Isolater - Feed

Ax Erin Tan, Judy Hanwen Shen, Irene Y. Chen 27d ago

Investigating Data Interventions for Subgroup Fairness: An ICU Case Study

Study of data intervention techniques for improving fairness across demographic subgroups in ICU prediction models using real healthcare data.

Ax Maria Chzhen, Priya L. Donti 27d ago

Improving Feasibility via Fast Autoencoder-Based Projections

Data-driven approach using trained autoencoders as fast projectors to enforce complex nonconvex operational constraints in learning and control systems.

Ax Jesse Geneson, Kuldeep Singh, Alexander Wang 27d ago

Online learning of smooth functions on $\mathbb{R}$

Theoretical analysis of adversarial online learning for smooth real-valued functions on ℝ with cumulative p-loss bounds.

Ax Benjamin S. Knight, Ahsaas Bajaj 27d ago

Choosing the Right Regularizer for Applied ML: Simulation Benchmarks of Popular Scikit-learn Regularization Frameworks

Empirical survey comparing regularization frameworks (Ridge, Lasso, ElasticNet, Post-Lasso) across 134,400 simulations with historical development context.

Ax Philipp Seitz, Jan Schmitt, Andreas Schiffler 27d ago

Evaluation of Bagging Predictors with Kernel Density Estimation and Bagging Score

Method for evaluating bagged neural network predictions using kernel density estimation to select representative predictions in nonlinear regression.

Ax Kitsuya Azuma, Takayuki Nishio 27d ago

BlazeFL: Fast and Deterministic Federated Learning Simulation

BlazeFL: lightweight federated learning simulation framework enabling fast, deterministic training of hundreds or thousands virtual clients on single node.

Ax Qusay Muzaffar, David Levin, Michael Werman 27d ago

Neural Global Optimization via Iterative Refinement from Noisy Samples

Neural approach for black-box global optimization from noisy samples using iterative refinement to avoid local minima in multi-modal functions.

Ax Jongsoo Lee, Jangwon Kim, Soohee Han 27d ago

Delayed Homomorphic Reinforcement Learning for Environments with Delayed Feedback

Reinforcement learning approach for handling delayed feedback by replacing state augmentation with homomorphic methods to reduce sample complexity.

Ax Jonathan Katzy, Razvan-Mihai Popescu, Erik Mekkes, Arie van Deursen, Maliheh Izadi 27d ago

Automated Attention Pattern Discovery at Scale in Large Language Models

Mechanistic interpretability method for discovering repeated attention patterns in large language models at scale without resource-intensive controlled settings.

Ax Renzo G. Soatto, Anders Hoel, Greycen Ren, Shorna Alam, Stephen Bates, Nikolaos P. Daskalakis, Caroline Uhler, Maria Skoularidou 27d ago

CountsDiff: A Diffusion Model on the Natural Numbers for Generation and Imputation of Count-Based Data

CountsDiff: diffusion model framework for generating and imputing count-based discrete ordinal data using survival probability schedules.

Ax Haocheng Ju, Guoxiong Gao, Jiedong Jiang, Bin Wu, Zeming Sun, Leheng Chen, Yutong Wang, Yuefeng Wang, Zichen Wang, Wanyi He, Peihao Wu, Liang Xiao, Ruochuan Liu, Bryan Dai, Bin Dong 27d ago

Automated Conjecture Resolution with Formal Verification

Framework for automated mathematical conjecture resolution combining LLMs with formal verification to improve reliability of research-level mathematical problem solving.

Ax Dipkumar Patel 27d ago

Representational Collapse in Multi-Agent LLM Committees: Measurement and Diversity-Aware Consensus

Research on representational collapse in multi-agent LLM committees using majority voting, measuring agent diversity via cosine similarity and effective rank on mathematical reasoning tasks.

Ax Jonas De Schouwer, Haitz S\'aez de Oc\'ariz Borde, Xiaowen Dong 27d ago

k-Maximum Inner Product Attention for Graph Transformers and the Expressive Power of GraphGPS The Expressive Power of GraphGPS

k-Maximum inner product attention for graph transformers addressing quadratic complexity while maintaining expressive power of GraphGPS.

Ax Giansalvo Cirrincione, Rahul Ranjeev Kumar 27d ago

Collapse-Free Prototype Readout Layer for Transformer Encoders

DDCL-Attention: Prototype-based readout layer for transformer encoders using soft probabilistic token matching for compact summaries.

Ax Daniel Agyapong, Julien Chiquet, Jane Marks, Toby Dylan Hocking 27d ago

Understanding When Poisson Log-Normal Models Outperform Penalized Poisson Regression for Microbiome Count Data

Empirical comparison of Poisson log-normal models vs penalized Poisson regression for microbiome count data prediction.

Ax Dharmesh Tailor, Nicol\`o Felicioni, Kamil Ciosek 27d ago

A Bayesian Information-Theoretic Approach to Data Attribution

Bayesian information-theoretic approach to training data attribution for tracing model predictions to influential training examples.

Ax Soham Gadgil, Chris Lin, Su-In Lee 27d ago

Where to Steer: Input-Dependent Layer Selection for Steering Improves LLM Alignment

Method for input-dependent layer selection in steering vectors to improve LLM alignment at inference time, adapting intervention layer per input.

Ax Xiwen Chen, Jingjing Wang, Wenhui Zhu, Peijie Qiu, Xuanzhao Dong, Hejian Sang, Zhipeng Wang, Alborz Geramifard, Feng Luo 27d ago

SODA: Semi On-Policy Black-Box Distillation for Large Language Models

SODA: Semi on-policy knowledge distillation method for LLMs balancing off-policy simplicity with on-policy effectiveness without adversarial training instability.

Ax Robin Young, Srinivasan Keshav 27d ago

Spatiotemporal Interpolation of GEDI Biomass with Calibrated Uncertainty

Spatiotemporal interpolation method for NASA GEDI satellite biomass data with uncertainty quantification for deforestation monitoring.

Ax Indar Kumar, Akanksha Tiwari 27d ago

Regime-Calibrated Demand Priors for Ride-Hailing Fleet Dispatch and Repositioning

Ride-hailing demand forecasting using regime-calibrated priors and demand segmentation for fleet dispatch optimization.

Ax Yaoze Guo, Shana Moothedath 27d ago

Provable Multi-Task Reinforcement Learning: A Representation Learning Framework with Low Rank Rewards

Theoretical research on multi-task representation learning for reinforcement learning with shared representations across related RL tasks with different rewards.

Ax M Jawad, HV Gupta, YH Wang, MA Farmani, A Behrangi, GY Niu 27d ago

Improving Model Performance by Adapting the KGE Metric to Account for System Non-Stationarity

ML research on adapting KGE metric for geoscientific systems with temporal non-stationarity in water management and climate variability modeling.

Ax Aniketh Iyengar, Jiaqi Han, Pengwei Sun, Mingjian Jiang, Jianwen Xie, Stefano Ermon 27d ago

Align Your Structures: Generating Trajectories with Structure Pretraining for Molecular Dynamics

Framework combining structure pretraining with diffusion models for generating molecular dynamics trajectories with limited MD data.

Ax Hui Sun, Yun-Ji Zhang, Zheng Xie, Ren-Biao Liu, Yali Du, Xin-Ye Li, Ming Li 27d ago

ACES: Who Tests the Tests? Leave-One-Out AUC Consistency for Code Generation

ACES: method for selecting LLM-generated code using LLM-generated tests via leave-one-out AUC consistency without determining test correctness.

Ax Indar Kumar, Girish Karhana, Sai Krishna Jasti, Ankit Hemant Lade 27d ago

Supervised Dimensionality Reduction Revisited: Why LDA on Frozen CNN Features Deserves a Second Look

Title mismatch: discusses ride-hailing demand forecasting with regime-calibrated similarity ensemble, not dimensionality reduction on CNN features.

Ax Yifu Ding, Xinhao Zhang, Jinyang Guo 27d ago

Diagonal-Tiled Mixed-Precision Attention for Efficient Low-Bit MXFP Inference

Low-bit mixed-precision attention kernel using MXFP for efficient transformer inference with reduced memory bandwidth.

Ax Yifu Ding, Xianglong Liu, Shenghao Jin, Jinyang Guo, Jiwen Lu 27d ago

BWTA: Accurate and Efficient Binarized Transformer by Algorithm-Hardware Co-design

BWTA: binarized transformer quantization scheme with ternary activations and algorithm-hardware co-design for efficient inference.

Ax Arash Sarshar 27d ago

Multirate Stein Variational Gradient Descent for Efficient Bayesian Sampling

Multirate Stein variational gradient descent optimizing different step sizes for attraction and repulsion in Bayesian sampling.

Ax Momoka Iida, Hayato Motohashi, Hirotaka Takahashi 27d ago

Autoencoder-Based Parameter Estimation for Superposed Multi-Component Damped Sinusoidal Signals

Autoencoder method for parameter estimation of superposed damped sinusoidal signals in physical systems.

Ax Shenzhi Yang, Guangcheng Zhu, Bowen Song, Sharon Li, Haobo Wang, Xing Zheng, Yingfan Ma, Zhongqi Chen, Weiqiang Wang, Gang Chen 27d ago

Can LLMs Learn to Reason Robustly under Noisy Supervision?

Analysis of LLM reasoning models under noisy labels in reinforcement learning with verifiable rewards, identifying label noise vulnerabilities.

Ax Ozgur Yilmaz 27d ago

ArrowFlow: Hierarchical Machine Learning in the Space of Permutations

ArrowFlow: novel ML architecture operating in permutation space using ranking filters and permutation-matrix updates without gradients.

Ax Xuelin Zhang, Hong Chen, Bin Gu, Tieliang Gong, Feng Zheng 27d ago

Fine-grained Analysis of Stability and Generalization for Stochastic Bilevel Optimization

Generalization analysis of stochastic bilevel optimization with applications to hyperparameter optimization, meta-learning, and RL.

Ax Milo Coombs 27d ago

Spectral Path Regression: Directional Chebyshev Harmonics for Interpretable Tabular Learning

Spectral Path Regression using directional Chebyshev harmonics for interpretable learning on tabular data without exponential scaling.

Ax Nida Zamir, I-Hong Hou 27d ago

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

Index policy for restless multi-armed bandits under individual penalty constraints for wireless resource allocation.

Ax Ziye Yu, Yuqi Cai, Xin Liu 27d ago

Physical Sensitivity Kernels Can Emerge in Data-Driven Forward Models: Evidence From Surface-Wave Dispersion

Neural network surrogates for geophysics recover physical sensitivity kernels through gradient analysis on surface-wave dispersion.

Ax Prashant C. Raju 27d ago

The Geometric Alignment Tax: Tokenization vs. Continuous Geometry in Scientific Foundation Models

Analysis of geometric alignment cost in scientific foundation models for biology/physics, showing discrete tokenization degrades continuous geometry preservation.

Ax Qian Zhou, Yuanyun Zhang, Shi Li 27d ago

Uncertainty-Aware Foundation Models for Clinical Data

Framework for uncertainty-aware foundation models on clinical data, addressing incomplete and irregular measurements in healthcare.

Ax Gabriel Diaz Ramos, Lorenzo Luzi, Debshila Basu Mallick, Richard Baraniuk 27d ago

Stable and Privacy-Preserving Synthetic Educational Data with Empirical Marginals: A Copula-Based Approach

Copula-based method for generating synthetic educational data that preserves marginal distributions while protecting student privacy.

Ax Haonian Ji, Kaiwen Xiong, Siwei Han, Peng Xia, Shi Qiu, Yiyang Zhou, Jiaqi Liu, Jinlong Li, Bingzhou Li, Zeyu Zheng, Cihang Xie, Huaxiu Yao 27d ago

ClawArena: Benchmarking AI Agents in Evolving Information Environments

ClawArena benchmark for evaluating AI agents in dynamic environments with evolving information, contradictions, and implicit user feedback.

Ax Muhammad Rizwan Awan, Volker Pickert, Muhammad Waqar Ashraf, Saleh Ali, Farshid Mahmouditabar, Shafiq Odhano 27d ago

Towards Agentic Defect Reasoning: A Graph-Assisted Retrieval Framework for Laser Powder Bed Fusion

Graph-assisted retrieval framework for reasoning about defects in laser powder bed fusion manufacturing using structured scientific knowledge.

Ax Aniruddh G. Puranic, Sebastian Schirmer, John S. Baras, Calin Belta 27d ago

Learning from Imperfect Demonstrations via Temporal Behavior Tree-Guided Trajectory Repair

Framework using Temporal Behavior Trees to repair suboptimal trajectories before using them for robot control policy learning.

Ax Charafeddine Mouzouni 27d ago

Three Phases of Expert Routing: How Load Balance Evolves During Mixture-of-Experts Training

Analysis of token routing in Mixture-of-Experts models reveals three-phase training trajectory for load balance evolution.

Ax Yancheng Huang, Changsheng Wang, Chongyu Fan, Yicheng Lang, Bingqi Shang, Yang Zhang, Mingyi Hong, Qing Qu, Alvaro Velasquez, Sijia Liu 27d ago

Subspace Control: Turning Constrained Model Steering into Controllable Spectral Optimization

Method for constrained model steering of LLMs addressing safety/privacy requirements via spectral subspace optimization.

Ax Sajad Ghawami 27d ago

Good Rankings, Wrong Probabilities: A Calibration Audit of Multimodal Cancer Survival Models

Calibration audit of multimodal cancer survival models fusing histopathology images with genomic data.

Ax Suzan Kagan, Shira Spigelman, Sankar Sudhir, Thalappil Pradeep, Hadas Mamane 27d ago

Peoples Water Data: Enabling Reliable Field Data Generation and Microbial Contamination Screening in Household Drinking Water

Two-stage ML framework predicting E. coli presence in household drinking water for microbial contamination screening.

Ax Wenhao Chi, \c{S}. \.Ilker Birbil 27d ago