Ax Natsuto Isogai, Hayata Yamasaki, Sho Sonoda, Mio Murao 5/15/2026

Winning Lottery Tickets in Neural Networks via a Quantum-Inspired Classical Algorithm

Quantum-inspired classical algorithm for finding sparse subnetworks in neural networks via ridgelet transform.

Ax Shuoyang Sun, Chang Da, Hao Fang, Kuofeng Gao, Xinhao Zhong, Yi Sun, Fan Mo, Shu-Tao Xia, Bin Chen 5/15/2026

Mistletoe: Stealthy Acceleration-Collapse Attacks on Speculative Decoding

Security vulnerability in speculative decoding for LLM inference where draft tokens can be manipulated to collapse performance.

Ax Wuao Liu, Mustafa Chasmai, Subhransu Maji, Grant Van Horn 5/15/2026

Masked Autoencoders with Limited Data: Does It Work? A Fine-Grained Bioacoustics Case Study

Study of masked autoencoders for bioacoustic recognition with weak annotations using self-supervised learning.

Ax David N. Olivieri, Roque J. Hern\'andez 5/15/2026

Sheaf-Theoretic Transport and Obstruction for Detecting Scientific Theory Shift in AI Agents

Sheaf-theoretic framework for detecting theory-shift in AI agents to identify when representational frameworks become obstructed.

Ax Leslie G. Valiant 5/15/2026

Enhanced and Efficient Reasoning in Large Learning Models

Principled reasoning method for LLMs to improve content trustworthiness beyond smooth prose generation.

Ax Yongkai Chen, Wenxuan Zhong, Ping Ma 5/15/2026

Wahkon: A Statistically Principled Deep RKHS Superposition Network

Deep RKHS network unifying Kolmogorov superposition with RKHS regularization for prediction with finite-sample guarantees.

Ax Nilay Patel, Noah Arias, Davit Babayan, Victoria Cochran, Timothy Libman, Hafsah Mahmood, Liam McCarty, Soli Munoz, Laurel Willey, Jeffrey Flanigan 5/15/2026

MathAtlas: A Benchmark for Autoformalization in the Wild

Large-scale autoformalization benchmark with 52k graduate-level math theorems, definitions, and proofs from 103 textbooks.

Ax Mokshit Surana, Archit Rathod, Akshaj Satishkumar 5/15/2026

Measuring and Mitigating Toxicity in Large Language Models: A Comprehensive Replication Study

Replication study evaluating toxicity in LLMs trained on web-scale data and testing mitigation strategies while maintaining utility.

Ax Yu Gu, Zijun Yu, Vahid Partovi Nia, Masoud Asgharian 5/15/2026

Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning

Conformal procedure for aggregating multiple chain-of-thought reasoning paths with uncertainty quantification to improve reasoning reliability.

Ax Nishi Doshi, Shrey Shah 5/15/2026

Bridging the Rural Healthcare Gap: A Cascaded Edge-Cloud Architecture for Automated Retinal Screening

Edge-cloud cascaded architecture for automated diabetic retinopathy screening in rural areas with limited bandwidth using deep learning.

Ax Alvaro Lopez Pellicer, Plamen Angelov, Marwan Bukhari, Yi Li, Eduardo Soares, Jemma Kerns 5/15/2026

ProtoMedAgent: Multimodal Clinical Interpretability via Privacy-Aware Agentic Workflows

Agentic workflow framework combining interpretable prototype networks with LLMs for clinical diagnostics while avoiding hallucination through privacy-aware design.

Ax Benjamin Schneider, Xavier Schneider, Victor Zhong, Sun Sun 5/15/2026

ASH: Agents that Self-Hone via Embodied Learning

ASH system that learns embodied policies for long-horizon tasks from unlabeled internet video through self-improvement loops and inverse dynamics models.

Ax Noah Flynn 5/15/2026

GenCircuit-RL: Reinforcement Learning from Hierarchical Verification for Genetic Circuit Design

Reinforcement learning framework for genetic circuit design using code generation and hierarchical verification rewards for synthetic biology.

Ax Harry Robertshaw, Yanghe Hao, Weiyuan Deng, Benjamin Jackson, S. M. Hadi Sadati, Nikola Fischer, Tom Vercauteren, Alejandro Granados, Thomas C. Booth 5/15/2026

Towards Real-Time Autonomous Navigation: Transformer-Based Catheter Tip Tracking in Fluoroscopy

Transformer-based real-time catheter tip tracking system for autonomous robotic navigation in mechanical thrombectomy procedures.

Ax Zhenyu Yao, Daniel Paulin 5/15/2026

Training-Free Generative Sampling via Moment-Matched Score Smoothing

Training-free generative sampling method using moment-matched score-smoothed overdamped Langevin dynamics without requiring neural network training.

Ax Chengshuai Zhao, Zhen Tan, Dawei Li, Zhiyuan Yu, Huan Liu 5/15/2026

To See is Not to Learn: Protecting Multimodal Data from Unauthorized Fine-Tuning of Large Vision-Language Model

Proposes MMGuard to prevent unauthorized fine-tuning of vision-language models through proactive data protection mechanisms before training occurs.

Ax Hengjie Liu, Zhenya Zhang, Jianjun Zhao 5/15/2026

Precise Verification of Transformers through ReLU-Catalyzed Abstraction Refinement

Formal verification approach for transformers using ReLU-catalyzed abstraction refinement to verify complex attention mechanisms in safety-critical applications.

Ax Shen Lin, Jing Lin, Junhao Dong, Piotr Koniusz, Li Xu 5/15/2026

ICED: Concept-level Machine Unlearning via Interpretable Concept Decomposition

Method for concept-level machine unlearning in vision-language models via interpretable concept decomposition to remove target knowledge precisely.

Ax Sanjoy Chowdhury, Dinesh Manocha 5/15/2026

Uncovering the Representation Geometry of Minimal Cores in Overcomplete Reasoning Traces

Studies reasoning necessity in chain-of-thought traces by analyzing minimal cores within overcomplete reasoning to understand how much intermediate reasoning preserves model predictions.

Ax Zeli Su, Ziyin Zhang, Zhou Liu, Xuexian Song, Zhankai Xu, Longfei Zheng, Xiaolu Zhang, Rong Fu, Guixian Xu, Wentao Zhang 5/15/2026

Reinforcement Learning with Semantic Rewards Enables Low-Resource Language Expansion without Alignment Tax

Proposes semantic-space alignment with reinforcement learning to extend LLMs to low-resource languages while avoiding performance degradation in general capabilities.

Ax Sarkar Snigdha Sarathi Das, Palash Goyal, Mihir Parmar, Nanyun Peng, Vishy Tirumalashetty, Chun-Liang Li, Rui Zhang, Jinsung Yoon, Tomas Pfister 5/15/2026

Nexus : An Agentic Framework for Time Series Forecasting

Nexus agentic framework for time series forecasting integrating LLMs with specialized foundation models using contextual textual signals.

Ax Chenyi Wang, Ruoyu Song, Raymond Muller, Jean-Philippe Monteuuis, Jonathan Petit, Z. Berkay Celik, Ryan Gerdes, Ming F. Li 5/15/2026

Systematic Discovery of Semantic Attacks in Online Map Construction through Conditional Diffusion

MIRAGE framework discovers semantic attacks bypassing adversarial defenses to degrade autonomous vehicle HD map construction.

Ax Krishna Sayana, Ketan Todi, Ambarish Jash 5/15/2026

Prompting Policies for Multi-step Reasoning and Tool-Use in Black-box LLMs with Iterative Distillation of Experience

RL framework for training prompting policies that optimize multi-step reasoning and tool-use in frozen LLMs via iterative distillation.

Ax Chandan Rajah, Neha Sengupta, Federico Castanedo, Robin Mills, Amit Bahree, Ramesh Krishnan Muthukrishnan, Larry Murray 5/15/2026

Intelligence Impact Quotient (IIQ): A Framework for Measuring Organizational AI Impact

Intelligence Impact Quotient metric framework quantifying organizational AI integration depth and impact beyond usage metrics.

Ax Tianjue Lin, Jianan Zhou, Jieyi Bi, Yaoxin Wu, Wen Song, Zhiguang Cao, Jie Zhang 5/15/2026

Learning Scenario Reduction for Two-Stage Robust Optimization with Discrete Uncertainty

PRISE framework for learning scenario reduction in two-stage robust optimization with discrete uncertainty.

Ax Edoardo Scarpel, Alberto Pettena, Matteo Cederle, Federico Chiariotti, Marco Fabris, Gian Antonio Susto 5/15/2026

Fully Dynamic Rebalancing in Dockless Bike-Sharing Systems via Deep Reinforcement Learning

Deep reinforcement learning method for dynamic rebalancing of dockless bike-sharing systems using graph-based simulation.

Ax Avik Bhattacharya, Siddhant Dnyanesh Gole, Subhasis Chaudhuri, Alejandro C. Frery, Biplab Banerjee 5/15/2026

ArcGate: Adaptive Arctangent Gated Activation

ArcGate activation function with learnable parameters offering adaptive non-linear transformations for deep networks.

Ax Arie Wortsman-Zurich, Hugo Tabanelli, Yatin Dandi, Florent Krzakala, Bruno Loureiro 5/15/2026

Scaling Laws from Sequential Feature Recovery: A Solvable Hierarchical Model

Theoretical analysis of how scaling laws emerge from feature learning in hierarchical multi-layer neural networks.

Ax Ali Hassaan Mughal, Noor Fatima, Muhammad Bilal 5/15/2026

Mining Subscenario Refactoring Opportunities in Behaviour-Driven Software Test Suites: ML Classifiers and LLM-Judge Baselines

ML classifiers and LLM-based approach to automatically identify and rank refactoring opportunities in BDD test suites.

Ax Itay Zloczower, Eyal Lenga, Gilad Gressel, Yisroel Mirsky 5/15/2026

One Step to the Side: Why Defenses Against Malicious Finetuning Fail Under Adaptive Adversaries

Research showing existing defenses against malicious fine-tuning of foundation models fail under adaptive adversaries.

Ax Minghao Wu, Yuting Yan, Zhenyang Cai, Ke Ji, Chuangsen Fang, Ziying Sheng, Xidong Wang, Rongsheng Wang, Hejia Zhang, Shuang Li, Benyou Wang, Hongyuan Zha 5/15/2026

Agentifying Patient Dynamics within LLMs through Interacting with Clinical World Model

SepsisAgent augments LLMs with clinical world models to simulate patient dynamics for sepsis treatment recommendations in ICU settings.

Ax Weimin Xiong, Shuhao Gu, Bowen Ye, Zihao Yue, Lei Li, Feifan Song, Sujian Li, Hao Tian 5/15/2026

Video2GUI: Synthesizing Large-Scale Interaction Trajectories for Generalized GUI Agent Pretraining

Video2GUI: Automated framework extracting interaction trajectories from videos to generate large-scale training data for GUI agents, addressing data scarcity in multimodal LLM-based automation systems.

Ax Sangwoo Kim 5/15/2026

Non-linear Interventions on Large Language Models

Method extending LLM intervention techniques beyond linear representations to non-linear manifolds for model interpretability.

Ax William Lugoloobi, Samuelle Marro, Jabez Magomere, Joss Wright, Chris Russell 5/15/2026

Known By Their Actions: Fingerprinting LLM Browser Agents via UI Traces

Study showing LLM browser agents can be fingerprinted via UI interaction traces and timings across 14 models, enabling targeted attacks.

Ax Andrea Angino, Bindi \c{C}apriqi, Shega Likaj, Ken Trotti, Rolf Krause 5/15/2026

A Non-Monotone Preconditioned Trust-Region Method for Neural Network Training

Non-monotone preconditioned trust-region method for parallel neural network training with domain decomposition.

Ax Nikolaos Al. Papadopoulos 5/15/2026

Temporal Fair Division in Multi-Agent Systems: From Precise Alternation Metrics to Scalable Coordination Proxies

Fairness metrics for multi-agent resource competition using rotational periodicity and sliding-window measures.

Ax Jakub Grzywaczewski, Dawid P{\l}udowski, Przemys{\l}aw Biecek 5/15/2026

Your CLIP has 164 dimensions of noise: Exploring the embeddings covariance eigenspectrum of contrastively pretrained vision-language transformers

Analysis of vision-language model embedding spaces showing 164 noise dimensions in CLIP through spectral covariance decomposition.

Ax Varad Vishwarupe, Nigel Shadbolt, Marina Jirotka 5/15/2026

From Sycophantic Consensus to Pluralistic Repair: Why AI Alignment Must Surface Disagreement

Research on pluralistic AI alignment arguing aggregation methods produce sycophantic consensus rather than genuine value pluralism representation.

Ax KiHyun Nam, Jungwoo Heo, Siu Bae, Ha-Jin Yu, Joon Son Chung 5/15/2026

SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning

SpeakerLLM audio-LLM specialized for speaker understanding and verification reasoning in conversational AI applications.

Ax Guangyu Feng, Huanzhi Mao, Prabal Dutta, Joseph E. Gonzalez 5/15/2026

Concurrency without Model Changes: Future-based Asynchronous Function Calling for LLMs

AsyncFC framework enables concurrent function calling in LLM agents through asynchronous execution, decoupling decoding from function calls.

Ax Libin Zhu, Damek Davis, Dmitriy Drusvyatskiy, Maryam Fazel 5/15/2026

Average Gradient Outer Product in kernel regression provably recovers the central subspace for multi-index models

Theoretical analysis of kernel regression with gradient outer product for recovering low-dimensional structure in multi-index models.

Ax Connor Douglas, Joel Persson, Foster Provost 5/15/2026

Logging Policy Design for Off-Policy Evaluation

Studies optimal logging policy design to minimize off-policy evaluation error for treatment policy assessment.

Ax Lanxin Xiang, Liang Shi, Youhui Ye, Boyu Jiang, Dawei Zhou, Feng Guo 5/15/2026

RoSHAP: A Distributional Framework and Robust Metric for Stable Feature Attribution

RoSHAP distributional framework for stable and robust feature attribution analysis in ML models accounting for stochastic variation.

Ax Ryan Wei Heng Quek, Sanghyuk Lee, Alfred Wei Lun Leong, Arun Verma, Alok Prakash, Nancy F. Chen, Bryan Kian Hsiang Low, Daniela Rus, Armando Solar-Lezama 5/15/2026

MeMo: Memory as a Model

MeMo framework encodes new knowledge into a dedicated memory model while keeping the LLM frozen for efficient knowledge updates.

Ax Ruijia Niu, Dongxia Wu, Rose Yu, Yi-An Ma 5/15/2026

Functional-level Uncertainty Quantification for Calibrated Fine-tuning on LLMs

Functional-level uncertainty quantification method for calibrated fine-tuning of LLMs using parameter-efficient adapters.

Ax Alexis Bose, Jonathan Ethier, Paul Guinand 5/15/2026

Conformal Prediction for Multimodal Regression

Extends conformal prediction to multimodal regression using internal neural network features from images and text.

Ax Zhiliang Chen, Gregory Kang Ruey Lau, Chuan-Sheng Foo, Bryan Kian Hsiang Low 5/15/2026

DUET: Optimizing Training Data Mixtures via Feedback from Unseen Evaluation Tasks

DUET method optimizes LLM training data mixtures by learning from feedback on unseen evaluation tasks without access to task data.

Ax Zhiqiang He, Zhi Liu 5/15/2026

Silent Neuron Theory and Plasticity Preservation for Deep Reinforcement Learning in Adaptive Video Streaming

Silent neuron theory and plasticity preservation for deep RL in adaptive video streaming with network heterogeneity.

Ax Michael Theologitis, Vasilis Samoladas, Antonios Deligiannakis 5/15/2026

Communication-Efficient Federated Fine-Tuning

Communication-efficient federated fine-tuning of language models with parameter compression for distributed learning scenarios.

Ax Eli Chien, Wei-Ning Chen, Pan Li 5/15/2026

Privacy Amplification in Differentially Private Zeroth-Order Optimization with Hidden States

Privacy amplification analysis for zeroth-order optimization in differentially private fine-tuning of large language models.