Ax Krzysztof Choromanski, Avinava Dubey, Arijit Sehanobish, Isaac Reid 19d ago

Computationally-efficient Graph Modeling with Refined Graph Random Features

GRFs++: refined graph random features with walk-stitching for efficient kernel computations on graph-structured data.

Ax Mingyang Lyu, Yinqian Sun, Erliang Lin, Huangrui Li, Ruolin Chen, Feifei Zhao, Yi Zeng 19d ago

Reinforcement Fine-Tuning of Flow-Matching Policies for Vision-Language-Action Models

Reinforcement fine-tuning of flow-matching Vision-Language-Action models through online interaction, improving performance beyond supervised data.

Ax Wenqian Weng, Yi He, Xingyu Zhou 19d ago

Improved Bounds for Private and Robust Alignment

Theoretical bounds on private and robust alignment of language models under privacy constraints and adversarial corruption.

Ax Lecheng Yan, Ruizhe Li, Guanhua Chen, Qing Li, Jiahui Geng, Wenxi Li, Longyue Wang, Chenyang Lyu 19d ago

Spurious Rewards Paradox: Mechanistically Understanding How RLVR Activates Memorization Shortcuts in LLMs

Investigation of spurious rewards paradox in RLVR for LLMs: models bypass reasoning when trained with incorrect rewards, identified via perplexity divergence.

Ax Haonan Yang, Jianchao Tang, Zhuo Li 19d ago

Dual-Prototype Disentanglement: A Context-Aware Enhancement Framework for Time Series Forecasting

Dual-Prototype Disentanglement framework for context-aware time series forecasting by dynamically separating temporal patterns.

Ax Ionut-Vlad Modoranu, Philip Zmushko, Erik Schultheis, Mher Safaryan, Dan Alistarh 19d ago

DASH: Faster Shampoo via Batched Block Preconditioning and Efficient Inverse-Root Solvers

DASH optimizer: faster Shampoo implementation via batched block preconditioning and efficient inverse-root solvers for second-order optimization.

Ax Julien Siems, Riccardo Grazzi, Korbinian P\"oppel, Kirill Kalinin, Hitesh Ballani, Babak Rahmani 19d ago

Learning State-Tracking from Code Using Linear RNNs

Linear RNNs trained on code for state-tracking tasks, bridging sequence-to-sequence learning with next-token prediction in language models.

Ax Xu Zhang, Qitong Wang, Peng Wang, Wei Wang 19d ago

SEMixer: Semantics Enhanced MLP-Mixer for Multiscale Mixing and Long-term Time Series Forecasting

SEMixer: MLP-Mixer architecture with random attention for multiscale time series forecasting, addressing redundancy and noise in temporal data alignment.

Ax Irene Iele, Giulia Romoli, Daniele Molino, Elena Mulero Ayll\'on, Filippo Ruffini, Paolo Soda, Matteo Tortora 19d ago

Probabilistic NDVI Forecasting from Sparse Satellite Time Series and Weather Covariates

Probabilistic forecasting framework for NDVI vegetation dynamics from sparse satellite data with weather covariates for precision agriculture applications.

Ax Tom Potter, Oliver Rhodes 19d ago

Learning Long-Range Dependencies with Temporal Predictive Coding

Temporal Predictive Coding improved for learning long-range dependencies in recurrent systems on neuromorphic hardware through better credit assignment mechanisms.

Ax Mingi Kim, Yongjun Kim, Jungwoo Kang, Hyungki Kim 19d ago

BrepCoder: A Unified Multimodal Large Language Model for Multi-task B-rep Reasoning

BrepCoder is a multimodal LLM for CAD tasks using B-rep format instead of point clouds/images, enabling unified multi-task reasoning without task-specific modifications.

Ax Jeffrey D. Varner 19d ago

Training-Free Generation of Protein Sequences from Small Family Alignments via Stochastic Attention

Training-free protein sequence generation using stochastic attention on small sequence alignments.

Ax Raphael Simon, Jos\'e Carrasquel, Wim Mees, Pieter Libin 19d ago

NASimJax: A GPU-Accelerated Policy Learning Framework for Penetration Testing

NASimJax: GPU-accelerated RL framework for training penetration testing agents with realistic network simulation.

Ax Mark Braverman, Roi Livni, Yishay Mansour, Shay Moran, Kobbi Nissim 19d ago

Learning from Equivalence Queries, Revisited

Learning framework for evolving models through user interaction queries; theoretical foundations for deployed systems.

Ax Augustin Chan 19d ago

Statistical Properties of the King Wen Sequence: An Anti-Habituation Structure That Does Not Improve Neural Network Training

Statistical analysis of I-Ching sequence properties; not practically relevant to AI/ML systems.

Ax Keyang Chen, Mingxuan Jiang, Yongsheng Zhao, Zeping Li, Zaiyuan Chen, Weiqi Luo, Zhixin Li, Sen Liu, Yinan Jing, Guangnan Ye, Xihong Wu, Hongfeng Chai 19d ago

TransXion: A High-Fidelity Graph Benchmark for Realistic Anti-Money Laundering

TransXion benchmark for anti-money laundering detection using realistic transaction graph datasets.

Ax Sofianos Panagiotis Fotias, Vassilis Gaganis 19d ago

Closed-Loop CO2 Storage Control With History-Based Reinforcement Learning and Latent Model-Based Adaptation

Deep reinforcement learning for CO2 storage control with latent model adaptation under partial observability.

Ax Emma Leonhart 19d ago

Sutra: Tensor-Op RNNs as a Compilation Target for Vector Symbolic Architectures

Sutra: compiler for vector symbolic architectures that targets PyTorch neural networks with tensor operation fusion.

Ax Stefan Huber, Hannes Unger, Georg Sch\"afer, Jakob Rehrl 19d ago

Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks

Analytical solution to Mountain Car problem revealing optimal control simplicity and introducing Chebyshev policies as universal RL policy class.

Ax Ziyan Chen, Zhongzhu Zhou, Ding-Xuan Zhou 19d ago

From One-Pass SGD to Data Reuse: Mini-Batch Scaling Laws in Sketched Linear Regression

Theoretical analysis of mini-batch scaling laws in sketched linear regression across single-pass and multi-pass SGD settings.

Ax Daria Grushina, Kseniia Kuvshinova, Alina Kostromina, Aziz Temirkhanov, Mile Mitrovic, Dmitry Simakov 19d ago

LLMTabBench: Evaluating LLMs on Binary Tabular Classification From Zero to Few Shots

Benchmark evaluating LLM zero- and few-shot performance on binary tabular classification without labeled context examples.

Ax Vadim Porvatov, Andrey Dukhovny, Andrey Lange 19d ago

How Many Trees in a Random Forest? A Revisited Approach with Plateau Search and Optuna Integration

Hyperparameter optimization method for Random Forest using plateau search and Optuna to determine optimal number of trees.

Ax Damian Lebied\'z, Robert \'Slepaczuk 19d ago

Dynamic Multi-Pair Trading Strategy in Cryptocurrency Markets with Deep Reinforcement Learning

Deep reinforcement learning overlay for pair trading strategy in cryptocurrency markets with high volatility adaptation.

Ax Yunbei Xu 19d ago

Bellman-sufficient Information Complexity

Formal framework for sequential decision making based on Bellman-sufficient state representations and information complexity.

Ax Yash Vardhan Tomar, Dheeraj Peddireddy 19d ago

SymQNet: Amortized Acquisition for Low-Latency Adaptive Hamiltonian Learning

Amortized reinforcement learning approach for low-latency adaptive Hamiltonian learning in quantum device calibration.

Ax Mykola Vysotskyi, Runqi Lin, Grzegorz Biziel, Michal Zakrzewski, Sebastian Montagna, Damian Rynczak, Shreyansh Padarha, Kumail Alhamoud, Zihao Fu, William Lugoloobi, Kai Rawal, Hanna Yershova, Xander Davies, Taras Rumezhak, Guohao Li, Fazl Barez, Baoyuan Wu, Arkadiusz Drohomirecki, Yarin Gal, Chris Russell, Christopher Summerfield, Adam Mahdi, Volodymyr Karpiv, Philip Torr, Adel Bibi 19d ago

Running the Gauntlet: Re-evaluating the Capabilities of Agents Beyond Familiar Environments

Benchmark for evaluating AI agent capabilities across diverse environments beyond common applications, addressing limitations of saturated performance on existing benchmarks.

Ax Baijia Zhang, Yining Huang 19d ago

When to Write and When to Suppress: Route-Specialized Dual Adapters for Memory-Assisted Knowledge Editing

Parameter-efficient adapter approach for knowledge editing in LLMs using memory retrieval and dual routing mechanisms to update facts while preserving model behavior.

Ax Chih-Duo Hong, Yen-Pang Chen, Fang Yu 19d ago

Signature filtering: a lightweight enhancement for statistical watermark detection in large language models

Signature filtering module enhances statistical watermark detection in LLM outputs without modifying generation or embedding.

Ax Nathaniel Jeffries, Miriam Wolff, Sam Royston, Elizabeth Healey, Caleb Mayer, David Klonoff, Michael Snyder, Tao Wang 19d ago

MetaboNet-Bench: A Multi-modal Benchmark for Glucose Forecasting in Type 1 Diabetes

Benchmark dataset and evaluation framework for glucose forecasting algorithms in type 1 diabetes management.

Ax Linara Adilova, Henning Petzka, Asja Fischer, Bernhard C. Geiger 19d ago

Geometric and Information Compression of Representations in Deep Learning

Investigates relationship between information-theoretic and geometric properties of deep neural network representations.

Ax Aarya Vasantlal, Joshua Zolla, Chuxu Zhang 19d ago

MORL-A2C: Multi-Objective Reinforcement Learning Reranker for Optimizing Healthiness in MOPI-HFRS

Multi-objective RL reranker optimizing health-aware food recommendations balancing preference, nutrition and diversity.

Ax Rui Jiao, Xiangzhe Kong, Yinjun Jia, Yijia Zhang, Ziyi Yang, Yang Liu, Jianzhu Ma 19d ago

Scalable Peptide Design via Memory-Efficient Equivariant Transformer

Memory-efficient equivariant transformer for scalable target-specific peptide sequence and structure co-design.

Ax Hongye Xu, Bartosz Krawczyk 19d ago

Geometry-Anchored Transport Framework for Exemplar-Free Class-Incremental Learning

Geometry-anchored transport method for exemplar-free class-incremental learning managing anisotropic representation drift.

Ax Jinghan Zhang, Zerui Cheng, Shiqi Chen, Ge Zhang, Wenhao Huang, Jiashuo Liu, Junxian He, Tianle Cai 19d ago

The Generalization Spectrum: A Chromatographic Approach to Evaluating Learning Algorithms

Generalization Spectrum framework evaluates learning algorithms on per-sample transfer ability rather than aggregate test scores.

Ax Ke Zhao, Zixiang Di, Hong Qian, Xiang Shu, Yaolin Wen, Qitao Shi, Bingdong Li, Xingyu Lu, Xiangfeng Wang, Jun Zhou, Ke Tang, Yang Yu 19d ago

MiniOpt: Reasoning to Model and Solve General Optimization Problems with Limited Resources

MiniOpt framework enabling LLMs to reason, model and solve diverse optimization problems with minimal training resources.

Ax Roshni Sahoo, Lihua Lei, Stefan Wager 19d ago

Learning from a Biased Sample

Methods for learning decision rules from biased training samples with under/over-represented groups.

Ax Sina Mavali, Jonas Ricker, David Pape, Asja Fischer, Lea Sch\"onherr 19d ago

Adversarial Robustness of AI-Generated Image Detectors in the Real World

Study of adversarial robustness of AI-generated image detectors, testing methods against evasion and poisoning attacks.

Ax Pranav Mani, Peng Xu, Zachary C. Lipton, Michael Oberst 19d ago

No Free Lunch: Non-Asymptotic Analysis of Prediction-Powered Inference

Non-asymptotic analysis of Prediction-Powered Inference showing finite-sample behavior differs from asymptotic free lunch results.

Ax Ji Xie, Trevor Darrell, Luke Zettlemoyer, XuDong Wang 19d ago

Reconstruction Alignment Improves Unified Multimodal Models

Reconstruction Alignment (RECA) method improves unified multimodal models by leveraging visual understanding for better generation.

Ax Marco Fanizza, Vishnu Iyer, Junseo Lee, Antonio A. Mele, Francesco A. Mele 19d ago

Efficient learning of bosonic Gaussian unitaries

Time-efficient algorithm for learning bosonic Gaussian unitaries in continuous-variable quantum technologies.

Ax Qi Li, Wendong Huang, Qichen Ye, Wutong Xu, Cheems Wang, Wei Yuan, Miao Xu, Zhiyu Mou, Guan Wang, Rongquan Bai, Chuan Yu, Jian Xu 19d ago

HOB: A Holistically Optimized Bidding Strategy under Heterogeneous Bidding Environments

HOB optimization strategy for advertising campaign bidding across heterogeneous auction channels with shared constraints.

Ax Bo Liang, Hanlin Song, Chang Liu, Tianyu Zhao, Yuxiang Xu, Zihao Xiao, Manjia Liang, Minghui Du, Wei-Liang Qian, Li-e Qiang, Peng Xu, Ziren Luo 19d ago

Estimating Orbital Parameters of Direct Imaging Exoplanet Using Neural Network

Flow-matching MCMC algorithm for estimating orbital parameters of exoplanetary systems using neural networks.

Ax Tianyi Xiong, Haonan Chen, Kelly Mahoney, Jingyin Tang, Tim Smith, Janice Bytheway 19d ago

CSU-PCAST: A Dual-Branch Transformer Framework for medium-range ensemble Precipitation Forecasting

Deep learning ensemble transformer model for global medium-range precipitation forecasting using ERA5 data.

Ax You Zuo (ALMAnaCH), Kim Gerdes (LISN), Eric Villemonte de La Clergerie (ALMAnaCH), Beno\^it Sagot (ALMAnaCH) 19d ago

Patent Representation Learning via Self-supervision

Self-supervised contrastive learning method for patent document representation, optimizing dropout and temperature settings.

Ax Tian Liu, Anwesha Basu, James Caverlee, Shu Kong 19d ago

Solving Semi-Supervised Few-Shot Learning from an Auto-Annotation Perspective

Semi-supervised few-shot learning approach using vision-language models and auto-annotation for learning from limited labeled data.

Ax Zhibo Hu, Chen Wang, Yanfeng Shu, Hye-young Paik, Liming Zhu 19d ago

Metaphors are a Source of Cross-Domain Misalignment of Large Reasoning Models

Study showing metaphors in training data cause cross-domain misalignment and reasoning errors in large language models.

Ax Hugo Malard, Gael Le Lan, Daniel Wong, David Lou Alon, Yi-Chiao Wu, Sanjeel Parekh 19d ago

Conditional Flow Matching for Visually-Guided Acoustic Highlighting

Conditional flow matching method for audio-visual alignment in acoustic highlighting using generative models.

Ax Sreejith Sreekumar, Nir Weinberger 19d ago

Quantum Maximum Likelihood Prediction via Hilbert Space Embeddings

Quantum maximum likelihood prediction via Hilbert space embeddings for independent and identically distributed samples.

Ax Sigma Jahan, Saurabh Singh Rajput, Tushar Sharma, Mohammad Masudur Rahman 19d ago

Hierarchical Fault Detection and Diagnosis for Transformer Architectures

DEFault++ hierarchical fault detection system for identifying component-level failures in transformer architectures without visible errors.

Ax Diego Marcondes 19d ago

Random test functions, $H^{-1}$ norm equivalence, and stochastic variational physics-informed neural networks

Physics-informed neural networks using random test functions to compute H^-1 norm equivalence for solving PDEs.