Ax Itai Allouche, Joseph Keshet 5/5/2026

Mitigating Multimodal LLMs Hallucinations via Relevance Propagation at Inference Time

Method to reduce hallucinations in multimodal LLMs by using relevance propagation to balance modality utilization at inference.

Ax Tian Xu, Zhilong Zhang, Zexuan Chen, Ruishuo Chen, Yihao Sun, Yang Yu 5/5/2026

Adversarial Imitation Learning with General Function Approximation: Theoretical Analysis and Practical Algorithms

Theoretical analysis and practical algorithms for adversarial imitation learning with general function approximation.

Ax Fernando Martin-Maroto, Nabil Abderrahaman, Gonzalo G. de Polavieja 5/5/2026

Beyond ECE: Calibrated Size Ratio, Risk Assessment, and Confidence-Weighted Metrics

Proposes Calibrated Size Ratio metric to improve model confidence calibration assessment beyond Expected Calibration Error.

Ax G. Victor Daniela, A. Mallikarjuna Reddya, Uday Kumar Addankia, Sridhar Reddy Gogua, Sravanth Kumar Ramakuria 5/5/2026

Federated Semi-Supervised Graph Neural Networks with Prototype-Guided Pseudo-Labeling for Privacy-Preserving Gestational Diabetes Mellitus Prediction

Federated learning approach for gestational diabetes prediction using graph neural networks with pseudo-labeling and privacy preservation.

Ax Phil Sidney Ostheimer, Mayank Nagda, Andriy Balinskyy, Gabriel Vicente Rodrigues, Jean Radig, Carl Herrmann, Stephan Mandt, Marius Kloft, Sophie Fellenz 5/5/2026

Skipping the Zeros in Diffusion Models for Sparse Data Generation

Sparsity-Exploiting Diffusion model design that preserves sparse patterns and reduces computation on zero-heavy data.

Ax Nicholas T. Runcie, Fergus Imrie, Charlotte M. Deane 5/5/2026

Molecular Representations for Large Language Models

Research on molecular representation methods for LLMs to improve chemistry tasks like reaction prediction and structure analysis.

Ax Rudray Dave, Vedang Dubey, Smit Deoghare, Sudhakar Mishra 5/5/2026

Selector-Guided Autonomous Curriculum for One-Shot Reinforcement Learning from Verifiable Rewards

Research on selector-guided curriculum learning for improving LLM math reasoning via reinforcement learning from verifiable rewards.

Ax Kumar Shubham, Pavan Karjol, Kiran M K, Prathosh AP 5/5/2026

Leveraging Data Symmetries to Select an Optimal Subset of Training Data under Label Noise

Data symmetry approach for selecting training subsets under label noise, improving on k-NN based cutstats method.

Ax Kyle Lee, Corentin Delacour, Kevin Callahan-Coray, Kyle Jiang, Can Yaras, Samet Oymak, Tathagata Srimani, Kerem Y. Camsari 5/5/2026

Stochastic Sparse Attention for Memory-Bound Inference

SANTA: stochastic sparse attention mechanism reducing KV cache memory bandwidth for long-context LLM inference via post-softmax sampling.

Ax Sadia Asif, Mohammad Mohammadi Amiri 5/5/2026

RefusalGuard: Geometry-Preserving Fine-Tuning for Safety in LLMs

RefusalGuard: geometry-preserving fine-tuning method maintaining safety alignment in LLMs during downstream task adaptation.

Ax Lu Gao, Zhe Han, Yunshen Chen 5/5/2026

Deep learning-based pavement performance modeling using multiple distress indicators and road work history

CNN and deep learning for pavement deterioration prediction using distress indicators and road work history.

Ax An T. Le 5/5/2026

Training Non-Differentiable Networks via Optimal Transport

PolyStep: gradient-free optimizer for training neural networks with non-differentiable components using forward passes and polytope vertices.

Ax Gerardo A. Flores, Yash Deshpande, Jannis R. Brea, Ashia C. Wilson 5/5/2026

Pandora's Regret: A Proper Scoring Rule for Evaluating Sequential Search

Pandora's Regret: proper scoring rule for sequential search that uses pairwise structure to align model evaluation with search utility.

Ax Zhiwen Yang, Pan Liu, Yifan Li, Yunhua Zhong, Jun Xia 5/5/2026

PepSpecBench: A Unified Evaluation Benchmark for Peptide Tandem Mass Spectrometry Prediction

PepSpecBench: benchmark for evaluating deep learning models on peptide tandem mass spectrometry prediction in computational proteomics.

Ax Siyuan Duan, Ke Zhang, Xizhao Luo 5/5/2026

TRAP: Tail-aware Ranking Attack for World-Model Planning

TRAP: backdoor attack against world-model planning agents that manipulates ranking of imagined trajectories for unauthorized behavior.

Ax Zongqian Li, Yixuan Su, Han Zhou, Zihao Fu, Nigel Collier 5/5/2026

Flexi-LoRA with Input-Adaptive Ranks: Efficient Finetuning for Speech and Reasoning Tasks

Flexi-LoRA: parameter-efficient fine-tuning with input-adaptive ranks that dynamically adjust based on input complexity for multiple task types.

Ax Maheed H. Ahmed, Mahsa Ghasemi 5/5/2026

Multi-User Dueling Bandits: A Fair Approach using Nash Social Welfare

Fair multi-user dueling bandits framework using Nash social welfare for learning from preference data while protecting minority group preferences.

Ax Allassan Tchangmena A Nken, Baimam Boukar Jean Jacques, Miriam Rateike, Celia Cintas, Skyler Speakman 5/5/2026

Retrieval with Multiple Query Vectors through Anomalous Pattern Detection

Vector retrieval method handling multiple query vectors simultaneously using anomalous pattern detection for complex reasoning and retrieval tasks.

Ax Nan Qiao, Sheng Yue, Shuning Wang, Ju Ren 5/5/2026

AdamO: A Collapse-Suppressed Optimizer for Offline RL

AdamO optimizer for offline reinforcement learning preventing TD update collapse through control-theoretic modeling of optimizer dynamics.

Ax Zechen Ma, Zixi Qu, Jinyan Yi, David Lin, Yashar Ganjali 5/5/2026

DBLP: Phase-Aware Bounded-Loss Transport for Burst-Resilient Distributed ML Training

DBLP: distributed ML training optimization addressing network-layer transient congestion and tail latency through phase-aware bounded-loss transport.

Ax Mario Koddenbrock, Christoph Lange, Robin Legner, Martin J\"ager, Martin K\"ogler, Mariano N. Cruz Bournazou, Peter Neubauer, Felix Biessmann, Erik Rodner 5/5/2026

RamanBench: A Large-Scale Benchmark for Machine Learning on Raman Spectroscopy

RamanBench: first large-scale reproducible benchmark for machine learning on Raman spectroscopy with standardized datasets and evaluation protocols.

Ax Daniel da Silva Costa, Pedro Nuno de Souza Moura, Adriana C. F. Alvim 5/5/2026

How Can One Choose the Best CAM-Based Explainability Method for a CNN Model?

Study of metrics and methodology for evaluating Class Activation Mapping-based explainability methods in CNN models.

Ax Yan Zhou, Kevin Hamlen, Michael De Lucia, Murat Kantarcioglu, Latifur Khan, Sharad Mehrotra, Ananthram Swami, Bhavani Thuraisingham 5/5/2026

Robust and Explainable Divide-and-Conquer Learning for Intrusion Detection

Divide-and-conquer learning technique for intrusion detection that decomposes complex problems into manageable subproblems on resource-constrained devices.

Ax Reza Rawassizadeh, Tanvi Sharma 5/5/2026

NeuroViz: Real-time Interactive Visualization of Forward and Backward Passes in Neural Network Training

NeuroViz interactive visualization tool for real-time exploration of neural network training including forward/backward passes and weight updates.

Ax James Wang, Surbhi Goel 5/5/2026

Weight Clipping for Robust Conformal Inference under Unbounded Covariate Shifts

Weight clipping method for conformal prediction robustness under unbounded covariate shifts and unbounded density ratios.

Ax Baobing Zhang, Wanxin Sui 5/5/2026

GETA-3DGS: Automatic Joint Structured Pruning and Quantization for 3D Gaussian Splatting

GETA-3DGS automatic joint pruning and quantization framework for compressing 3D Gaussian splatting models for mobile deployment.

Ax Haoxing Tian, Zaiwei Chen, Ioannis Ch. Paschalidis, Alex Olshevsky 5/5/2026

Bridging the Gap Between Average and Discounted TD Learning

Novel theoretical algorithm bridging average-reward and discounted temporal difference learning in reinforcement learning.

Ax Ishaan Watts, Catherine Li, Sachin Goyal, Jacob Mitchell Springer, Aditi Raghunathan 5/5/2026

Sharpness-Aware Pretraining Mitigates Catastrophic Forgetting

Study of pretraining optimizers that bias toward flatter minima to improve model robustness against catastrophic forgetting during fine-tuning.

Ax Furkan Mumcu, Yasin Yilmaz 5/5/2026

Detecting Adversarial Data via Provable Adversarial Noise Amplification

Formal analysis of adversarial noise amplification through neural network layers with sufficient conditions for detecting adversarial inputs.

Ax Wenwei Zhao, Xiaowen Li, Yao Liu, Zhuo Lu 5/5/2026

Adversarial Update-Based Federated Unlearning for Poisoned Model Recovery

FAUN method for recovering poisoned federated learning models through adversarial unlearning without full retraining.

Ax Yuanfan Li, Xiyuan Wei, Tianbao Yang, Yiming Ying 5/5/2026

Statistical Consistency and Generalization of Contrastive Representation Learning

Theoretical analysis of contrastive representation learning consistency, generalization bounds, and retrieval performance of foundation models.

Ax Akash Bonagiri, Gerard Janno Anderias, Saee Patil, Angelina Lai, Devang Borkar, Gezheng Kang, Ishant Gandhi, Setareh Rafatirad, Houman Homayoun 5/5/2026

STABLEVAL: Disagreement-Aware and Stable Evaluation of AI Systems

STABLEVAL framework for stable AI system evaluation that accounts for annotator disagreement and bias in human evaluation.

Ax Reza Rastegar 5/5/2026

Boundary Mass and the Soft-to-Hard Limit in Mixture-of-Experts

Theoretical analysis of mixture-of-experts models studying singular behavior in hard routing limits and boundary mass probability.

Ax Kaixuan Ji, Qiwei Di, Heyang Zhao, Qingyue Zhao, Quanquan Gu 5/5/2026

On the Optimal Sample Complexity of Offline Multi-Armed Bandits with KL Regularization

Characterizes optimal sample complexity of offline multi-armed bandits with KL regularization for offline decision-making.

Ax Dongwon Kim, Gyuejeong Lee 5/5/2026

Personalized Federated Learning for Gradient Alignment

pFLAlign framework for personalized federated learning using gradient alignment to preserve client-specific information and reduce variance.

Ax Debarshi Kundu, Archisman Ghosh, Swaroop Ghosh, Vasant Honavar 5/5/2026

Projection-Free Transformers via Gaussian Kernel Attention

Gaussian Kernel Attention replaces learned projections in transformers with similarity-based diffusion operator for simplified self-attention.

Ax Ujjwal Patil, Javad Ghofrani 5/5/2026

Combining Trained Models in Reinforcement Learning

Survey combining trained models in reinforcement learning through transfer, distillation, ensembles, and federated approaches for improved sample efficiency.

Ax Qinwei Huang, Rui Zuo, Simon Khan, Qinru Qiu 5/5/2026

Experience Constrained Hierarchical Federated Reinforcement Learning for Large-scale UAV Teams in Hazardous Environments

Hierarchical federated reinforcement learning for UAV teams in hazardous environments with constrained experience generation and safety considerations.

Ax Soyeon Kim, Seongwoo Lim, Kyowoon Lee, Jaesik Choi 5/5/2026

Manifold-Aligned Guided Integrated Gradients for Reliable Feature Attribution

Manifold-aligned guided Integrated Gradients for improving feature attribution reliability in deep neural network interpretation.

Ax Guanmeng Xian, Ning Yang, Philip S. Yu 5/5/2026

Manifold-Constrained Adversarial Training for Long-Tailed Robustness via Geometric Alignment

Manifold-constrained adversarial training framework for robust models on long-tailed datasets with balanced geometric alignment.

Ax Abdullah Ahmad Khan, Ferdous Sohel 5/5/2026

DurableUn: Quantization-Induced Recovery Attacks in Machine Unlearning

Quantization-induced recovery attacks on machine unlearning showing INT4 quantization restores forgotten content despite compliance at higher precision.

Ax S M Asif Hossain, Shruti Kshirsagar 5/5/2026

Demographic-Aware Transfer Learning for Sleep Stage Classification in Clinical Polysomnography

Transfer learning approach for sleep stage classification accounting for demographic variations across gender, age, and sleep apnea severity.

Ax Yan Jiang, Ruihong Qiu, Zi Huang 5/5/2026

Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning

Dynamic-size reasoning blocks for diffusion language models using monotonic entropy descent and reinforcement learning for improved reasoning.

Ax Fengming Zhang, Wenjie Du, Huan Zhang, Ke Yu, Shen Qu 5/5/2026

HELIX: Hybrid Encoding with Learnable Identity and Cross-dimensional Synthesis for Time Series Imputation

HELIX method for time series imputation using learnable feature identities and persistent embeddings for cross-feature correlation modeling.

Ax Xinyu Li, Jianhua Zhang, Liang Chen 5/5/2026

Variational Matrix-Learning Fourier Networks for Parametric Multiphysics Surrogates

Variational matrix-learning Fourier networks for efficient parametric surrogate modeling in multiphysics simulation and design exploration.

Ax Ruotong Ma, Wentao Yu, Qizhou Wang, Jie Yang, Chen Gong 5/5/2026

Graph Federated Unlearning for Privacy Preservation

Graph federated learning framework with unlearning capabilities for privacy preservation and user data removal in distributed settings.

Ax Sanjiv R. Das, Harshad Khadilkar, Sukrit Mittal, Daniel Ostrov, Deep Srivastav, Hungjen Wang 5/5/2026

A Meta Reinforcement Learning Approach to Goals-Based Wealth Management

Meta reinforcement learning approach for wealth management pre-trained on thousands of goals-based portfolio optimization problems.

Ax Jean-Marc Mercier, Gabriele Santin 5/5/2026

Differentiable Kernel Ridge Regression for Deep Learning Pipelines

Introduces Sparse Kernels (SKs), differentiable kernel ridge regression variant for deep learning pipelines with lazy training at inference time.

Ax Niklas Houba 5/5/2026

When Attention Collapses: Residual Evidence Modeling for Compositional Inference

Identifies slot collapse failure in attention-based models for compositional inference and proposes residual evidence modeling approach.

Ax Xianli Zhu, Jia Yin 5/5/2026

ZNO: Stable Rational Neural Operators in the Z-Domain for Discrete-Time Dynamic

Z-Domain Neural Operator for stable discrete-time system identification and operator learning.