Ax Seokwon Lee, Jaeyoung Sim, Sihyun Kim, Yuhsing Li, Yiwen Zhu, Kwanghyun Park 4/17/2026

RELOAD: A Robust and Efficient Learned Query Optimizer for Database Systems

RELOAD: reinforcement learning-based query optimizer for database systems with robust per-query performance.

Ax Runze Li, Hongyin Zhang, Junxi Jin, Qixin Zeng, Zifeng Zhuang, Yiqi Tang, Shangke Lyu, Donglin Wang 4/17/2026

World-Value-Action Model: Implicit Planning for Vision-Language-Action Systems

World-Value-Action model for vision-language-action embodied agents with implicit planning capabilities.

Ax Adrian Edin, Michel Kieffer, Mikael Johansson, Zheng Chen 4/17/2026

Exploiting Correlations in Federated Learning: Opportunities and Practical Limitations

Systematic classification and analysis of compression techniques exploiting correlations in federated learning.

Ax Yifan Zhao, Yuchen Yang, Matei Budiu, Sasa Misailovic 4/17/2026

Nautilus: An Auto-Scheduling Tensor Compiler for Efficient Tiled GPU Kernels

Nautilus tensor compiler with automated scheduling for efficient GPU kernel generation from high-level specifications.

Ax Yasin Abbasi-Yadkori, Peter L. Bartlett, Victor Gabillon, Alan Malek, Michal Valko 4/17/2026

Best of both worlds: Stochastic & adversarial best-arm identification

Bandit best-arm identification algorithm robust to both stochastic and adversarial reward distributions.

Ax Subhodip Panda, Shubhada Agrawal 4/17/2026

Regret Tail Characterization of Optimal Bandit Algorithms with Generic Rewards

Theoretical analysis of regret tail behavior in multi-armed bandit algorithms with stochastic rewards.

Ax Danae S\'anchez Villegas, Samuel Lewis-Lim, Nikolaos Aletras, Desmond Elliott 4/17/2026

Reasoning Dynamics and the Limits of Monitoring Modality Reliance in Vision-Language Models

arXiv paper analyzing reasoning dynamics and visual-textual information integration in 18 vision-language models.

Ax Evaldas Vaiciukynas, Paulius Danenas, Linas Ablonskis, Algirdas Sukys, Edgaras Dambrauskas, Voldemaras Zitkus, Rita Butkiene, Rimantas Butleris 4/17/2026

Comparison of Modern Multilingual Text Embedding Techniques for Hate Speech Detection Task

arXiv paper evaluating multilingual text embedding models for hate speech detection across Lithuanian, Russian, and English.

Ax Aihua Li 4/17/2026

Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching

arXiv paper proposing mixture-of-experts flow matching for faster language model inference while maintaining generation quality.

Ax Haochun Tang, Yuliang Yan, Jiahua Lu, Huaxiao Liu, Enyan Dai 4/17/2026

Route to Rome Attack: Directing LLM Routers to Expensive Models via Adversarial Suffix Optimization

arXiv paper on Route to Rome Attack, demonstrating black-box adversarial suffix attacks on cost-aware LLM routers.

Ax Naryeong Kim, Shin Yoo 4/17/2026

Atropos: Improving Cost-Benefit Trade-off of LLM-based Agents under Self-Consistency with Early Termination and Model Hotswap

arXiv paper on Atropos, optimizing cost-performance trade-offs for LLM-based agents using small models with early termination and model hotswapping.

Ax Chenghui Zheng, Garvesh Raskutti 4/17/2026

MinShap: A Modified Shapley Value Approach for Feature Selection

Feature selection method based on modified Shapley values for non-linear models with dependent features.

Ax Haozhi Fan, Jinhao Duan, Kaidi Xu 4/17/2026

IUQ: Interrogative Uncertainty Quantification for Long-Form Large Language Model Generation

Uncertainty quantification framework for long-form LLM generation addressing factuality and coherence in open-ended text.

Ax Arman Hatami, Romina Aalishah, Ilya E. Monosov 4/17/2026

Class Unlearning via Depth-Aware Removal of Forget-Specific Directions

Machine unlearning method targeting class removal by identifying and removing forget-specific representational directions in neural networks.

Ax Manan Gupta, Inderjeet Nair, Lu Wang, Dhruv Kumar 4/17/2026

Context Over Content: Exposing Evaluation Faking in Automated Judges

Exposes vulnerability in LLM-as-judge systems where contextual framing about downstream consequences influences evaluation independent of content.

Ax Mengdi Wu, Xiaoyu Jiang, Oded Padon, Zhihao Jia 4/17/2026

Prism: Symbolic Superoptimization of Tensor Programs

Symbolic superoptimizer for tensor programs using hierarchical symbolic graphs to represent and optimize families of implementations.

Ax Manan Gupta, Dhruv Kumar 4/17/2026

Diagnosing LLM Judge Reliability: Conformal Prediction Sets and Transitivity Violations

Diagnostic framework using conformal prediction and transitivity analysis to measure reliability of LLM-as-judge systems for NLG evaluation.

Ax Yao Tong, Jiayuan Ye, Anastasia Borovykh, Reza Shokri 4/17/2026

Generalization in LLM Problem Solving: The Case of the Shortest Path

Controlled study examining whether LLMs can generalize systematically using shortest-path planning as a testbed to isolate training, architecture, and inference factors.

Ax Quyen Tran, Hai Nguyen, Hoang Phan, Quan Dao, Linh Ngo, Khoat Than, Dinh Phung, Dimitris Metaxas, Trung Le 4/17/2026

An Optimal Transport-driven Approach for Cultivating Latent Space in Online Incremental Learning

Online incremental learning method using optimal transport to manage multimodal class distributions in latent space with continuous data streams.

Ax Bo Shu, Yiting Zhang, Saisai Hu, Dong Shu 4/17/2026

Generative Models and Connected and Automated Vehicles: A Survey in Exploring the Intersection of Transportation and AI

Survey on generative models applied to connected autonomous vehicles for predictive modeling, simulation, and decision-making.

Ax Utsav Singh, Souradip Chakraborty, Wesley A. Suttle, Brian M. Sadler, Derrik E. Asher, Anit Kumar Sahu, Mubarak Shah, Vinay P. Namboodiri, Amrit Singh Bedi 4/17/2026

Direct Preference Optimization for Primitive-Enabled Hierarchical RL: A Bilevel Approach

Bilevel DPO approach for hierarchical RL addressing non-stationarity and infeasible subgoals through preference optimization.

Ax Peidong Liu, Wenbo Zhang, Wei Ju, Jiancheng Lv, Xianggen Liu 4/17/2026

Bridging the Gap between Learning and Inference for Diffusion-Based Molecule Generation

DiffGap framework for molecule generation integrating adaptive sampling and pseudo-molecule estimation to address exposure bias in diffusion models.

Ax Fernando H. O. Duarte, Gladston J. P. Moreira, Eduardo J. S. Luz, Leonardo B. L. Santos, Vander L. S. Freitas 4/17/2026

Leveraging graph neural networks and mobility data for COVID-19 forecasting

Applies GNNs with human mobility data for COVID-19 forecasting, analyzing when spatio-temporal architectures outperform simpler baselines.

Ax Andrea Apicella, Salvatore Giugliano, Francesco Isgr\`o, Andrea Pollastro, Roberto Prevete 4/17/2026

IMPACTX: improving model performance by appropriately constraining the training with teacher explanations

IMPACTX leverages XAI techniques as automated attention mechanism to improve model performance without external knowledge or manual intervention.

Ax Jiacheng Liang, Tanqiu Jiang, Yuhui Wang, Rongyi Zhu, Fenglong Ma, Ting Wang 4/17/2026

AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models

AutoRAN framework automating hijacking of safety reasoning in large reasoning models using weaker model simulation and iterative refinement.

Ax Wenjie Ou, Zhishuo Zhao, Cheng Chen, Dongyue Guo, Yi Lin 4/17/2026

Logo-LLM: Local and Global Modeling with Large Language Models for Time Series Forecasting

Logo-LLM adapts LLMs for time series forecasting by combining local and global modeling to capture both short-term and long-range dependencies.

Ax Devendra Parkar, Anya Chaturvedi, Joshua J. Daymude 4/17/2026

Unsupervised Learning of Local Updates for Maximum Independent Set in Dynamic Graphs

First unsupervised learning model for Maximum Independent Set in dynamic graphs using GNNs with learned distributed update mechanisms.

Ax Yixian Xu, Shengjie Luo, Liwei Wang, Di He, Chang Liu 4/17/2026

Diagnosing and Improving Diffusion Models by Estimating the Optimal Loss Value

Method for estimating optimal loss value in diffusion models to distinguish between large optimal loss and insufficient model capacity.

Ax Yiyuan Yang, Zichuan Liu, Lei Song, Kai Ying, Zhiguang Wang, Tom Bamford, Svitlana Vyetrenko, Jiang Bian, Qingsong Wen 4/17/2026

Time-RA: Towards Time Series Reasoning for Anomaly Diagnosis with LLM Feedback

Time-RA reformulates time series anomaly detection as reasoning task using LLM feedback, introducing RATs40K dataset for fine-grained categorization.

Ax Dai Do, Manh Nguyen, Svetha Venkatesh, Hung Le 4/17/2026

SPaCe: Unlocking Sample-Efficient Large Language Models Training With Self-Pace Curriculum Learning

SPaCe applies curriculum learning to LLM fine-tuning with RL, reducing data/compute requirements by sampling examples by difficulty and learning value.

Ax Shaocong Wang, Tong Liu, Yihan Li, Ming Li, Kairui Wen, Pei Yang, Wenqi Ji, Minjing Yu, Yong-Jin Liu 4/17/2026

EEGDM: Learning EEG Representation with Latent Diffusion Model

EEGDM uses latent diffusion models for self-supervised EEG representation learning, capturing global dynamics beyond masked reconstruction.

Ax Yubo Gao, Renbo Tu, Gennady Pekhimenko, Nandita Vijaykumar 4/17/2026

DPQuant: Efficient and Differentially-Private Model Training via Dynamic Quantization Scheduling

DPQuant combines quantization scheduling with differentially-private SGD/Adam to reduce training time and energy while protecting privacy.

Ax Hannah Markgraf, Shambhuraj Sawant, Hanna Krasowski, Lukas Sch\"afer, Sebastien Gros, Matthias Althoff 4/17/2026

Safe Reinforcement Learning using Action Projection: Safeguard the Policy or the Environment?

Compares two strategies for integrating safety filters in RL: safeguarding environment vs embedding in policy through differentiable optimization.

Ax Armin Karamzade, Kyungmin Kim, JB Lanier, Davide Corsi, Roy Fox 4/17/2026

Model-Based Reinforcement Learning under Random Observation Delays

Studies reinforcement learning under random sensor delays in POMDPs where observations arrive out-of-sequence, addressing real-world RL challenges.

Ax Vladimir Fanaskov, Vladislav Trifonov, Alexander Rudikov, Ekaterina Muravleva, Ivan Oseledets 4/17/2026

Deep Learning for Subspace Regression

Research on reduced-order modeling using deep learning to compute linear subspaces for parametric systems with offline/online stages.

Ax Enda Yu, Dezun Dong, Zhaoning Zhang, Zhe Bai, Weiling Yang, Haojie Wang, Dongsheng Li, Yongwei Wu, Xiangke Liao 4/17/2026

LayerScope: Predictive Cross-Layer Scheduling for Efficient Multi-Batch MoE Inference on Legacy Servers

Presents PreScope, a prediction-driven scheduling system for efficient MoE inference on commodity hardware with CPU offloading.

Ax Gunjun Lee, Jiwon Kim, Jaiyoung Park, Younjoo Lee, Jung Ho Ahn 4/17/2026

From Tokens to Layers: Redefining Stall-Free Scheduling for MoE Serving with Layered Prefill

Proposes layered prefill scheduling for MoE LLM inference to optimize time-to-first-token and throughput while managing compute/memory constraints.

Ax Wenshuo Wang, Ziyou Jiang, Junjie Wang, Mingyang Li, Jie Huang, Yuekai Huang, Zhiyuan Chang, Feiyan Duan, Qing Wang 4/17/2026

Fall into a Pit, Gain in a Wit: Cognitive-Guided Harmful Meme Detection via Misjudgment Risk Pattern Retrieval

PatMD approach for detecting harmful memes by learning from misjudgment patterns in multimodal content with implicit rhetorical devices.

Ax Harris Hardiman-Mostow, Jack Mauro, Adrien Weihs, Andrea L. Bertozzi 4/17/2026

Topology-Aware Active Learning on Graphs

Graph-topological active learning using Balanced Forman Curvature for coreset construction under label budget constraints.

Ax Chenming Tang, Hsiu-Yuan Huang, Weijie Liu, Clive Bai, Saiyong Yang, Yunfang Wu 4/17/2026

Do Not Step Into the Same River Twice: Learning to Reason from Trial and Error

Reinforcement learning approach for language model reasoning that learns from trial-and-error to overcome exploration stagnation in RLVR.

Ax Zhuoyun Du, Runze Wang, Huiyu Bai, Zouying Cao, Xiaoyong Zhu, Yu Cheng, Bo Zheng, Wei Chen, Haochao Ying 4/17/2026

Enabling Agents to Communicate Entirely in Latent Space

Interlat enables LLM-based agents to communicate in latent space instead of natural language, improving information transfer depth.

Ax Genghan Zhang, Shaowei Zhu, Anjiang Wei, Zhenyu Song, Allen Nie, Zhen Jia, Nandita Vijaykumar, Yida Wang, Kunle Olukotun 4/17/2026

AccelOpt: A Self-Improving LLM Agentic System for AI Accelerator Kernel Optimization

AccelOpt is a self-improving LLM agent that autonomously optimizes kernels for AI accelerators using iterative generation and optimization memory.

Ax Yegon Kim, Hyunsu Kim, Gyeonghoon Ko, Juho Lee 4/17/2026

Active Learning with Selective Time-Step Acquisition for PDEs

Active learning framework for PDE surrogate modeling with selective time-step acquisition to reduce training data generation costs.

Ax Qiwei Tian, Chenhao Lin, Zhengyu Zhao, Chao Shen 4/17/2026

Pay Less Attention to Function Words for Free Robustness of Vision-Language Models

Function-word De-Attention method improves robustness of vision-language models against cross-modal adversarial attacks.

Ax Jeff J. Ma, Jae-Won Chung, Jisang Ahn, Yizhuo Liang, Runyu Lu, Akshay Jajoo, Myungjin Lee, Mosharaf Chowdhury 4/17/2026

Cornfigurator: Automated Planning for Any-to-Any Multimodal Model Serving

Cornfigurator automates deployment planning for any-to-any multimodal models with heterogeneous computation paths and component scaling.

Ax Toshiaki Hori, Jonathan DeCastro, Deepak Gopinath, Avinash Balachandran, Guy Rosman 4/17/2026

Learning to Plan, Planning to Learn: Adaptive Hierarchical RL-MPC for Sample-Efficient Decision Making

Hierarchical approach combining reinforcement learning with MPC planning for sample-efficient decision making in structured planning problems.

Ax Suyan Dai, Gan Sun, Fazeng Li, Xu Tang, Qianqian Wang, Yang Cong 4/17/2026

Federated Multi-Task Clustering

Federated learning approach for spectral clustering in decentralized environments, capturing latent correlations across tasks.

Ax Waleed Khalid, Dmitry Ignatov, Radu Timofte 4/17/2026

From Memorization to Creativity: LLM as a Designer of Novel Neural Architectures

NNGPT framework uses LLMs for neural architecture synthesis through iterative supervised fine-tuning cycles generating validated PyTorch networks.

Ax Kun Liang, Clive Bai, Xin Xu, Chenming Tang, Sanwoo Lee, Weijie Liu, Saiyong Yang, Yunfang Wu 4/17/2026

ORBIT: On-policy Exploration-Exploitation for Controllable Multi-Budget Reasoning

ORBIT system for controlling reasoning budget in Large Reasoning Models via on-policy exploration-exploitation to reduce computational cost.

Ax Murat Bilgehan Ertan, Marten van Dijk 4/17/2026

Fundamental Limitations of Favorable Privacy-Utility Guarantees for DP-SGD

Theoretical analysis of differential privacy limitations in DP-SGD using f-differential privacy framework with shuffled sampling.