subject EEG emotion recognition.

Ax Yuting Zhang, Yanbei Liu, Zhitao Xiao, Lei Geng, Yanwei Pang, Xiao Wang 11d ago

SAOT: Self-Supervised Continual Graph Learning with Structure-Aware Optimal Transport

Self-supervised continual graph learning method using structure-aware optimal transport for sequential graph tasks.

Ax Jongchan Park, Seungjun Oh, Seungho Baek, Yusung Kim 11d ago

Learning Generalizable Skill Policy with Data-Efficient Unsupervised RL

GenDa addresses non-stationary skill semantics and generalization in unsupervised RL for skill-conditioned policy pre-training.

Ax Md Rakibul Haque, Shireen Elhabian, Warren Woodrich Pettine 11d ago

Timesynth: A Temporal Fidelity Framework for Health Signal Digital Twins

Proposes temporal fidelity framework for health signal forecasting that preserves oscillatory and phase dynamics.

Ax Konstantin Garbers 11d ago

Gauging, Measuring, and Controlling Critic Complexity in Actor-Critic Reinforcement Learning

Introduces spectral effective-rank entropy as diagnostic for critic complexity in actor-critic RL methods.

Ax Tong Xu, Xinzhe Cao, Zhihui Zhu, Keyan Ding, Huajun Chen 11d ago

MolSafeEval: A Benchmark for Uncovering Safety Risks in AI-Generated Molecules

Benchmark for evaluating safety risks in AI-generated molecules, addressing toxicity and hazard detection.

Ax Xiao Han, Jingjing Liu, Moxuan Zheng, Zhen Zhang, Chenyu Wu 11d ago

Interpretable vs Learned Encoders for High-Cardinality Fraud Detection

Comparison of seven categorical encoding methods for high-cardinality fraud detection on IEEE-CIS benchmark dataset.

Ax Peilin Liu, Ding-Xuan Zhou 11d ago

Ghost in the Kernel: In-Context Learning with Efficient Transformers via Domain Generalization

Linear transformers enable efficient in-context learning with reduced computational complexity while maintaining task generalization.

Ax Anindya Sarkar, Nasik Muhammad Nafi, Isaac Lyngaas, Muralikrishnan Gopalakrishnan Meena, Yevgeniy Vorobeychik 11d ago

PAPA: Online Personalized Active Preference Alignment

Diffusion models fine-tuned via RL for personalized recommender systems using interactive user feedback.

Ax Dan Ley, Giang Nguyen, Himabindu Lakkaraju, Julius Adebayo 11d ago

Prototype Language Models

arXiv paper introducing prototype language models that make training data influence explicit and traceable for interpretability.

Ax Ka Ching Chan, Qiana Liu, Sanjib Tiwari, Ranga Chimhundu 11d ago

From Structural Equation Modelling to Double Machine Learning: Robustness Analysis for Survey-Based Research

arXiv paper connecting structural equation modeling with machine learning for robustness analysis in survey research.

Ax Xuefeng Liu, Mingxuan Cao, Qinan Huang, Thomas Brettin, Rick Stevens, Le Cong 11d ago

Active-GRPO: Adaptive Imitation and Self-Improving Reasoning for Molecular Optimization

arXiv paper combining adaptive imitation learning and RL for improving LLM reasoning in molecular optimization.

Ax Zhiqi Li, Wen Zhang, Bo Zhu 11d ago

Flow-Map GRPO: Reinforcement Learning for Few-Step Flow-Map Generators via Anchored Stochastic Composition

arXiv paper on RL post-training for few-step flow-map generators using anchored stochastic composition.

Ax Aiden Durrant, Rahul Baburajan, Georgios Leontidis 11d ago

Group-Equivariant Poincar\'e Convolutional Networks

arXiv paper on group-equivariant convolutional networks in hyperbolic space for visual representations.

Ax Haeun Jeon, Seunghoon Choi, Hyunglip Bae, Yongjae Lee, Woo Chang Kim 11d ago

Decision-focused Sparse Tangent Portfolio Optimization

arXiv paper on decision-focused learning for sparse portfolio optimization using end-to-end framework.

Ax Tejas Pradeep Shirodkar 11d ago

Measuring Dead Directions: Decomposing and Classifying Singular Structure off Canonical Alignment

arXiv paper measuring singular structure in neural networks through directional-Fisher rate analysis.

Ax Darshan Patil, Ekaterina Lobacheva, Razvan Pascanu, Sarath Chandar 11d ago

Loss Smoothing for Stable Adaptation Under Distribution Shift

arXiv paper on loss smoothing technique to stabilize neural network adaptation under distribution shift.

Ax Yifei Sun, Zemin Liu, Bryan Hooi, Yang Yang, Rizal Fathony, Jia Chen, Bingsheng He 11d ago

Multi-Label Node Classification with Label Influence Propagation

arXiv paper on multi-label node classification using label influence propagation on graphs.

Ax Bin Du, Chang Liu, Dingqi Zhu, Lintao Ye, Dengfeng Sun 11d ago

Distributed Online Bandit Submodular Maximization with Bounded Sampling Violations

arXiv paper on distributed online submodular maximization with bandit feedback across multiple agents.

Ax Seokhee Jin, Changhwan Sung, Sunung Mun, Hoyoung Kim, Jungseul Ok 11d ago

AdaBoosting Text Prompts for Vision-Language Models

arXiv paper using AdaBoosting for adapting text prompts in vision-language models with few labeled examples.

Ax Edouard R. Dufour, Pascal Fua 11d ago

Generative Refinement for Low-Budget Black-Box Optimization

arXiv paper on generative models for low-budget black-box optimization with noisy or expensive evaluations.

Ax Seung Hun Han, Hyeongwon Kang, Jinwoo Park, Pilsung Kang 11d ago

Detecting the Undetectable: Enhancing Unsupervised time series Anomaly Detection via Active Learning

arXiv paper combining active learning with unsupervised methods to detect anomalies in time series data.

Ax Hanning Yang, Meropi Karakioulaki, Lennart Purucker, Tim Litwin, Cristina Has, Moritz Hess 11d ago

LLM-Guided ODE Discovery and Parameter Inference from Small-Cohort Aggregate Data

arXiv paper using LLMs to guide ODE discovery and parameter inference from limited clinical data for rare diseases.

Ax Sheng Qiang, Ruiwei Chen, Yinpeng Wu, Jinyu Gu, Zhichao Hua, Yubin Xia, Binyu Zang, Haibo Chen 11d ago

MosaicKV: Serving Long-Context LLM with Dynamic Two-D KV Cache Compression

arXiv paper on MosaicKV, a dynamic 2D KV cache compression technique for serving long-context LLMs efficiently.

Ax Yu Yao, Huanjian Zhou, Andi Han, Wei Huang, Masashi Sugiyama 11d ago

Accelerating Discrete Diffusion Models with Parallel-In-Time Sampling

arXiv paper parallelizing discrete diffusion model sampling via τ-leaping algorithm in CTMC framework for faster generation.

Ax Okba Bekhelifi, Naoual El Djouher Mebtouche 11d ago

Which Metric Reflects the Spelling Rate Accuracy in Event-Related Potential-Based Brain-Computer Interfaces?

arXiv paper on metrics for ERP-based brain-computer interfaces focusing on spelling rate accuracy.

Ax Jinwen Wang, Youfang Lin, Xiaobo Hu, Qian Xu, Shuo Wang, Zhuo Chen, Kai Lv 11d ago

Task-Relevant Representation Decoupling for Visual Reinforcement Learning Generalization

arXiv paper proposing task-relevant representation decoupling for visual RL to improve generalization across environments.

Ax Jinwen Wang, Youfang Lin, Xiaobo Hu, Shuo Wang, Kai Lv 11d ago

Local Motion Matters: A Deconstruct-Recompose Paradigm for Reinforcement Learning Pre-training from Videos

arXiv paper on RL pre-training from videos using local motion patterns for better transfer across different agent morphologies.

Ax Jinwen Wang, Youfang Lin, Xiaobo Hu, Siyu Yang, Sheng Han, Shuo Wang, Kai Lv 11d ago

From Pixels to Temporal Correlations: Learning Informative Representations for Reinforcement Learning Pre-training

Unsupervised pre-training method for RL using temporal correlations from large-scale video datasets to improve sample efficiency.