Ax Kyriaki-Margarita Bintsi, Sparsh Makharia, Ya\"el Balbastre, Joselyn Romero Avila, Julia F. Lehman, Suzanne N. Haber, Anastasia Yendiki 19d ago

Tractography-Driven Synthetic Data Generation for Fiber Bundle Segmentation in Tracer Histology

Proposes synthetic data generation for fiber bundle segmentation in tracer histology using dMRI tractography validation.

Ax Prarabdh Shukla, Ritik, Suhas Rao, Arpit Agarwal, Arjun Bhagoji 19d ago

Jailbreaking for the Average Jane: Choosing Optimal Jailbreaks via Bandit Algorithms for Automatically Enhanced Queries

Examines automated jailbreak selection using bandit algorithms for non-expert malicious actors to craft effective LLM attacks.

Ax Jiahe Chen, Qian Shao, Qiyuan Chen, Jiaying He, Jintai Chen, Jian Wu, Hongxia Xu 19d ago

Geometric Gradient Rectification for Safe Open-Set Semi-Supervised Learning

Proposes geometric gradient rectification for semi-supervised learning with out-of-distribution outliers in unlabeled data.

Ax Minghao Chen, Jiale Zheng 19d ago

XMSE-Aware Adaptive Empirical Bayes Estimation

Develops XMSE-aware adaptive empirical Bayes estimator interpolating between ML and kernel-based EB to address second-order alignment issues.

Ax Antti S\"allinen, Siiri Rautio, Santeri Kaupinm\"aki, Andreas Hauptmann 19d ago

Enabling self-supervised learned primal dual with Noise2Inverse

Proposes self-supervised learned primal-dual method for X-ray CT reconstruction in low-dose settings without ground-truth data.

Ax Rongjian Chen, Jianmin Hu, Kejiang Ye, Minxian Xu 19d ago

RolloutPipe: Overlapping Pipelined Rollout and Training in Disaggregated On-Policy LLM Reinforcement Learning

Describes RolloutPipe, a system for overlapping pipelined rollout and training in disaggregated RL architectures for LLM post-training with verifiable rewards.

Ax Sahil Shrivastava 19d ago

Semantic Early-Stopping for Iterative LLM Agent Loops

Proposes semantic early-stopping for multi-agent LLM loops using embedding similarity to halt when output meaning stops improving, reducing token waste.

Ax Aleksandar Todorov, Jesse ten Napel, Alexander M\"uller 19d ago

Parametric Open Source Games

Introduces parametric open-source games, a continuous model where players choose parameters converted to actions, with equilibrium existence results.

Ax Hanli Xu, Fengxiang He, Sarat Moka 19d ago

Beyond Global Divergences: A Local-Mass Perspective on Bayesian Inference

Introduces Mass Index and regularized extended KL divergence for local-mass analysis in Bayesian inference beyond global divergence objectives.

Ax Vincent Chen, Starrick Liu, Regis Cheng, Dance Yang, Shalfun Li, Ryan Yu, Lucy Liang, Hang Su, Roy Gan, Hao Wang, Qian Wang 19d ago

DMuon: Efficient Distributed Muon Training with Near-Adam Overhead

Proposes DMuon, distributed training method for matrix-orthogonalization optimizers reducing communication overhead compared to element-wise optimization.

Ax Ilia Larchenko 19d ago

Learning to Fold: prizewinning solution at LeHome Challenge 2026 (1st place online, 2nd offline)

Describes prizewinning bimanual garment folding solution combining vision-language-action policy with reinforcement learning loop for robotic manipulation.

Ax Humzah Merchant, Bradford Levy 19d ago

Forecasting With LLMs: Improved Generalization Through Feature Steering

Uses sparse autoencoders to inspect LLM internal states for forecasting tasks, identifying time-specific knowledge versus generalizable patterns.

Ax Ziyuan Tang, Tianshi Xu, Yousef Saad, Yuanzhe Xi 19d ago

Hierarchical Muon: Tiled Newton-Schulz Updates for Efficient Muon Optimization

Introduces Hierarchical Muon (HiMuon), tiled Newton-Schulz optimization for efficient dense neural network training with reduced computational overhead.

Ax Sayak Dutta 19d ago

CARVE: Content-Aware Recurrent with Value Efficiency for Chunk-Parallel Linear Attention

Proposes CARVE, memory-aware recurrent architecture with content-aware gating for efficient chunk-parallel linear attention in sequence models.

Ax Graham Gibson, John Tipton, Kellin Rumsey, Natalie Klein 19d ago

Ribbon: Scalable Approximation and Robust Uncertainty Quantification

Introduces Ribbon, scalable approximation to Dirichlet-reweighted bootstrap for efficient uncertainty quantification in high-dimensional models.

Ax Josef Chen 19d ago

When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models

Analyzes fundamental ceiling on multi-model LLM systems (routing, voting, mixture-of-agents), showing accuracy limited by co-failure rate across 67 frontier models.

Ax Yu-Neng Wang, Sara Achour 19d ago

Generative Models on Analog Hardware with Dynamics

Proposes methods for implementing generative models on analog hardware with physics-determined dynamics for low-power computation.

Ax Haitong Liu, Deepak Narayanan Sridharan, David Steurer, Manuel Wiedmer 19d ago

Fast algorithms for learning a Gaussian under halfspace truncation with optimal sample complexity

Develops efficient algorithm for learning high-dimensional Gaussian distributions truncated to unknown halfspace with optimal sample complexity.

Ax Tianyi Men, Zhuoran Jin, Pengfei Cao, Yubo Chen, Kang Liu, Jun Zhao 19d ago

Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning

Introduces planning experience exploration for GUI agents using small open-source MLLMs, improving task planning and cross-website generalization.

Ax Nicholas Pulsone, Gregory Goren, Roee Shraga 19d ago

Understanding Domain-Aware Distribution Alignment in Budgeted Entity Matching

Studies domain-aware distribution alignment in entity matching under data constraints, applying low-resource learning to data integration.

Ax Johannes Zenn, Jonas Geiping 19d ago

When are likely answers right? On Sequence Probability and Correctness in LLMs

Investigates alignment between sequence probability and correctness in LLMs, quantifying when higher likelihood corresponds to correct outputs.

Ax Tao Luo, Zheng Ma, Zhi-Qin John Xu, Yaoyu Zhang 19d ago

Theory of the Frequency Principle for General Deep Neural Networks

Theoretical analysis of frequency principle phenomenon showing DNNs learn target functions from low to high frequencies during training.

Ax Zixiao Wang, Farzan Farnia, Zhenghao Lin, Yunheng Shen, Bei Yu 19d ago

Consistent Distributed Ranking of Generative Models via Kernel Distances

Proposes kernel distance method for ranking generative models in distributed settings based on output fidelity and diversity.

Ax Xiwen Tao, Chenyi Zhang, Helin Wang, Yexin Zhang, Tongyang Li 19d ago

Gradient Testing and Estimation by Comparisons

Develops gradient testing and estimation algorithms using only comparison oracle queries on smooth functions.

Ax Srishti Gupta, Zhang Chen, Luca Demetrio, Fabio Brau, Xiaoyi Feng, Zhaoqiang Xia, Antonio Emanuele Cin\`a, Maura Pintor, Luca Oneto, Ambra Demontis, Battista Biggio, Fabio Roli 19d ago

Over-parameterization and Adversarial Robustness in Neural Networks: An Overview and Empirical Analysis

Studies relationship between over-parameterization in neural networks and adversarial robustness, analyzing vulnerability to adversarial examples.

Ax Zaiwei Chen, Kaiqing Zhang, Eric Mazumdar, Asuman Ozdaglar, Adam Wierman 19d ago

Decentralized Best-Response-Based Learning in Two-Player Zero-Sum Stochastic Games: A Finite-Sample Analysis

Finite-sample analysis of decentralized best-response learning in two-player zero-sum games and stochastic games.

Ax Diego Cajaraville-Aboy, Ana Fern\'andez-Vilas, Rebeca P. D\'iaz-Redondo, Manuel Fern\'andez-Veiga 19d ago

Byzantine-Robust Aggregation for Securing Decentralized Federated Learning

Byzantine-robust aggregation algorithms for secure decentralized federated learning without central servers.

Ax Hong-ah Chai, Seokbin Yoon, Keumjin Lee 19d ago

Learning to Explain Air Traffic Situation

ML approach to model how air traffic controllers build mental representations of complex air traffic situations.

Ax Stefan P. Schmid, Ella Miray Rajaonson, Cher Tian Ser, Mohammad Haddadnia, Shi Xuan Leong, Al\'an Aspuru-Guzik, Agustinus Kristiadi, Kjell Jorner, Felix Strieth-Kalthoff 19d ago

Bayesian Optimization for General Reaction Conditions

Bayesian optimization method for identifying chemical reaction conditions that work across multiple substrates efficiently.

Ax Harikrishna Kuttivelil, Katia Obraczka 19d ago

Chisme: Heterogeneity-Aware Gossip Learning

Chisme: gossip learning framework addressing heterogeneity in resource-constrained edge devices for privacy-preserving distributed learning.

Ax Kai Tang, Jinhao You, Yichen Guo, Yiding Sun, Dongxu Zhang, Wenya Wang, Hanze Li, Tao Luo, Renyuan Li, Xiande Huang 19d ago

Mitigating Hallucinations via Inter-Layer Consistency Aggregation in Large Vision-Language Models

Training-free hallucination mitigation in vision-language models via inter-layer consistency aggregation during decoding.

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

DMSC: Dynamic Multi-Scale Coordination Framework for Time Series Forecasting

DMSC: dynamic multi-scale coordination framework addressing static decomposition and inflexible fusion in time series forecasting.

Ax Xiang Li, Shanshan Wang, Chenglong Xiao 19d ago

Learning to Select Maximum Clique Algorithms: From Traditional Machine Learning to a Dual-Channel Hybrid Neural Architecture

Hybrid neural architecture for instance-aware algorithm selection on maximum clique problems, combining ML and neural networks.

Ax Mingxuan Jiang, Keyang Chen, Yongxin Wang, Yongsheng Zhao, Ziyue Dai, Yicun Liu, Zeping Li, Qiuyang Zhang, Hongyi Nie, Hongbin Zhu, Sen Liu, Guangnan Ye, Hongfeng Chai 19d ago

Limited Reference, Reliable Generation: A Two-Component Framework for Tabular Data Generation in Low-Data Regimes

Two-component framework for tabular data generation in low-data regimes combining GANs and fine-tuned LLMs.

Ax Raphael Simon, Pieter Libin, Wim Mees 19d ago

Learning Robust Penetration Testing Policies under Partial Observability: A systematic evaluation

Reinforcement learning framework for penetration testing under partial observability, addressing belief state aggregation challenges.

Ax Isaac Reid, Arijit Sehanobish, Cederik H\"ofs, Bruno Mlodozeniec, Leonhard Vulpius, Federico Barbero, Adrian Weller, Krzysztof Choromanski, Richard E. Turner, Petar Veli\v{c}kovi\'c 19d ago

Rotary Position Encodings for Graphs

Rotary position encodings applied to graph-structured data using graph Laplacian spectrum for improved attention mechanisms.

Ax Yen-Shan Chen, Sian-Yao Huang, Cheng-Lin Yang, Yun-Nung Chen 19d ago

Eyes-on-Me: Scalable RAG Poisoning through Transferable Attention-Steering Attractors

Eyes-on-Me: scalable poisoning attack on RAG systems using reusable attention attractors to manipulate retrieval and generation.

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.