Ax Yixuan Zhang, Ruihao Zhu, Qiaomin Xie 3/20/2026

On the Peril of (Even a Little) Nonstationarity in Satisficing Regret Minimization

Analyzes optimal satisficing regret bounds for nonstationary K-armed bandits with piecewise-stationary segments.

Ax Abhinaba Basu, Pavan Chakraborty 3/20/2026

When Names Change Verdicts: Intervention Consistency Reveals Systematic Bias in LLM Decision-Making

ICE-Guard detects spurious feature reliance in LLM decision-making through intervention consistency testing on demographic, authority, and framing features.

Ax Andrew Choi, Xinjie Wang, Zhizhong Su, Wei Xu 3/20/2026

Scaling Sim-to-Real Reinforcement Learning for Robot VLAs with Generative 3D Worlds

Addresses sim-to-real transfer for vision-language-action models in robotics by generating diverse 3D simulation worlds for RL fine-tuning.

Ax Jiangtao Luo, Bingbing Xu, Shaohua Xia, Yongyi Ran 3/20/2026

iSatCR: Graph-Empowered Joint Onboard Computing and Routing for LEO Data Delivery

iSatCR optimizes onboard computing and routing for LEO satellite data processing using graph neural networks to reduce ground transmission bottlenecks.

Ax Yuhan Ye, Saurabh Amin, Asuman Ozdauglar 3/20/2026

Learning Decision-Sufficient Representations for Linear Optimization

Studies construction of compressed decision-sufficient datasets for linear programs with unknown cost vectors using decision-relevant dimension theory.

Ax Jiacheng Tang, Zhiyuan Zhou, Zhuolin He, Jia Zhang, Kai Zhang, Jian Pu 3/20/2026

CausalVAD: De-confounding End-to-End Autonomous Driving via Causal Intervention

CausalVAD applies causal intervention to de-confound end-to-end autonomous driving models, addressing dataset bias and improving reliability.

Ax Abhinaba Basu, Pavan Chakraborty 3/20/2026

ICE: Intervention-Consistent Explanation Evaluation with Statistical Grounding for LLMs

ICE framework evaluates explanation faithfulness in LLMs via randomization tests with multiple intervention operators, distinguishing genuine faithfulness from chance.

Ax Haotian Lu, Jincong Lu, Sachin Sachdeva, Sheldon X. -D. Tan 3/20/2026

WarPGNN: A Parametric Thermal Warpage Analysis Framework with Physics-aware Graph Neural Network

WarPGNN applies physics-aware graph neural networks for efficient thermal warpage analysis in chiplet-package systems, replacing costly numerical simulations.

Ax Eduar Castrillo Velilla 3/20/2026

Breaking Hard Isomorphism Benchmarks with DRESS

DRESS graph fingerprinting achieves unique fingerprints across 51,718 non-isomorphic strongly regular graphs using single-deletion vertex operations.

Ax Mohammadhossein Homaei, Iman Khazrak, Rub\'en Molano, Andr\'es Caro, Mar \'Avila 3/20/2026

Cyber-Resilient Digital Twins: Discriminating Attacks for Safe Critical Infrastructure Control

i-SDT combines predictive modelling and multi-class attack discrimination for detecting and responding to cyber-physical system attacks without full shutdowns.

Ax Rong Fu, Jiekai Wu, Haiyun Wei, Xiaowen Ma, Shiyin Lin, Kangan Qian, Chuang Liu, Jianyuan Ni, Simon James Fong 3/20/2026

SwiftGS: Episodic Priors for Immediate Satellite Surface Recovery

SwiftGS enables rapid 3D satellite surface reconstruction via meta-learned Gaussian primitives predicted in a single forward pass for environmental monitoring.

Ax Samuel Gruffaz, Kyurae Kim, Fares Guehtar, Hadrien Duval-decaix, Pac\^ome Trautmann 3/20/2026

A Theoretical Comparison of No-U-Turn Sampler Variants: Necessary and Su?cient Convergence Conditions and Mixing Time Analysis under Gaussian Targets

Theoretical analysis comparing NUTS-mul and NUTS-BPS variants for Bayesian sampling with convergence guarantees under Gaussian targets.

Ax Donglin Xie, Qingshuo Zhao, Jingyu Wang, Shijia Geng, Jiarui Jin, Jun Li, Rongrong Guo, Guangkun Nie, Gongzheng Tang, Yuxi Zhou, Thomas Penzel, Shenda Hong 3/20/2026

Holter-to-Sleep: AI-Enabled Repurposing of Single-Lead ECG for Sleep Phenotyping

Applies AI to repurpose single-lead ECG from Holter devices for sleep phenotyping, linking cardiovascular monitoring to sleep assessment.

Ax Huichi Zhou, Siyuan Guo, Anjie Liu, Zhongwei Yu, Ziqin Gong, Bowen Zhao, Zhixun Chen, Menglong Zhang, Yihang Chen, Jinsong Li, Runyu Yang, Qiangbin Liu, Xinlei Yu, Jianmin Zhou, Na Wang, Chunyang Sun, Jun Wang 3/20/2026

Memento-Skills: Let Agents Design Agents

Memento-Skills introduces an LLM agent that autonomously designs and improves task-specific agents through continual learning with stateful prompts and reusable skills.

Ax Yufei Zhang, Tao Wang, Jingyi Zhang 3/20/2026

SRRM: Improving Recursive Transport Surrogates in the Small-Discrepancy Regime

Studies consistency and convergence rates of Recursive Rank Matching for computing Wasserstein distance surrogates in small-discrepancy regime.

Ax Samuel Ofosu Mensah, Maria Camila Roa Carvajal, Kerol Djoumessi, Philipp Berens 3/20/2026

Towards Interpretable Foundation Models for Retinal Fundus Images

Dual-IFM develops an interpretable-by-design foundation model for retinal fundus image analysis using self-supervised learning with local and global interpretability.

Ax Xiucheng Wang, Zhenye Chen, Nan Cheng 3/20/2026

Learn for Variation: Variationally Guided AAV Trajectory Learning in Differentiable Environments

Proposes variational guidance for autonomous aerial vehicle trajectory learning to address credit assignment and training instability in sparse reward RL settings.

Ax Xiucheng Wang, Yue Zhang, Nan Cheng 3/20/2026

BeamAgent: LLM-Aided MIMO Beamforming with Decoupled Intent Parsing and Alternating Optimization for Joint Site Selection and Precoding

BeamAgent combines LLMs with wireless beamforming optimization through decoupled intent parsing and alternating optimization, separating LLM reasoning from numerical computation.

Ax Xiao Feng, Bo Han, Zhanke Zhou, Jiaqi Fan, Jiangchao Yao, Ka Ho Li, Dahai Yu, Michael Kwok-Po Ng 3/20/2026

RewardFlow: Topology-Aware Reward Propagation on State Graphs for Agentic RL with Large Language Models

RewardFlow proposes topology-aware reward propagation on state graphs for RL-enhanced LLM agents, addressing sparse reward limitations without expensive dedicated reward models.

Ax Samuel Del Fr\'e, Gilberto A. Alou Angulo, Maurice Monnerville, Alejandro Rivero Santamar\'ia 3/20/2026

Data-driven construction of machine-learning-based interatomic potentials for gas-surface scattering dynamics: the case of NO on graphite

Machine-learning interatomic potential workflow for gas-surface scattering dynamics simulation on graphite.

Ax Xiucheng Wang, Zixuan Guo, Nan Cheng 3/20/2026

RadioDiff-FS: Physics-Informed Manifold Alignment in Few-Shot Diffusion Models for High-Fidelity Radio Map Construction

Physics-informed diffusion model for radio map construction using few-shot learning with manifold alignment.

Ax Tianci Luo, Jinpeng Wang, Shiyu Qin, Niu Lian, Yan Feng, Bin Chen, Chun Yuan, Shu-Tao Xia 3/20/2026

PromptHub: Enhancing Multi-Prompt Visual In-Context Learning with Locality-Aware Fusion, Concentration and Alignment

Introduces PromptHub for visual in-context learning using locality-aware fusion of multiple visual demonstrations with alignment and concentration mechanisms.

Ax Min Hun Lee 3/20/2026

From Accuracy to Readiness: Metrics and Benchmarks for Human-AI Decision-Making

Proposes evaluation framework beyond accuracy for human-AI collaborative decision-making, addressing miscalibrated reliance and team effectiveness.

Ax Sakshi Arya, Satarupa Bhattacharjee, Bharath K. Sriperumbudur 3/20/2026

Kernel Single-Index Bandits: Estimation, Inference, and Learning

Analyzes contextual bandits with single-index reward models where arms represent stable decisions and covariates evolve under bandit policy.

Ax Xinghao Zhao 3/20/2026

Entropy trajectory shape predicts LLM reasoning reliability: A diagnostic study of uncertainty dynamics in chain-of-thought

Studies entropy trajectory shape in chain-of-thought reasoning to predict LLM correctness without additional inference, testing on GSM8K with Qwen2.5-7B.

Ax Bruna Alves, Armando J. Pinho, S\'onia Gouveia 3/20/2026

Unified Taxonomy for Multivariate Time Series Anomaly Detection using Deep Learning

Proposes unified taxonomy with 11 dimensions for categorizing deep learning approaches to multivariate time series anomaly detection.

Ax Bruna Alves, Ana Martins, Armando J. Pinho, S\'onia Gouveia 3/20/2026

Revisiting OmniAnomaly for Anomaly Detection: performance metrics and comparison with PCA-based models

Compares OmniAnomaly stochastic recurrent model with PCA-based methods for multivariate time series anomaly detection using standardized evaluation protocols.

Ax Zening Sun, Zhengpeng Xie, Lichen Bai, Shitong Shao, Shuo Yang, Zeke Xie 3/20/2026

CRAFT: Aligning Diffusion Models with Fine-Tuning Is Easier Than You Think

CRAFT method for aligning diffusion models through fine-tuning, addressing limitations of SFT and DPO-style preference optimization approaches.

Ax Chun-Jui Wang, Jian-Ting Guo, Hung Guei, Chung-Chin Shih, Ti-Rong Wu, I-Chen Wu 3/20/2026

Evaluating Game Difficulty in Tetris Block Puzzle

Uses Stochastic Gumbel AlphaZero to evaluate difficulty in Tetris Block Puzzle variants, extending prior game-evaluation methods.

Ax Rui Chai 3/20/2026

Regret Bounds for Competitive Resource Allocation with Endogenous Costs

Online resource allocation algorithm with endogenous costs modeling competitive interactions between modules.

Ax Hangeol Chang, Changsun Lee, Seungjoon Rho, Junho Yeo, Jong Chul Ye 3/20/2026

Hypothesis-Conditioned Query Rewriting for Decision-Useful Retrieval

Hypothesis-Conditioned Query Rewriting improves RAG systems by rewriting queries to prioritize decision-relevant evidence over topical relevance.

Ax Pranay Anchuri, Matteo Campanelli, Paul Cesaretti, Rosario Gennaro, Tushar M. Jois, Hasan S. Kayman, Tugce Ozdemir 3/20/2026

Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference

Lightweight cryptographic framework for verifiable AI inference enabling clients to verify model outputs without rerunning computation.

Ax Quentin Guimard, Federico Bartsch, Simone Caldarella, Rahaf Aljundi, Elisa Ricci, Massimiliano Mancini 3/20/2026

SEM: Sparse Embedding Modulation for Post-Hoc Debiasing of Vision-Language Models

SEM method for post-hoc debiasing of CLIP via sparse embedding modulation to remove social and spurious biases.

Ax Ana\'isa Lucena, Ana Martins, Armando J. Pinho, S\'onia Gouveia 3/20/2026

Fast and Interpretable Autoregressive Estimation with Neural Network Backpropagation

Neural network approach to autoregressive time series estimation using backpropagation while preserving interpretability.

Ax Carlos Hinojosa, Clemens Grange, Bernard Ghanem 3/20/2026

SAVeS: Steering Safety Judgments in Vision-Language Models via Semantic Cues

SAVeS framework steers safety judgments in Vision-Language Models through semantic cues and textual/visual interventions.

Ax Sheng Liu, Panos Papadimitratos 3/20/2026

FedTrident: Resilient Road Condition Classification Against Poisoning Attacks in Federated Learning

FedTrident defends federated learning-based road classification against poisoning attacks from malicious participants.

Ax Maksym Del, Markus K\"angsepp, Marharyta Domnich, Ardi Tampuu, Lisa Yankovskaya, Meelis Kull, Mark Fishel 3/20/2026

How Uncertainty Estimation Scales with Sampling in Reasoning Models

Studies how uncertainty estimation scales with sampling in reasoning language models using self-consistency and verbalized confidence.

Ax Jonathan Lys, Vincent Gripon, Bastien Pasdeloup, Axel Marmoret, Lukas Mauch, Fabien Cardinaux, Ghouthi Boukli Hacene 3/20/2026

D5P4: Partition Determinantal Point Process for Diversity in Parallel Discrete Diffusion Decoding

D5P4 framework applies determinantal point processes to discrete diffusion decoding for diverse parallel text generation.

Ax Lei Yang, Han Wan, Min Zhang, Ling Liang 3/20/2026

Fast and Effective Computation of Generalized Symmetric Matrix Factorization

Algorithm for generalized symmetric matrix factorization with exactness properties and non-Lipschitz optimization.

Ax Skyler Seto, Pierre Ablin, Anastasiia Filippova, Jiayuan Ye, Louis Bethune, Angelos Katharopoulos, David Grangier 3/20/2026

Optimal Splitting of Language Models from Mixtures to Specialized Domains

Method for splitting pretrained language models into specialized domain-specific models using continued pretraining strategies.

Ax Swagat Padhan, Lakshya Jain, Bhavya Minesh Shah, Omkar Patil, Thao Nguyen, Nakul Gopalan 3/20/2026

Meanings and Measurements: Multi-Agent Probabilistic Grounding for Vision-Language Navigation

Multi-agent framework for grounding vision-language navigation using probabilistic reasoning about spatial relations and metric constraints.

Ax Shang-Jui Ray Kuo, Paola Cascante-Bonilla 3/20/2026

Do VLMs Need Vision Transformers? Evaluating State Space Models as Vision Encoders

Evaluates State Space Models as vision encoders for Vision-Language Models, comparing SSM backbones to transformer-based alternatives.

Ax Tianjiao Yu, Xinzhuo Li, Muntasir Wahed, Jerry Xiong, Yifan Shen, Ying Shen, Ismini Lourentzou 3/20/2026

DreamPartGen: Semantically Grounded Part-Level 3D Generation via Collaborative Latent Denoising

DreamPartGen generates semantically grounded 3D objects with part-level decomposition using text-to-3D diffusion methods.

Ax Dong Zhuo, Wenzhao Zheng, Sicheng Zuo, Siming Yan, Lu Hou, Jie Zhou, Jiwen Lu 3/20/2026

DriveTok: 3D Driving Scene Tokenization for Unified Multi-View Reconstruction and Understanding

DriveTok proposes efficient 3D tokenization for multi-view driving scenes to improve autonomous driving systems and world models.

Ax Zhuolin Yang, Zihan Liu, Yang Chen, Wenliang Dai, Boxin Wang, Sheng-Chieh Lin, Chankyu Lee, Yangyi Chen, Dongfu Jiang, Jiafan He, Renjie Pi, Grace Lam, Nayeon Lee, Alexander Bukharin, Mohammad Shoeybi, Bryan Catanzaro, Wei Ping 3/20/2026

Nemotron-Cascade 2: Post-Training LLMs with Cascade RL and Multi-Domain On-Policy Distillation

Nemotron-Cascade 2: 30B open-weight MoE LLM with strong reasoning and agentic capabilities, achieving IMO Gold Medal performance.

Ax Carlos Esteves, Ameesh Makadia 3/20/2026

Spectrally-Guided Diffusion Noise Schedules

Method for designing adaptive noise schedules in diffusion models for image and video generation using spectral guidance.

Ax Huaide Jiang, Yash Chaudhary, Yuping Wang, Zehao Wang, Raghav Sharma, Manan Mehta, Yang Zhou, Lichao Sun, Zhiwen Fan, Zhengzhong Tu, Jiachen Li 3/20/2026

NavTrust: Benchmarking Trustworthiness for Embodied Navigation

NavTrust benchmark evaluates trustworthiness of embodied navigation agents under real-world corruptions in Vision-Language Navigation and Object-Goal Navigation tasks.

Ax Shaojie Li, Pengwei Tang, Yong Liu 3/20/2026

Improved Learning Rates for Stochastic Optimization

Establishes improved learning rates for stochastic gradient descent and Nesterov accelerated gradient with generalization performance guarantees.

Ax Caleb Princewill Nwokocha 3/20/2026

Rule Extraction in Machine Learning: Chat Incremental Pattern Constructor

Chat Incremental Pattern Constructor extracts ordered token-transition rules from text for interpretable machine learning rule extraction.

Ax Miguel \'A. Carreira-Perpi\~n\'an, Suryabhan Singh Hada 3/20/2026

Inverse classification with logistic and softmax classifiers: efficient optimization

Optimization methods for inverse classification problems including counterfactual explanations and adversarial examples using logistic and softmax classifiers.