Ax Arpit Agarwal, Rohan Ghuge, Viswanath Nagarajan, Zhengjia Zhuo 12d ago

Semi-Bandit Learning for Monotone Stochastic Optimization

Semi-bandit learning approach for monotone stochastic optimization without full probability distribution knowledge.

Ax Sheila Schoepp, Mehran Taghian, Shotaro Miwa, Yoshihiro Mitsuka, Shadan Golestan, Osmar Za\"iane 12d ago

Enhancing Hardware Fault Tolerance in Machines with Reinforcement Learning Policy Gradient Algorithms

Compares PPO and SAC reinforcement learning algorithms for fault tolerance in autonomous machines.

Ax Martin Surner, Abdelmajid Khelil, Ludwig Bothmann 12d ago

Invariance Pair Guidance: Robustness to Spurious Correlations via Corrective Gradients

Invariance Pair Guidance improves robustness to spurious correlations through corrective gradients without dense labels.

Ax Sanghyuk Chun, Olga Russakovsky 12d ago

Multiplicity is an Inevitable and Inherent Challenge in Multimodal Learning

Studies inherent many-to-many multiplicity in multimodal learning relationships beyond deterministic alignment.

Ax Davide D'Ascenzo, Sebastiano Cultrera di Montesano 12d ago

scDataset: Scalable Data Loading for Deep Learning on Large-Scale Single-Cell Omics

scDataset provides scalable data loading for deep learning on large-scale single-cell genomics datasets.

Ax Tao Feng, Haozhen Zhang, Zijie Lei, Pengrui Han, Mostofa Patwary, Mohammad Shoeybi, Bryan Catanzaro, Jiaxuan You 12d ago

FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data

FusionFactory fuses capabilities of multiple LLMs using multi-LLM log data for improved performance.

Ax Claudio Giusti, Luca Guarnera, Mirko Casu, Sebastiano Battiato 12d ago

Fraud is Not Just Rarity: A Causal Prototype Attention Approach to Realistic Synthetic Oversampling

Causal prototype attention approach for synthetic oversampling in credit card fraud detection.

Ax Tuan Nguyen, Sze Jue Yang, Khoa D. Doan, Chee Seng Chan, Kok-Seng Wong 12d ago

FLAT: Revealing Hidden Latent-Conditioned Backdoor Failures in Federated Learning

FLAT reveals hidden backdoor failures in federated learning through latent-conditioned reliability stress testing.

Ax YongKyung Oh, Dong-Young Lim, Sungil Kim, Alex Bui 12d ago

TANDEM: Temporal Attention-guided Neural Differential Equations for Missingness in Time Series Classification

TANDEM uses neural differential equations with temporal attention for time series classification with missing data.

Ax Zhanting Zhou, Zeyu Ma, Ziqiang Zheng, Yang Yang 12d ago

FedIA: Importance-Aware Aggregation for Domain-Robust Federated Graph Learning

FedIA improves federated graph learning through importance-aware aggregation on distributed social media networks.

Ax Woosung Koh, Juyoung Suk, Sungjun Han, Se-Young Yun, Jamin Shin 12d ago

Predicting LLM Reasoning Performance with Small Proxy Model

rBridge predicts reasoning performance of large LLMs using small proxy models under 1B parameters.

Ax Liangyu Ding, Guokai Li, Zizhuo Wang, Chenghan Wu 12d ago

Self-Improving Neural Pruning: A Graph Neural Network Framework for Scalable Mixed Bundle Pricing

Graph neural network approach for solving mixed bundle pricing problems in revenue management.

Ax Donald Shenaj, Ondrej Bohdal, Taha Ceritli, Mete Ozay, Pietro Zanuttigh, Umberto Michieli 12d ago

K-Merge: Online Continual Merging of Adapters for On-device Large Language Models

K-Merge enables online merging of LoRA adapters for efficient on-device LLM deployment with limited storage.

Ax David Kattermann, Lothar Sebastian Krapp 12d ago

Recursively Enumerably Representable Classes and Computable Versions of the Fundamental Theorem of Statistical Learning

Studies computable PAC learning and derives analogs of the Fundamental Theorem of Statistical Learning in the computable setting.

Ax YongKyung Oh, Dong-Young Lim, Sungil Kim 12d ago

FlowPath: Learning Data-Driven Manifolds with Invertible Flows for Robust Irregularly-sampled Time Series Classification

FlowPath: invertible flow-based method for learning manifolds from irregularly-sampled time series, improving neural controlled differential equations robustness.

Ax Michael S. Zhang, Rishi A. Ruia, Arnav Kewalram, Saathvik Dharmapuram, Utkarsh Sharma, Kevin Zhu 12d ago

When Less is More: 8-bit Quantization Improves Continual Learning in Large Language Models

Analysis showing 8-bit quantization unexpectedly improves continual learning in LLMs compared to FP16, reducing catastrophic forgetting with replay buffers.

Ax Pengfei Qu, Wenyu Ouyang, Chi Zhang, Yikai Chai, Shuolong Xu, Lei Ye, Yongri Piao, Miao Zhang, Huchuan Lu 12d ago

Utilizing Earth Foundation Models to Enhance the Simulation Performance of Hydrological Models with AlphaEarth Embeddings

Study using AlphaEarth foundation model embeddings from satellite imagery to improve hydrological river flow prediction in data-sparse regions.

Ax Shahbaz Alvi, Giusy Fedele, Gabriele Accarino, Italo Epicoco, Ilenia Manco, Pasquale Schiano 12d ago

OpFML: Pipeline for ML-based Operational Inference

OpFML pipeline for operationalizing ML-based climate and Earth science models with data acquisition, preprocessing, and failure handling infrastructure.

Ax Egor Cherepanov, Daniil Zelezetsky, Alexey K. Kovalev, Aleksandr I. Panov 12d ago

KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning

KAGE-Bench: JAX-native benchmark for systematically evaluating RL agent visual generalization by independently controlling observation distribution shifts.

Ax Jinju Park, Seokho Kang 12d ago

PaAno: Patch-Based Representation Learning for Time-Series Anomaly Detection

PaAno: lightweight patch-based representation learning for time-series anomaly detection, outperforming large transformer models on constrained hardware.

Ax Egor Serov, Ilya Kuleshov, Alexey Zaytsev 12d ago

Efficient Neural Controlled Differential Equations via Attentive Kernel Smoothing

Attentive kernel smoothing approach for efficient Neural Controlled Differential Equations, reducing function evaluations via smoother path construction.

Ax Karthik Elamvazhuthi, Shiba Biswal, Kian Rosenblum, Arushi Katyal, Tianli Qu, Grady Ma, Rishi Sonthalia 12d ago

Geometry-Preserving Neural Architectures on Manifolds with Boundary

Unified framework for geometry-preserving neural architectures on manifolds with boundary, organizing constraint enforcement strategies.

Ax Daniel Geyfman, Felix Draxler, Jan Groeneveld, Hyunsoo Lee, Theofanis Karaletsos, Stephan Mandt 12d ago

Calibrated Test-Time Guidance for Bayesian Inference

Analysis of test-time guidance in diffusion models showing common methods miscalibrate Bayesian inference; proposes correction for posterior sampling.

Ax Aviral Chawla, Galen Hall, Juniper Lovato 12d ago

MetaOthello: A Controlled Study of Multiple World Models in Transformers

MetaOthello controlled study examining how transformers organize multiple world models across different generative processes using Othello game variants.

Ax Theo X. Olausson, Jo\~ao Monteiro, Michal Klein, Marco Cuturi 12d ago

Amortized Maximum Inner Product Search with Learned Support Functions

Amortized maximum inner product search: neural networks trained to directly predict MIPS solutions, amortizing costs for repeated queries on fixed databases.

Ax Sebastian Frey, Edoardo Beccari, Maximilian Kranz, Nicol\`o Alberto Pellizzari, Ali Mete Karaman, Qiwei Han, Maximilian Kaiser 12d ago

Competition-Aware CPC Forecasting with Near-Market Coverage

Cost-per-click forecasting for Google Ads using competition-aware proxies from keyword data and market landscape analysis.

Ax Jiayuan Du, Yuebing Song, Yiming Zhao, Xianghui Pan, Jiawei Lian, Yuchu Lu, Liuyi Wang, Chengju Liu, Qijun Chen 12d ago

Deconfounded Lifelong Learning for Autonomous Driving via Dynamic Knowledge Spaces

DeLL framework for lifelong learning in autonomous driving using Dirichlet process mixture models and front-door causal adjustment to address catastrophic forgetting.

Ax Hyunji Nam, Haoran Li, Natasha Jaques 12d ago

Maximizing Mutual Information Between Prompt and Response Improves LLM Performance With No Additional Data

Self-improvement framework maximizing mutual information between prompts and LLM responses without additional labeled data or external verifiers.

Ax Lala Shakti Swarup Ray, Mengxi Liu, Alcina Pinto, Deepika Gurung, Daniel Geissler, Paul Lukowoicz, Bo Zhou 12d ago

ActivityNarrated: An Open-Ended Narrative Paradigm for Wearable Human Activity Understanding

ActivityNarrated dataset for open-ended narrative-based human activity recognition from wearables, replacing fixed-window classification benchmarks.

Ax Tin Had\v{z}i Veljkovi\'c, Joshua Rosenthal, Ivor Lon\v{c}ari\'c, Jan-Willem van de Meent 12d ago

Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

Crystalite: lightweight diffusion transformer for crystal material modeling using subatomic tokenization and equivariant inductive biases.

Ax Yiping Li, Zhiyu An, Wan Du 12d ago

When Less Latent Leads to Better Relay: Information-Preserving Compression for Latent Multi-Agent LLM Collaboration

Orthogonal BackFill method for compressing KV-cache communication in multi-agent LLM systems, reducing memory and communication costs while preserving information.

Ax Yangyue Wang, Harshvardhan Sikka, Yash Mathur, Tony Zhou, Jinu Nyachhyon, Pranav Guruprasad 12d ago

GUI-Perturbed: Domain Randomization Reveals Systematic Brittleness in GUI Grounding Models

GUI-Perturbed framework reveals brittleness in GUI grounding models through domain randomization, showing 27-56% accuracy drops on spatial reasoning tasks.

Ax Minhak Song, Liang Zhang, Bingcong Li, Niao He, Michael Muehlebach, Sewoong Oh 12d ago

Zeroth-Order Optimization at the Edge of Stability

Zeroth-order optimization methods for gradient-free black-box learning and memory-efficient LLM fine-tuning, analyzing stability dynamics.

Ax Sajjad Ghiasvand, Mark Beliaev, Mahnoosh Alizadeh, Ramtin Pedarsani 12d ago

REALM: Reliable Expertise-Aware Language Model Fine-Tuning from Noisy Annotations

REALM method for fine-tuning LLMs with noisy crowdsourced annotations by jointly learning model parameters and annotator expertise weights.

Ax Changyu Li, Shuanghong Huang, Jiashen Liu, Ming Lei, Jidu Xing, Kaishun Wu, Lu Wang, Fei Luo 12d ago

FED-FSTQ: Fisher-Guided Token Quantization for Communication-Efficient Federated Fine-Tuning of LLMs on Edge Devices

Fisher-guided token quantization reduces communication overhead in federated fine-tuning of LLMs on edge devices.

Ax Hongmin Li 12d ago

FastUMAP: Scalable Dimensionality Reduction via Bipartite Landmark Sampling

FastUMAP landmark-based dimensionality reduction method optimized for repeated analysis with changing hyperparameters.

Ax Qijun Hou, Yuchen Shi, Pingyi Fan, Khaled B. Letaief 12d ago

Federated Client Selection under Partial Visibility: A POMDP Approach with Spatio-Temporal Attention

POMDP approach with spatio-temporal attention for federated learning client selection under partial visibility constraints.

Ax Markus Herre, Andrej Tschalzev, Sascha Marton, Christian Bartelt 12d ago

Explaining Tabular Foundation Model Differences Through Meta-Features

Meta-feature analysis explains performance gaps between tabular foundation models and traditional models on prediction tasks.

Ax Sasan Vakili, Dani\"el Woonings, Pradyumna Paruchuri, Peyman Mohajerin Esfahani 12d ago

Nonlinear Bayesian Estimator for Parameter Learning: A Fixed-Point Characterization

Fixed-point architecture for nonlinear Bayesian parameter estimation in Wiener-type state-space models using dynamic basis statistics.

Ax Luca Zhou 12d ago

Tail-Shape Estimation in LLM Evaluation Is Fragile: A Protocol for Diagnosing False Positives

Protocol for diagnosing false positives in tail-aware LLM evaluation metrics beyond mean-based assessment.

Ax Yingshuo Wang, Xian Sun, Lingdong Kong, Wei Gao, Yanhang Li, Zhichao Fan, Zexin Zhuang 12d ago

Do Time Series Foundation Model Benchmarks Hide Regime-Dependent Failures? Evidence from Traffic Speed Forecasting

Regime-stratified evaluation reveals hidden failures in time series foundation models masked by standard aggregate metrics.

Ax Borui Cai, Yao Zhao 12d ago

Topological Neural Dynamics: A Neuron-wise Framework for Sequence Modeling

Neuron-wise sequence modeling framework allowing independent evolution of neurons instead of layer-wise shared dynamics.

Ax Julio Gonz\'alez-D\'iaz, Beatriz Pateiro-L\'opez, Iria Rodr\'iguez-Acevedo 12d ago

A new classification method based on Minimum Spanning Trees

Classification algorithm based on Minimum Spanning Trees with robust variant for improved performance.

Ax Navin Bondade 12d ago

Inverse Reinforcement Learning for Interpretable Keystroke Biomarkers in Parkinson's Disease

Applies inverse reinforcement learning to keystroke dynamics for interpretable Parkinson's disease biomarker extraction.

Ax Muhammad Ahmed 12d ago

PersistentKV: Page-Aware Decode Scheduling for Long-Context LLM Serving on Commodity GPUs

PersistentKV optimizes decode scheduling for long-context LLM serving on GPUs through page-aware KV cache management.

Ax Andrew C. Cullen, Neil G. Marchant, Jiani Xie, Paul Montague, Benjamin I. P. Rubinstein 12d ago

What Was That Again? Certified Robustness for Automatic Speech Recognition

Certification-inspired mechanisms improve robustness and reduce word error rate in automatic speech recognition systems.

Ax Rajat Ghosh, Datta Nimmaturi, Aryan Singhal, Vaishnavi Bhargava, Henry Wong, Johnu George, Debojyoti Dutta 12d ago

Predictable GRPO: A Closed-Form Model of Training Dynamics

Closed-form reduced-order model of GRPO training dynamics using mean-field approximation and stochastically-forced oscillator analogy.

Ax Rui Zhou, Tianci Xie 12d ago

Fora: From Weight-Space to Function-Space Protection in Capability-Preserving Fine-Tuning

Fora protects LLM capabilities during fine-tuning by preserving activation subspaces rather than just parameter distances.

Ax Abhishek Dey 12d ago

ComplianceGate: Classifier-Gated Multi-Tier LLM Routing for Inference in Regulated Industries

ComplianceGate routes LLM queries through multi-tier classifier system for compliance enforcement and cost efficiency in regulated industries.

Ax Kung-Ming Lan, Edward Huang 12d ago

Beyond the Expressivity-Trainability Paradox: A Dynamical Lie Algebra Perspective on Navigating Barren Plateaus in Quantum Machine Learning

Analysis of barren plateaus in quantum machine learning using Lie algebra perspective to address expressivity-trainability tradeoffs.