Ax Xidong Wu, Yue Zhuan, Ruoqiao Wei, Hangxin Chen, Di Bai, Jintao Liu, Xinyi Wang, Xue Wang, Luoshu Wang, Xinwu Cheng 5/14/2026

AgenticRecTune: Multi-Agent with Self-Evolving Skillhub for Recommendation System Optimization

AgenticRecTune: multi-agent framework with self-evolving skill hub for optimizing multi-stage recommendation system pipelines.

Ax Bingli Wang, Huanze Tang, Haijun Lv, Zhishan Lin, Lixin Gu, Lei Feng, Qipeng Guo, Kai Chen 5/14/2026

COHERENCE: Benchmarking Fine-Grained Image-Text Alignment in Interleaved Multimodal Contexts

COHERENCE benchmark for evaluating multimodal LLMs on fine-grained image-text alignment in interleaved document-like contexts.

Ax Yiheng Yao, Chelsea Zou, Robert D. Hawkins 5/14/2026

Talk is Cheap, Communication is Hard: Dynamic Grounding Failures and Repair in Multi-Agent Negotiation

Multi-agent LLM benchmark for negotiation that tests dynamic grounding and communication repair across conversational turns.

Ax Venkat Srinivasan, Vishaal Jatav, Anushka Chandrababu, Geetika Sharma 5/14/2026

Gyan: An Explainable Neuro-Symbolic Language Model

Gyan: neuro-symbolic language model combining transformers with symbolic reasoning to improve compositionality, interpretability, and reduce hallucinations.

Ax Mohammad Al Ridhawi, Mahtab Haj Ali, Hussein Al Osman 5/14/2026

Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using Large Language Model Judges with Closed-Loop Reinforcement Learning Feedback

Framework for evaluating agentic stock prediction systems using LLM judges and closed-loop reinforcement learning feedback on behavioral dimensions.

Ax Nan Jia, Haojin Yang, Xing Ma, Jiesong Lian, Shuailiang Zhang, Weipeng Zhang, Ke Zeng, Xunliang Cai, Zequn Sun 5/14/2026

Asymmetric On-Policy Distillation: Bridging Exploitation and Imitation at the Token Level

Asymmetric on-policy distillation method for training student language models with token-level teacher feedback, improving upon standard RL and off-policy approaches.

Ax Nithin Somasekharan, Rabi Pathak, Manushri Dhanakoti, Tingwen Zhang, Ling Yue, Andy Zhu, Shaowu Pan 5/14/2026

AI CFD Scientist: Toward Open-Ended Computational Fluid Dynamics Discovery with Physics-Aware AI Agents

AI CFD Scientist: open-source physics-aware AI agent for autonomous computational fluid dynamics discovery with LLM-based scientific reasoning loop.

Ax Zixuan Xie, Xinyu Liu, Shangtong Zhang 5/14/2026

MathlibPR: Pull Request Merge-Readiness Benchmark for Formal Mathematical Libraries

Benchmark for LLM-assisted formal mathematical reasoning using Lean and Mathlib, evaluating pull request merge-readiness for library contributions.

Ax Leonel Aguilar, Jan Nagler, Christoph Hoelscher, Nino Antulov-Fantulin 5/14/2026

Does Your Neural Network Extrapolate? Feature Engineering as Identifiability Bias for OOD Generalization

Study on when neural networks fail to extrapolate out-of-distribution, analyzing feature learning versus data-generating-process identifiability.

Ax Harshvardhan Saini, Samyak Jha, Yiming Tang, Dianbo Liu 5/14/2026

When Language Overwrites Vision: Over-Alignment and Geometric Debiasing in Vision-Language Models

Mechanistic analysis of hallucination failures in vision-language models, tracing issues to geometric over-alignment in decoder-based VLMs.

Ax Karim Othman, Jonas Petersen, Matei Ignuta-Ciuncanu, Camilla Mazzoleni, Federico Martelli, Alessandro Lombardi, Riccardo Maggioni, Philipp Petersen 5/14/2026

FactoryNet: A Large-Scale Dataset toward Industrial Time-Series Foundation Models

FactoryNet: industrial time-series pretraining dataset with 51M datapoints across 23k task executions for zero-shot transfer and anomaly detection.

Ax Musa Cim, Poovaiah Palangappa, Miro Hodak, Ravi Dwivedula, Meena Arunachalam, Mahmut Taylan Kandemir 5/14/2026

Pretraining large language models with MXFP4 on Native FP4 Hardware

Research on FP4 quantization for pretraining large language models, investigating stability and convergence issues in full-pipeline low-precision training on Llama 3.1-8B.

Ax Daniel Goldstein, Eugene Cheah 5/14/2026

Key-Value Means: Transformers with Expandable Block-Recurrent Compressed Memory

Key-Value Means presents block-recurrent attention mechanism achieving O(N) complexity with fixed or growing state for efficient long-context transformer inference.

Ax Wolfgang Grieskamp, Teng Zhang, Vineeth Kashyap 5/14/2026

Combining Mechanical and Agentic Specification Inference for Move

Tool combining weakest-precondition analysis with agentic Claude Code CLI for specification inference in Move Prover to reduce verification boilerplate.

Ax Huilin Zhou, Jian Zhao, Yilu Zhong, Zhen Liang, Xiuyuan Chen, Yuchen Yuan, Tianle Zhang, Chi Zhang, Lan Zhang, Xuelong Li 5/14/2026

Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization

Metis framework reformulates LLM jailbreaking as inference-time policy optimization using adversarial POMDP for improved red teaming scalability.

Ax Minqing Huang, Yujiao Xiang, Zihan Liang, Jiajie Huang, Jingqi Wang, Zhi Xu, Feiyang Tan, Hangning Zhou, Mu Yang, Gong Che 5/14/2026

CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving

CoWorld-VLA multi-expert world model framework for vision-language-action autonomous driving with planning-oriented spatiotemporal representations.

Ax Zuojin Tang, Haoyun Liu, Xinyuan Chang, Changjie Wu, Dongjie Huo, Yandan Yang, Bin Liu, Zhejia Cai, Feng Xiong, Mu Xu, jiachen Luo, De Ma, Zhiheng Ma, Gang Pan 5/14/2026

ALAM: Algebraically Consistent Latent Action Model for Vision-Language-Action Models

ALAM latent action model for vision-language-action models that extracts action priors from video using algebraically consistent representations.

Ax Linus Heck, Filip Mac\'ak, Roman Andriushchenko, Milan \v{C}e\v{s}ka, Sebastian Junges 5/14/2026

Shields to Guarantee Probabilistic Safety in MDPs

Formal framework for probabilistic safety shielding in Markov decision processes with conservative guarantees.

Ax Yaxin Du, Xiyuan Yang, Zhifan Zhou, Wanxu Liu, Zixing Lei, Zimeng Chen, Fenyi Liu, Haotian Wu, Yuzhu Cai, Zexi Liu, Xinyu Zhu, WenHao Wang, Linfeng Zhang, Chen Qian, Siheng Chen 5/14/2026

DataMaster: Data-Centric Autonomous AI Research

DataMaster autonomous system for data-centric ML research automating dataset discovery, adaptation, validation, and knowledge propagation.

Ax Jiaming Li, Chenyu Zhu, Nanxi Yi, Youjun Bao, Li Sun, Quanying Lv, Xiang Fang, Daizong Liu, Jianjun Li, Kun He, Bowen Zhou, Zhiyuan Ma 5/14/2026

TMPO: Trajectory Matching Policy Optimization for Diverse and Efficient Diffusion Alignment

TMPO trajectory matching policy optimization for diffusion alignment addressing reward hacking through probability distribution constraints.

Ax Sultan Zavrak 5/14/2026

MCPShield: Content-Aware Attack Detection for LLM Agent Tool-Call Traffic

MCPShield attack detection framework for LLM agent tool-call traffic via Model Context Protocol, using graph encoding and embeddings.

Ax Jonas Petersen, Gian-Alessandro Lombardi, Riccardo Maggioni, Camilla Mazzoleni, Federico Martelli, Philipp Petersen 5/14/2026

HEPA: A Self-Supervised Horizon-Conditioned Event Predictive Architecture for Time Series

HEPA self-supervised architecture for event prediction in multivariate time series using horizon-conditioned JEPA pretraining.

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

LiBaGS: Lightweight Boundary Gap Synthesis for Targeted Synthetic Data Selection

LiBaGS lightweight method for selecting informative synthetic training data by scoring boundary proximity, uncertainty, and data density.

Ax Jeongsol Kim, Hongeun Kim, Jian Wang, Jong Chul Ye 5/14/2026

Gradient-Free Noise Optimization for Reward Alignment in Generative Models

ZeNO gradient-free noise optimization method for reward alignment in diffusion and flow models without backpropagation.

Ax Seonghoon Yu, Dongjun Nam, Byung-Kwan Lee, Jeany Son 5/14/2026

Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation

Reasoning-prefix masking technique for distilling visual-reasoning capabilities from large VLMs into compact student models.

Ax Sayantani Ghosh, Amit Kumar Das, Amlan Chakrabarti 5/14/2026

A New Technique for AI Explainability using Feature Association Map

FAMeX algorithm for AI explainability using feature association maps based on graph-theoretic approaches.

Ax Adam Haroon, Erick J. Rodr\'iguez-Seda, Cody Fleming, Tristan Schuler 5/14/2026

Learning When to Act: Communication-Efficient Reinforcement Learning via Run-Time Assurance

Safe reinforcement learning approach that learns when agents should act via communication-efficient timing decisions under Lyapunov safety constraints.

Ax Mushir Akhtar, M. Tanveer, Mohd. Arshad 5/14/2026

CAWI: Copula-Aligned Weight Initialization for Randomized Neural Networks

CAWI initialization method for randomized neural networks using copulas to capture inter-feature dependencies.

Ax Sirui Zhang, Haonan Wang, Xunkai Li, Zekai Chen, Shumeng Li, Hongchao Qin, Rong-Hua Li, Guoren Wang 5/14/2026

Towards Robust Federated Multimodal Graph Learning under Modality Heterogeneity

Federated multimodal graph learning approach addressing modality heterogeneity and incomplete data across distributed networks.

Ax Sanah Suri, Kieran Ringel, Maike Sonnewald 5/14/2026

OceanCBM: A Concept Bottleneck Model for Mechanistic Interpretability in Ocean Forecasting

OceanCBM concept bottleneck model for interpretable ocean forecasting that provides mechanistic explanations aligned with physics.

Ax Nina Corvelo Benz, Eleni Straitouri, Manuel Gomez-Rodriguez 5/14/2026

Learning to Decide with AI Assistance under Human-Alignment

Study on decision-making with AI assistance, examining how decision-makers interpret model confidence and prediction utility in high-stakes domains.

Ax Puyu Wang, Jan Schuchardt, Nikita Kalinin, Junyu Zhou, Sophie Fellenz, Christoph Lampert, Marius Kloft 5/14/2026

Population Risk Bounds for Kolmogorov-Arnold Networks Trained by DP-SGD with Correlated Noise

Theoretical analysis establishing population risk bounds for Kolmogorov-Arnold Networks trained with mini-batch SGD and differential privacy.

Ax Parv Kapoor, Abigail Hammer, Ashish Kapoor, Karen Leung, Eunsuk Kang 5/14/2026

Runtime Monitoring of Perception-Based Autonomous Systems via Embedding Temporal Logic

Embedding Temporal Logic framework for runtime monitoring of perception-based autonomous systems without expensive learned abstraction modules.

Ax Weichen Yu, Xiaomin Li, Yizhou Zhao, Xiaoze Liu, Ruowang Zhang, Haixin Wang, Yinyi Luo, Chen Henry Wu, Gaurav Mittal, Matt Fredrikson, Yu Hu 5/14/2026

Multi-Rollout On-Policy Distillation via Peer Successes and Failures

Multi-rollout on-policy distillation method for LLMs that leverages peer successes and failures to provide denser token-level supervision beyond sparse verifier rewards.

Ax Eun Go, Rohan Deb, Arindam Banerjee 5/14/2026

Plan Before You Trade: Inference-Time Optimization for RL Trading Agents

FPILOT framework applies inference-time optimization via Model Predictive Control to RL trading agents for portfolio management, incorporating price forecasts at deployment.

Ax Nirmal Patel, Fei Wang, Inderjit Dhillon 5/14/2026

ODRPO: Ordinal Decompositions of Discrete Rewards for Robust Policy Optimization

Method for robust LLM alignment using ordinal decomposition of discrete rewards in RLHF with stochastic auto-raters for long-form QA and instruction following.

Ax Benjamin Amoh, Geoffrey G. Parker, Wesley Marrero 5/14/2026

IGT-OMD: Implicit Gradient Transport for Decision-Focused Learning under Delayed Feedback

IGT-OMD: implicit gradient transport for decision-focused learning with delayed feedback in online bilevel optimization.

Ax Kamel Abdous, Nairouz Mrabah, Mohamed Bouguessa 5/14/2026

Modeling Heterophily in Multiplex Graphs: An Adaptive Approach for Node Classification

Method for node classification in multiplex graphs with heterophily using adaptive cross-domain learning approach.

Ax Hanli Qiao, George Em Karniadakis, Muhammad Muniruzzaman 5/14/2026

UFO: A Domain-Unification-Free Operator Framework for Generalized Operator Learning

UFO: domain-unification-free neural operator framework for learning cross-domain function space mappings.

Ax Lawrence Feng, Gaurav R. Ghosal, Jacob Mitchell Springer, Ziqian Zhong, Aditi Raghunathan 5/14/2026

Early Data Exposure Improves Robustness to Subsequent Fine-Tuning

Research on how upstream training choices affect model robustness when capabilities are retained through subsequent fine-tuning.

Ax Ziwei Huang, Zeyuan Song, Paola Sebastiani, Stefano Monti 5/14/2026

A Resampling-Based Framework for Network Structure Learning in High-Dimensional Data

RSNet: open-source R package for robust network inference in high-dimensional data using resampling-based framework.

Ax Tomasz D\k{a}dela, Adam Kania, Maciej Rut, Przemys{\l}aw Spurek 5/14/2026

Spectral Energy Centroid: a Metric for Improving Performance and Analyzing Spectral Bias in Implicit Neural Representations

Research on Spectral Energy Centroid metric for improving performance and analyzing spectral bias in implicit neural representations.

Ax Jingzhou Jiang, Yi Yang, Kar Yan Tam 5/14/2026

Layer-wise Representation Dynamics: An Empirical Investigation Across Embedders and Base LLMs

Framework measuring layer-wise representation dynamics in LLMs using Frenet geometry, neighborhood retention, and information metrics.

Ax Anastasiia Sedova, Skyler Seto, Natalie Schluter, Pierre Ablin 5/14/2026

Scaling Laws for Mixture Pretraining Under Data Constraints

Scaling laws for mixing scarce target data with abundant generic data during LLM pretraining under data constraints.

Ax Shravan Doda 5/14/2026

Before the Last Token: Diagnosing Final-Token Safety Probe Failures

Analysis of safety probe failures in LLMs where jailbreak evidence distributed across tokens bypasses final-token readout.

Ax Yujia Zheng, Fan Feng, Yuke Li, Shaoan Xie, Kevin Murphy, Kun Zhang 5/14/2026

From Generalist to Specialist Representation

Nonparametric framework for learning task-relevant specialist representations from generalist models with identifiability analysis.

Ax Yuwei Zhang, Sha Li, Changlong Yu, Qin Lu, Shuowei Jin, Chengyu Dong, Haoran Liu, Ilgee Hong, Xintong Li, Zhenyu Shi, Bing Yin, Jingbo Shang 5/14/2026

Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation

Reflection-enhanced self-distillation for LLMs to learn from rare successful interactions with rich environmental feedback.

Ax Joana Pasquali, Ramiro N. Barros, Arthur S. Bianchessi, Vin\'icius Conte Turani, Jo\~ao Vitor Boer Abitante, Rafaela Cappelari Ravazio, Christian Mattjie, Ot\'avio Parraga, Lucas S. Kupssinsk\"u, Rodrigo C. Barros 5/14/2026

Low-Rank Adapters Initialization via Gradient Surgery for Continual Learning

LoRA initialization method using gradient surgery to mitigate catastrophic forgetting in continual LLM fine-tuning.

Ax Jacob K. Christopher, James E. Warner, Ferdinando Fioretto 5/14/2026

Constraint-Aware Flow Matching: Decision Aligned End-to-End Training for Constrained Sampling

Constraint-aware flow matching for physics-informed generative models with strict constraint satisfaction.

Ax Vin\'icius Conte Turani, Ot\'avio Parraga, Jo\~ao Vitor Boer Abitante, Kristen K. Arguello, Joana Pasquali, Ramiro N. Barros, Flavio du Pin Calmon, Christian Mattjie, Rodrigo C. Barros, Lucas S. Kupssinsk\"u 5/14/2026

Inference-Time Machine Unlearning via Gated Activation Redirection

Inference-time machine unlearning via gated activation redirection to remove memorized training data from LLMs without retraining.