Ax Wihan van der Heever, Keane Ong, Ranjan Satapathy, Erik Cambria 3/24/2026

Beyond Correlation: Refutation-Validated Aspect-Based Sentiment Analysis for Explainable Energy Market Returns

Aspect-based sentiment analysis with refutation validation for energy market financial predictions.

Ax Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou, Wenze Ren, Yu-Han Huang, Yun-Shao Tsai, Chien-Cheng Chen, Yu Tsao, Yuan-Fu Liao, Shrikanth Narayanan, James Glass, Hung-yi Lee 3/24/2026

TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild

TaigiSpeech: Low-resource speech dataset in Taiwanese with 3k utterances and in-the-wild data mining approach.

Ax Ruiqi Xian, Jing Liang, He Yin, Xuewei Qi, Dinesh Manocha 3/24/2026

GaussianSSC: Triplane-Guided Directional Gaussian Fields for 3D Semantic Completion

GaussianSSC: 3D semantic scene completion using Gaussian-weighted fields and triplane guidance.

Ax Mohammad Eslami, Dhanvinkumar Ganeshkumar, Saber Kazeminasab, Michael G. Morley, Michael V. Boland, Michael M. Lin, John B. Miller, David S. Friedman, Nazlee Zebardast, Lucia Sobrin, Tobias Elze 3/24/2026

CataractSAM-2: A Domain-Adapted Model for Anterior Segment Surgery Segmentation and Scalable Ground-Truth Annotation

CataractSAM-2: Domain-adapted Segment Anything Model 2 for surgical video segmentation and automated annotation.

Ax Hyoseok Park, Yeonsang Park 3/24/2026

PRISM: Breaking the O(n) Memory Wall in Long-Context LLM Inference via O(1) Photonic Block Selection

PRISM: Photonic accelerator design achieving O(1) memory access for long-context LLM inference via block selection.

Ax Jing Zhang, Chenping Hou 3/24/2026

Feature Incremental Clustering with Generalization Bounds

Algorithm for clustering data streams with incrementally expanding feature spaces, with theoretical guarantees.

Ax Zijun Qin, Jingxuan Huang, Zesong Fei, Haichuan Ding, Yulin Shao, Xianhao Chen 3/24/2026

Rateless DeepJSCC for Broadcast Channels: a Rate-Distortion-Complexity Tradeoff

Deep learning approach for joint source-channel coding in wireless broadcast with rate-distortion tradeoffs.

Ax Amil Khanzada, Takuji Takemoto 3/24/2026

Engineering Distributed Governance for Regional Prosperity: A Socio-Technical Framework for Mitigating Under-Vibrancy via Human Data Engines

Framework for regional economic development using human data engines to address demographic decline in tourism.

Ax Shenghan Zhang, Run Ling, Ke Cao, Ao Ma, Zhanjie Zhang 3/24/2026

FedCVU: Federated Learning for Cross-View Video Understanding

Federated learning framework for privacy-preserving multi-camera video understanding across heterogeneous viewpoints.

Ax Bowen Chen, Namgi Han, Yusuke Miyao 3/24/2026

A Comparative Analysis of LLM Memorization at Statistical and Internal Levels: Cross-Model Commonalities and Model-Specific Signatures

Comparative study of memorization mechanisms across multiple LLM model series including Pythia and OpenLLaMa.

Ax Kangbo Zhao, Miaoxin Guan, Xiang Chen, Yukai Shi, Jinshan Pan 3/24/2026

Cross-Scenario Deraining Adaptation with Unpaired Data: Superpixel Structural Priors and Multi-Stage Pseudo-Rain Synthesis

Domain adaptation method for image deraining using unpaired data and pseudo-rain synthesis.

Ax Shailesh Garg, Luis Mandl, Somdatta Goswami, Souvik Chakraborty 3/24/2026

SPINONet: Scalable Spiking Physics-informed Neural Operator for Computational Mechanics Applications

Energy-efficient spiking neural network for physics-informed operator learning in computational mechanics.

Ax Shailesh Garg, Souvik Chakraborty 3/24/2026

CoNBONet: Conformalized Neuroscience-inspired Bayesian Operator Network for Reliability Analysis

Neuroscience-inspired surrogate model for fast reliability analysis of nonlinear stochastic dynamical systems.

Ax Kazuki Matsumoto, Ren Uchida, Kohei Yatabe 3/24/2026

LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation

Lipschitz-continuous neural network architecture for certified robustness in audio signal processing.

Ax Shuo Wang, Ziyu Chen, Ming Tang 3/24/2026

CurvZO: Adaptive Curvature-Guided Sparse Zeroth-Order Optimization for Efficient LLM Fine-Tuning

Memory-efficient zeroth-order optimization method with adaptive curvature guidance for fine-tuning large language models.

Ax Harsh Wadhwa, Rahul Bhowmick, Naipunnya Raj, Rajiv Sangle, Ruchira V. Bhat, Krishnakumar Sabapathy 3/24/2026

Model selection in hybrid quantum neural networks with applications to quantum transformer architectures

Framework for model selection and evaluation of hybrid quantum-classical transformer architectures.

Ax Emma Hannula, Jana de Wiljes, Matthew T. Moores, Heikki Haario, Lassi Roininen 3/24/2026

Identifiability and amortized inference limitations in Kuramoto models

Amortized Bayesian inference method for parameter estimation in Kuramoto oscillator network models.

Ax Gianluca Fontanesi, Luca Barbieri, Lorenzo Galati Giordano, Alfonso Fernandez Duran, Thorsten Wild 3/24/2026

Cluster-Specific Predictive Modeling: A Scalable Solution for Resource-Constrained Wi-Fi Controllers

Clustering-based predictive modeling approach for resource-constrained Wi-Fi network management.

Ax Jesper B. Christensen, Ciaran Bench, Spencer A. Thomas, H\"usn\"u Aslan, David Balslev-Harder, Nadia A. S. Smith, Alessandra Manzin 3/24/2026

Ctrl-A: Control-Driven Online Data Augmentation

Automated data augmentation algorithm using control theory principles for dynamic adjustment during image model training.

Ax Donald Shenaj, Federico Errica, Antonio Carta 3/24/2026

Not All Layers Are Created Equal: Adaptive LoRA Ranks for Personalized Image Generation

Adaptive approach for selecting LoRA ranks per layer in diffusion model fine-tuning for personalized image generation.

Ax Suchuan Dong, Yuchuan Zhang 3/24/2026

A Novel Method for Enforcing Exactly Dirichlet, Neumann and Robin Conditions on Curved Domain Boundaries for Physics Informed Machine Learning

Method for enforcing boundary conditions in physics-informed neural networks on curved domains.

Ax Chedly Ben Azizi, Claire Guilloteau, Gilles Roussel, Matthieu Puigt 3/24/2026

A Latent Representation Learning Framework for Hyperspectral Image Emulation in Remote Sensing

Latent representation framework for synthetic hyperspectral image generation in remote sensing applications.

Ax L. Riso, M. G. Zoia 3/24/2026

Structural Concentration in Weighted Networks: A Class of Topology-Aware Indices

Framework for measuring concentration in weighted networks considering topology of relationships.

Ax Guannan Lai, Da-Wei Zhou, Zhenguo Li, Han-Jia Ye 3/24/2026

The Golden Subspace: Where Efficiency Meets Generalization in Continual Test-Time Adaptation

Method for efficient online adaptation of neural networks to distribution shifts with minimal parameter updates.

Ax Peter Fasogbon, Ugurcan Budak, Patrice Rondao Alface, Hamed Rezazadegan Tavakoli 3/24/2026

Camera-Agnostic Pruning of 3D Gaussian Splats via Descriptor-Based Beta Evidence

Pruning technique for 3D Gaussian splatting representations that is independent of camera parameters.

Ax Marco Arazzi, Vignesh Kumar Kembu, Antonino Nocera 3/24/2026

SecureBreak -- A dataset towards safe and secure models

Dataset and methods for improving security alignment and robustness of large language models against adversarial attacks.

Ax Hubert Leterme, Andreas Tersenov, Jalal Fadili, Jean-Luc Starck 3/24/2026

A plug-and-play approach with fast uncertainty quantification for weak lensing mass mapping

Deep learning method for reconstructing dark matter distribution from weak lensing measurements for cosmological surveys.

Ax Dong Heon Cho, Boyuan Chen 3/24/2026

RAFL: Generalizable Sim-to-Real of Soft Robots with Residual Acceleration Field Learning

RAFL learns residual acceleration fields to reduce sim-to-real gap in soft robot control with differentiable simulators.

Ax Atticus Rex, Elizabeth Qian, David Peterson 3/24/2026

MAGPI: Multifidelity-Augmented Gaussian Process Inputs for Surrogate Modeling from Scarce Data

MAGPI augments Gaussian processes with multifidelity data to improve surrogate modeling accuracy from limited high-fidelity observations.

Ax Risa Shinoda, Kaede Shiohara, Nakamasa Inoue, Hiroaki Santo, Fumio Okura 3/24/2026

AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference

AnimalCLAP combines taxonomy-aware training with language-audio pretraining for species recognition and trait inference from vocalizations.

Ax Syed Usama Imtiaz, Mitra Nasr Azadani, Nasrin Alamdari 3/24/2026

SpecTM: Spectral Targeted Masking for Trustworthy Foundation Models

SpecTM applies physics-informed spectral masking to Earth observation foundation models for trustworthy band reconstruction in remote sensing.

Ax Joanna Zou, Youssef Marzouk 3/24/2026

Data Curation for Machine Learning Interatomic Potentials by Determinantal Point Processes

Uses determinantal point processes for efficient data curation to select informative atomic configurations for ML interatomic potential training.

Ax A. Chervov, F. Levkovich-Maslyuk, A. Smolensky, F. Khafizov, I. Kiselev, D. Melnikov, I. Koltsov, S. Kudashev, D. Shiltsov, M. Obozov, S. Krymskii, V. Kirova, E. V. Konstantinova, A. Soibelman, S. Galkin, L. Grunwald, A. Kotov, A. Alexandrov, S. Lytkin, D. Fedoriaka, A. Chevychelov, Z. Kogan, A. Natyrova, L. Cheldieva, O. Nikitina, S. Fironov, A. Vakhrushev, A. Lukyanenko, V. Ilin, D. Gorodkov, N. Bogachev, I. Gaiur, M. Zaitsev, F. Petrov, L. Petrov, T. Gaintseva, A. Gavrilova, M. N. Smirnov, N. Kalinin, A. Khan, K. Jung, H. Mousset, H. Isambert, O. Debeaupuis 3/24/2026

CayleyPy-4: AI-Holography. Towards analogs of holographic string dualities for AI tasks

Proposes discrete holographic string duality analogues for AI tasks on large graphs with speculative connections to GPT and RL systems.

Ax Tom Biskupski, Stephan Kleber 3/24/2026

Evaluating the Reliability and Fidelity of Automated Judgment Systems of Large Language Models

Evaluates reliability and fidelity of using LLMs as judges for automated assessment of victim ML model outputs and quality.

Ax Chi Zhang, Xixi Hu, Bo Liu, Qiang Liu 3/24/2026

Gumbel Distillation for Parallel Text Generation

Gumbel Distillation enables parallel decoders to match autoregressive LLM quality by learning joint token distributions via novel distillation.

Ax Yanchen Jiang, Zhe Feng, Christopher P. Mah, Aranyak Mehta, Di Wang 3/24/2026

One Model, Two Markets: Bid-Aware Generative Recommendation

GEM-Rec unifies semantic and commercial retrieval in generative recommender systems by incorporating bid-awareness for monetization.

Ax Claudia Islas-Vargas, L. Ricardo Montoya, Carlos A. Vital-Jos\'e, Oliver T. Unke, Klaus-Robert M\"uller, Huziel E. Sauceda 3/24/2026

Characterizing High-Capacity Janus Aminobenzene-Graphene Anode for Sodium-Ion Batteries with Machine Learning

Uses SpookyNet ML force field and DFT to characterize sodium storage in aminobenzene-graphene anodes for battery design.

Ax Kelly Cui, Nikhil Prakash, Ayush Raina, David Bau, Antonio Torralba, Tamar Rott Shaham 3/24/2026

The Dual Mechanisms of Spatial Reasoning in Vision-Language Models

Analyzes two concurrent mechanisms in VLMs for spatial reasoning: content-independent spatial tokens and language-based spatial relations.

Ax Haichao Zhang, Yijiang Li, Shwai He, Tushar Nagarajan, Mingfei Chen, Jianglin Lu, Ang Li, Yun Fu 3/24/2026

ThinkJEPA: Empowering Latent World Models with Large Vision-Language Reasoning Model

ThinkJEPA combines V-JEPA latent world models with vision-language models for improved long-horizon semantic reasoning in video prediction.

Ax Shivam Duggal, Xingjian Bai, Zongze Wu, Richard Zhang, Eli Shechtman, Antonio Torralba, Phillip Isola, William T. Freeman 3/24/2026

End-to-End Training for Unified Tokenization and Latent Denoising

UNITE enables end-to-end training of latent diffusion models with unified tokenization without separate staging phases.

Ax Umair Nawaz, Ahmed Heakl, Ufaq Khan, Abdelrahman Shaker, Salman Khan, Fahad Shahbaz Khan 3/24/2026

WorldCache: Content-Aware Caching for Accelerated Video World Models

WorldCache accelerates video diffusion Transformers via physics-aware feature caching across denoising steps with content-aware strategies.

Ax Di Chen, Jeff M. Phillips 3/24/2026

Relative Error Embeddings for the Gaussian Kernel Distance

Analyzes approximation quality of random Fourier features for Gaussian kernel RKHS embeddings with relative error bounds.

Ax Caleb Ju, Guanghui Lan 3/24/2026

Policy Optimization over General State and Action Spaces

Generalizes policy mirror descent for RL over continuous/general state and action spaces with convergence guarantees.

Ax Daiqing Qi, Handong Zhao, Sheng Li 3/24/2026

Better Generative Replay for Continual Federated Learning

Introduces continual federated learning with generative replay for incremental task learning across distributed clients without storing history data.

Ax Liang Yan, Shengzhong Zhang, Bisheng Li, Menglin Yang, Chen Yang, Min Zhou, Weiyang Ding, Yutong Xie, Zengfeng Huang 3/24/2026

Geometric Imbalance in Semi-Supervised Node Classification

Theoretical analysis of geometric imbalance problem in semi-supervised graph node classification on imbalanced datasets.

Ax Rickard Br\"annvall, Tony Zhang, Henrik Forsgren, Andrei Stoian, Fredrik Sandin, Marcus Liwicki 3/24/2026

Inhibitor Transformers and Gated RNNs for Torus Efficient Fully Homomorphic Encryption

FHE-compatible neural architectures using modified Transformers and RNNs for privacy-preserving ML with reduced computational complexity.

Ax Ziao Yang, Han Yue, Jian Chen, Hongfu Liu 3/24/2026

Revisit, Extend, and Enhance Hessian-Free Influence Functions

Extends Hessian-free influence functions for deep models, enabling sample importance assessment for interpretation and noisy label detection.

Ax Jingyang Ou, Shen Nie, Kaiwen Xue, Fengqi Zhu, Jiacheng Sun, Zhenguo Li, Chongxuan Li 3/24/2026

Your Absorbing Discrete Diffusion Secretly Models the Conditional Distributions of Clean Data

Reveals absorbing discrete diffusion models implicitly model conditional distributions via concrete score functions for language modeling.

Ax Kevin Qiu, W{\l}adys{\l}aw Pa{\l}ucki, Krzysztof Ciebiera, Pawe{\l} Fija{\l}kowski, Marek Cygan, {\L}ukasz Kuci\'nski 3/24/2026

RoboMorph: Evolving Robot Morphology using Large Language Models

Automated modular robot design generation using LLMs and evolutionary algorithms with grammar-based representation and RL refinement.

Ax Caleb Ju, Guanghui Lan 3/24/2026

Strongly-polynomial time and validation analysis of policy gradient methods

Policy gradient methods with novel advantage gap termination criterion achieving strongly-polynomial convergence independent of optimal policy distribution.