Ax Debosmita Bhaumik, Julian Togelius, Georgios N. Yannakakis, Ahmed Khalifa 5/14/2026

Learning Local Constraints for Reinforcement-Learned Content Generators

Hybrid approach combining constraint-based and RL-trained generators for game content creation with visual and global property guarantees.

Ax Francesco Montagna, Francesco Locatello 5/14/2026

Causal Learning with the Invariance Principle

Causal discovery method using structural causal models and invariance principle across multiple environments.

Ax Ankit Kulshrestha, Xiaoyuan Liu 5/14/2026

CO-MAP: A Reinforcement Learning Approach to the Qubit Allocation Problem

Reinforcement learning approach to optimize qubit allocation in quantum compilers, reducing SWAP gate overhead.

Ax Oliver Hennh\"ofer, Maximilian Kirsch, Christine Preisach 5/14/2026

Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with 'nonconform'

Python library for conformal anomaly detection that converts anomaly scores into calibrated p-values with statistical validity.

Ax Florian P. Mahner, Johannes Roth, Ka Chun Lam, Michael F. Bonner, Francisco Pereira, Martin N. Hebart 5/14/2026

Characterizing Universal Object Representations Across Vision Models

Analysis of universal visual representations across 162 diverse vision models identifying convergent properties.

Ax Cenwei Zhang, Suncheng Xiang, Lei You 5/14/2026

MedCore: Boundary-Preserving Medical Core Pruning for MedSAM

Structured pruning framework for medical SAM models preserving boundary fidelity during compression.

Ax Haaris Mehmood, Giorgos Tatsis, Dimitrios Alexopoulos, Karthikeyan Saravanan, Jie Xu, Anastasios Drosou, Mete Ozay 5/14/2026

DisAgg: Distributed Aggregators for Efficient Secure Aggregation in Federated Learning

Secure aggregation scheme for federated learning with reduced communication rounds and dropout handling.

Ax Qian Shen (University of Florida, Gainesville, USA), Fanghua Cao (University of Florida, Gainesville, USA), Min Yao (University of Florida, Gainesville, USA), Shlok Gilda (University of Florida, Gainesville, USA), Bonnie J. Dorr (University of Florida, Gainesville, USA), Walter L. Leite (University of Florida, Gainesville, USA) 5/14/2026

Children's English Reading Story Generation via Supervised Fine-Tuning of Compact LLMs with Controllable Difficulty and Safety

Fine-tuning compact LLMs with supervised learning for controllable difficulty children's story generation.

Ax Ben Wilson, Matimba Swana, Peter Winter, Matt Roach 5/14/2026

Humanwashing -- It Should Leave You Feeling Dirty

Critical analysis of 'human-in-the-loop' claims for AI safety in deployed decision systems.

Ax Jascha Wanger 5/14/2026

VectorSmuggle: Steganographic Exfiltration in Embedding Stores and a Cryptographic Provenance Defense

Security analysis of steganographic exfiltration attacks on vector databases in RAG systems with cryptographic defenses.

Ax Abdalrahman Wael 5/14/2026

Dense vs Sparse Pretraining at Tiny Scale: Active-Parameter vs Total-Parameter Matching

Empirical comparison of dense vs sparse MoE transformers at tiny scale with parameter-matched baselines.

Ax Martino Bernasconi, Matteo Castiglioni, Andrea Celli, Alexandros Hollender 5/14/2026

Min-Max Optimization Requires Exponentially Many Queries

Theoretical analysis proving min-max optimization requires exponential query complexity for nonconvex-nonconcave functions.

Ax Ejaaz Merali, Mohamed Hibat-Allah, Mohammad Kohandel, Richard T. Scalettar, Ehsan Khatami 5/14/2026

Parallel Scan Recurrent Neural Quantum States for Scalable Variational Monte Carlo

Parallel scan technique for scaling recurrent neural network quantum states to larger quantum many-body systems efficiently.

Ax Jiayi Zhang, Yongfeng Gu, Jianhao Ruan, Maojia Song, Yiran Peng, Zhiguang Han, Jinyu Xiang, Zhitao Wang, Caiyin Yang, Yixi Ouyang, Bang Liu, Chenglin Wu, Yuyu Luo 5/14/2026

Harnessing Agentic Evolution

Framework for iteratively evolving agentic systems via candidate generation and feedback-guided search, balancing flexibility and stability.

Ax Harry Mayne, Lev McKinney, Jan Dubi\'nski, Adam Karvonen, James Chua, Owain Evans 5/14/2026

Negation Neglect: When models fail to learn negations in training

Study documenting failure mode where LLMs mislearn negations during fine-tuning despite recognizing false claims during training.

Ax S. Akshay, Chaitanya Garg, Ashutosh Gupta, Kuldeep S. Meel, Ajinkya Naik 5/14/2026

Quantifying Sensitivity for Tree Ensembles: A symbolic and compositional approach

Verification technique for measuring input sensitivity in decision tree ensembles used for safety-critical classification tasks.

Ax Steve Hanneke, Anay Mehrotra, Grigoris Velegkas, Manolis Zampetakis 5/14/2026

What is Learnable in Valiant's Theory of the Learnable?

Theoretical characterization of which function classes are learnable in Valiant's original 1984 learning model with membership queries.

Ax Tara Bogavelli, Gabrielle Gauthier Melan\c{c}on, Katrina Stankiewicz, Oluwanifemi Bamgbose, Fanny Riols, Hoang H. Nguyen, Raghav Mehndiratta, Lindsay Devon Brin, Joseph Marinier, Hari Subramani, Anil Madamala, Sridhar Krishna Nemala, Srinivas Sunkara 5/14/2026

EVA-Bench: A New End-to-end Framework for Evaluating Voice Agents

Benchmark framework for evaluating voice agents on realistic simulated conversations and voice-specific failure modes.

Ax Anastasis Kratsios, A. Martina Neuman, Gudmund Pammer 5/14/2026

Tighter Learning Guarantees on Digital Computers via Concentration of Measure on Finite Spaces

Theoretical work on generalization bounds for machine learning models on digital computers considering finite precision.

Ax Hugo Koubbi, Louis Hernandez, Matthieu Boussard 5/14/2026

Understanding Catastrophic Forgetting In LoRA via Mean-Field Attention Dynamics

Analysis of catastrophic forgetting in LoRA fine-tuning using mean-field attention dynamics and dynamical systems theory.

Ax Yan Sun, Qixin Zhang, Li Shen, Dacheng Tao 5/14/2026

Convergent Differential Privacy Analysis for General Federated Learning

Privacy analysis framework for federated learning with differential privacy providing tighter bounds across communication rounds.

Ax Chaozhi Zhang, Lin Liu, Xiaoqun Zhang 5/14/2026

Few-shot Multi-Task Learning of Linear Invariant Features with Meta Subspace Pursuit

Meta-learning framework for few-shot multi-task learning with limited data using linear invariant features.

Ax Jialin Yu, Yuxiang Zhou, Haoxuan Li, Junchi Yu, Mengyue Yang, Yulan He, Nevin L. Zhang, Philip Torr, Ricardo Silva 5/14/2026

Causal Fine-Tuning under Latent Confounded Shift

Fine-tuning approach for mitigating spurious correlations caused by latent confounders during model adaptation and deployment.

Ax Sergio Rozada, Jose Luis Orejuela, Antonio G. Marques 5/14/2026

Addressing Finite-Horizon MDPs via Low-Rank Tensor Value Approximation

Low-rank tensor approximation method for learning optimal policies in finite-horizon MDPs with high-dimensional state spaces.

Ax Pui Ieng Lei, Ximing Chen, Yijun Sheng, Yanyan Liu, Zhiguo Gong, Qiang Yang 5/14/2026

Gradual Domain Adaptation for Graph Learning

Graph domain adaptation framework constructing intermediate domain sequences to handle large distribution shifts in graph learning.

Ax Albert Alcalde, Giovanni Fantuzzi, Enrique Zuazua 5/14/2026

Exact Sequence Interpolation with Transformers

Theoretical proof that transformers can exactly interpolate finite input-output sequence datasets with polynomial-sized architectures.

Ax Quentin Duchemin, Guillaume Obozinski 5/14/2026

Efficient distributional regression trees learning algorithms for calibrated non-parametric probabilistic forecasts

Regression trees algorithm for probabilistic forecasting with uncertainty quantification in critical applications.

Ax Xuyang Chen, Keyu Yan, Guojian Wang, Lin Zhao 5/14/2026

VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning

Offline reinforcement learning method addressing value function inconsistency in model-based approaches for risk-averse applications.

Ax Lukas Silvester Barth, Paulo von Petersenn 5/14/2026

Efficient compression of neural networks and datasets

Study connecting compression theory to neural network generalization, combining pruning techniques with algorithmic information theory principles.

Ax Isaac Ning Lee, Leila Mahmoodi, Trung Le, Mehrtash Harandi 5/14/2026

Exemplar-Free Continual Learning for State Space Models

Research on adapting State-Space Models to continual learning without stored exemplars, addressing catastrophic forgetting in evolving SSM states.

Ax Yashas Samaga, Varun Yerram, Spandana Raj Babbula, Prateek Jain, Praneeth Netrapalli 5/14/2026

A Faster Generalized Two-Stage Approximate Top-K

Fast two-stage approximate Top-K selection algorithm optimized for dense matrix operations on accelerators.

Ax Yan Sun, Qixin Zhang, Zhiyuan Yu, Xikun Zhang, Li Shen, Dacheng Tao 5/14/2026

MaskPro: Linear-Space Probabilistic Learning for Strict (N:M)-Sparsity on LLMs

MaskPro enables (N:M) semi-structured sparsity for LLMs through probabilistic learning with hardware acceleration.

Ax Wenbing Li, Zikai Song, Hang Zhou, Yunyao Zhang, Junqing Yu, Wei Yang 5/14/2026

LoRA-Mixer: Coordinate Modular LoRA Experts Through Serial Attention Routing

LoRA-Mixer routes task-specific LoRA experts through attention projections for parameter-efficient multi-task LLM adaptation.

Ax John Wu, Adam Cross, Jimeng Sun 5/14/2026

RDMA: Cost Effective Agent-Driven Rare Disease Mining from Electronic Health Records

Agent-driven mining of rare diseases from electronic health records using LLMs on noisy clinical notes.

Ax Jiale Chen, Yalda Shabanzadeh, Elvir Crn\v{c}evi\'c, Torsten Hoefler, Dan Alistarh 5/14/2026

The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm

Theoretical analysis of GPTQ quantization method for LLMs, showing connection to Babai's nearest plane algorithm.

Ax Marco Bagatella, Mert Albaba, Jonas H\"ubotter, Georg Martius, Andreas Krause 5/14/2026

Test-time Offline Reinforcement Learning on Goal-related Experience

Framework connecting foundation models to offline goal-conditioned RL, enabling test-time adaptation to novel tasks.

Ax Yifan Zhang 5/14/2026

A Markov Categorical Framework for Language Modeling

Analytical framework using Markov categories to explain internal mechanisms and representation learning in autoregressive language models.

Ax Nicholas E. Corrado, Josiah P. Hanna 5/14/2026

Centralized Adaptive Sampling for Reliable Co-Training of Independent Multi-Agent Policies

Adaptive sampling approach for multi-agent reinforcement learning achieving optimal convergence in cooperative games.

Ax Minghao Liu, Chia-Hsuan Lu, Marta Kwiatkowska 5/14/2026

Exact Verification of Graph Neural Networks with Incremental Constraint Solving

Exact verification method for graph neural networks to compute adversarial robustness guarantees against attacks.

Ax Amirmohsen Sattarifard, Sepehr Lavasani, Kunlin Zhang, Amirhossein Rajabpour, Hanlin Xu, Fengyu Sun, Negar Hassanpour, Chao Gao 5/14/2026

GLASS: Global-Local Aggregation for Inference-time Sparsification of LLMs

GLASS method for inference-time sparsification of LLMs using global-local importance estimation for resource-constrained deployment.

Ax Dikshant Sagar, Kaiwen Yu, Alejandro Yankelevich, Jianming Bian, Pierre Baldi 5/14/2026

Adapting Vision-Language Models for Neutrino Event Classification in High-Energy Physics

Fine-tuned vision-language model for classifying neutrino events in high-energy physics detector data.

Ax Boao Kong, Junzhu Liang, Yuxi Liu, Renjia Deng, Kun Yuan 5/14/2026

CR-Net: Scaling Parameter-Efficient Training with Cross-Layer Low-Rank Structure

CR-Net enables parameter-efficient LLM pre-training using cross-layer low-rank structure with reduced memory and computation.

Ax Zongyue Li, Xiao Han, Yusong Li, Niklas Strauss, Matthias Schubert 5/14/2026

DAWM: Diffusion Action World Models for Offline Reinforcement Learning via Action-Inferred Transitions

Diffusion-based world model for offline reinforcement learning that jointly generates actions, states, and rewards.

Ax Abhishek Moturu, Muhammad Muzammil, Anna Goldenberg, Babak Taati 5/14/2026

LiLAW: Lightweight Learnable Adaptive Weighting to Learn Sample Difficulty & Improve Noisy Training

LiLAW method that dynamically adjusts training sample weights based on difficulty for noisy data training.

Ax Zheng Wang, Kaixuan Zhang, Wanfang Chen, Xiaonan Lu, Longyuan Li, Tobias Schlagenhauf 5/14/2026

Characteristic Root Analysis and Regularization for Linear Time Series Forecasting

Theoretical analysis of linear models for time series forecasting, examining robustness and interpretability.

Ax Kamel Alrashedy, Vriksha Srihari, Zulfiqar Zaidi, Ridam Srivastava, Pradyumna Tambwekar, Matthew Gombolay 5/14/2026

Constraints-of-Thought: A Framework for Constrained Reasoning in Language-Model-Guided Search

Framework enabling LLMs to perform multi-step constrained reasoning by satisfying symbolic constraints in planning tasks.

Ax Mike Lasby, Ivan Lazarevich, Nish Sinnadurai, Sean Lie, Yani Ioannou, Vithursan Thangarasa 5/14/2026

REAP the Experts: Why Pruning Prevails for One-Shot MoE compression

Research on expert pruning vs merging for compressing Mixture-of-Experts models, showing pruning superior for generative tasks.

Ax Dario Shariatian, Alain Durmus, Umut Simsekli, Stefano Peluchetti 5/14/2026

Latent-Augmented Discrete Diffusion Models

Latent-Augmented Discrete Diffusion: learnable auxiliary channels for improved few-step language generation.

Ax Song Bian, Tao Yu, Shivaram Venkataraman, Youngsuk Park 5/14/2026

Scaling Laws Meet Model Architecture: Toward Inference-Efficient LLMs

Study of architectural factors and scaling laws trade-offs for inference-efficient LLMs.

Ax Mingyu Jo, Jaesik Yoon, Justin Deschenaux, Caglar Gulcehre, Sungjin Ahn 5/14/2026

Loopholing Discrete Diffusion: Deterministic Bypass of the Sampling Wall

Loopholing: mechanism preserving distributional information in discrete diffusion for parallel decoding.