Ax Akash Dhasade, Rachid Guerraoui, Anne-Marie Kermarrec, Diana Petrescu, Rafael Pires, Mathis Randl, Martijn de Vos 17d ago

Efficient Federated Search for Retrieval-Augmented Generation using Lightweight Routing

Federated search mechanism for retrieval-augmented generation across distributed knowledge sources to reduce LLM hallucinations.

Ax Yihong Huang, Chen Chu, Fan Zhang, Liping Wang Fei Chen, Yu Lin, Ruiduan Li, Zhihao Li 17d ago

ShuffleGate: A Unified Gating Mechanism for Feature Selection, Model Compression, and Importance Estimation

ShuffleGate: unified gating mechanism for feature selection, model compression, and importance estimation in recommender systems.

Ax Ruwen Fulek, Markus Lange-Hegermann 17d ago

Approximately Equivariant Recurrent Generative Models for Quasi-Periodic Time Series with a Progressive Training Scheme

AEQ-RVAE-ST: recurrent variational autoencoder with progressive training for quasi-periodic time series generation.

Ax Mohamed Djilani, Thibault Simonetto, Karim Tit, Florian Tambon, Salah Ghamizi, Maxime Cordy, Mike Papadakis 17d ago

On the Robustness of Tabular Foundation Models: Test-Time Attacks and In-Context Defenses

Study of adversarial robustness in tabular foundation models like TabPFN and TabICL, examining test-time attacks and in-context defenses.

Ax Jacob Piland, Chris Sweet, Adam Czajka 17d ago

DiffGradCAM: A Class Activation Map Using the Full Model Decision to Solve Unaddressed Adversarial Attacks

DiffGradCAM improves class activation maps for CNNs by addressing adversarial vulnerabilities in gradient-based explanation methods.

Ax Hao Gu, Lujun Li, Hao Wang, Lei Wang, Zheyu Wang, Bei Liu, Jiacheng Liu, Qiyuan Zhu, Sirui Han, Yike Guo 17d ago

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook

BTC-LLM: sub-1-bit quantization framework for LLMs using learnable transformations and binary codebooks for extreme compression.

Ax Alvaro Almeida Gomez 17d ago

A Data-Driven Interpolation Method on Smooth Manifolds via Diffusion Processes and Voronoi Tessellations

Data-driven interpolation method for functions on smooth manifolds using Laplace-Beltrami operators and Voronoi tessellations with diffusion processes.

Ax Muhammad Awais Ali, Marlon Dumas, Fredrik Milani 17d ago

How Will My Business Process Unfold? Predicting Case Suffixes With Start and End Timestamps

Predicts case suffix in business processes with start/end timestamps for resource capacity planning using sequence models.

Ax Alejandro Almod\'ovar, Patricia A. Apell\'aniz, Alba Garrido, Fernando Fern\'andez-Salvador, Santiago Zazo, Juan Parras 17d ago

Interpretable Clinical Classification with Kolmogorov-Arnold Networks

Investigates Kolmogorov-Arnold Networks as interpretable alternatives to black-box models for clinical tabular data classification.

Ax Simon Pedro Galeano Munoz, Mustapha Bounoua, Giulio Franzese, Pietro Michiardi, Maurizio Filippone 17d ago

TENDE: Transfer Entropy Neural Diffusion Estimation

Neural diffusion method for estimating transfer entropy in time series addressing curse of dimensionality and convergence issues.

Ax Guanjie Cheng, Siyang Liu, Xinkui Zhao, Yishan Chen, Junqin Huang, Linghe Kong, Shiguang Deng 17d ago

ALPINE: Closed-Loop Adaptive Privacy Budget Allocation for Mobile Edge Crowdsensing

Adaptive privacy budget allocation framework for mobile edge crowdsensing balancing privacy, utility, and device overhead.

Ax Ayrat Abdullin, Denis Anikiev, Umair Bin Waheed 17d ago

Explainable AI for microseismic event detection

Applies XAI techniques (Grad-CAM, SHAP) to interpret PhaseNet deep neural network for microseismic event detection.

Ax Nadav Dym, Matthias Wellershoff, Efstratios Tsoukanis, Daniel Levy, Radu Balan 17d ago

Quantitative Bounds for Sorting-Based Permutation-Invariant Embeddings

Quantitative bounds analysis for permutation-invariant embeddings using sorting-based projections relevant to graph deep learning.

Ax Hangshuo Tian 17d ago

On the Interaction Between Chicken Swarm Rejuvenation and KLD-Adaptive Sampling in Particle Filters

Theoretical analysis of interactions between chicken swarm optimization-based particle rejuvenation and KLD-adaptive sampling in particle filters.

Ax Shanchuan Lin, Ceyuan Yang, Zhijie Lin, Hao Chen, Haoqi Fan 17d ago

Adversarial Flow Models

Generative model combining adversarial and flow-based families with native one-step/multi-step generation trained via adversarial objective.

Ax Colin Doumont, Donney Fan, Natalie Maus, Jacob R. Gardner, Henry Moss, Geoff Pleiss 17d ago

We Still Don't Understand High-Dimensional Bayesian Optimization

Research on high-dimensional Bayesian optimization showing simple Bayesian linear regression outperforms complex BO methods after geometric transformation.

Ax Hao Tang, Hao Chen, Chao Li 17d ago

Generalized Spherical Neural Operators: Green's Function Formulation

Neural operator framework for solving PDEs on spherical domains using Green's function formulation preserving rotational geometry.

Ax Xuwei Tan, Yao Ma, Xueru Zhang 17d ago

Understanding Structured Financial Data with LLMs: A Case Study on Fraud Detection

Case study applying LLMs to structured financial fraud detection data with focus on interpretability and feature analysis.

Ax Joyjit Roy, Samaresh Kumar Singh 17d ago

Comparative Evaluation of Embedding Representations for Financial News Sentiment Analysis

Comparative evaluation of embedding techniques for financial news sentiment analysis in resource-constrained environments.

Ax Carla Crivoi, Radu Tudor Ionescu 17d ago

Machine Unlearning in the Era of Quantum Machine Learning: An Empirical Study

First empirical study of machine unlearning in hybrid quantum-classical neural networks with adaptation of classical unlearning methods.

Ax Yusuf Brima, Marcellin Atemkeng 17d ago

From Classical Machine Learning to Tabular Foundation Models: An Empirical Investigation of Robustness and Scalability Under Class Imbalance in Emergency and Critical Care

Empirical study of tabular foundation models versus classical ML for healthcare applications under class imbalance in critical care.

Ax Lang Cao, Hui Ruan, Yongqian Li, Peng Chao, Wu Ning, Haonan Song, Renhong Chen, Yitong Li 17d ago

TreeAdv: Tree-Structured Advantage Redistribution for Group-Based RL

Tree-structured advantage redistribution method for group-based RL improving sample efficiency in LLM alignment on reasoning tasks.

Ax Rohan Tangri, Jan-Peter Calliess 17d ago

Constrained Policy Optimization with Cantelli-Bounded Value-at-Risk

Sample-efficient reinforcement learning algorithm for Value-at-Risk constrained optimization with safety guarantees during training.

Ax Ziqiao Shang, Lingyue Ge, Yang Chen, Shi-Yu Tian, Zhenyu Huang, Wenbo Fu, Yu-Feng Li, Lan-Zhe Guo 17d ago

MapTab: Are MLLMs Ready for Multi-Criteria Route Planning in Heterogeneous Graphs?

Benchmark for evaluating multimodal LLMs on multi-criteria route planning reasoning tasks in heterogeneous graphs.

Ax Wall Kim, Chaeyoung Song, Hanul Kim 17d ago

MultiModalPFN: Extending Prior-Data Fitted Networks for Multimodal Tabular Learning

Extension of TabPFN foundation model to handle multimodal tabular data combining images, text and structured features.

Ax Ruinan Jin, Yingbin Liang, Shaofeng Zou 17d ago

Why Adam Can Beat SGD: Second-Moment Normalization Yields Sharper Tails

Theoretical analysis explaining Adam optimizer's empirical advantages over SGD through second-moment normalization properties.

Ax Lukas K\"onig, Manuel Kuhn, David Kappel, Anand Subramoney 17d ago

Training event-based neural networks with exact gradients via Differentiable ODE Solving in JAX

JAX framework for gradient-based training of spiking neural networks using differentiable ODE solving with exact gradients.

Ax Jiayang Gao, Tianyi Zheng, Jiayang Zou, Fengxiang Yang, Shice Liu, Luyao Fan, Zheyu Zhang, Hao Zhang, Jinwei Chen, Peng-Tao Jiang, Bo Li, Jia Wang 17d ago

C$^2$FG: Control Classifier-Free Guidance via Score Discrepancy Analysis

Theoretical analysis of classifier-free guidance in diffusion models with bounds on score discrepancy for controlled guidance weights.

Ax Yuval Ran-Milo 17d ago

Attention Sinks Are Provably Necessary in Softmax Transformers: Evidence from Trigger-Conditional Tasks

Theoretical analysis proving attention sinks are functionally necessary in softmax Transformers for trigger-conditional tasks.

Ax Martin G. Frasch 17d ago

Minimum-Action Learning: Energy-Constrained Symbolic Model Selection for Physical Law Identification from Noisy Data

Framework for identifying symbolic physical laws from noisy data by minimizing action functional with sparsity and energy conservation.

Ax Huamin Chen, Xunzhuo Liu, Bowei He, Fuyuan Lyu, Yankai Chen, Xue Liu, Yuhan Liu, Junchen Jiang 17d ago

The Workload-Router-Pool Architecture for LLM Inference Optimization: A Vision Paper from the vLLM Semantic Router Project

vLLM Semantic Router architecture for optimizing LLM inference with routing mechanisms, semantic caching, and safety classification.

Ax Shreeram Murali, Cristian R. Rojas, Dominik Baumann 17d ago

Computationally lightweight classifiers with frequentist bounds on predictions

Computationally efficient classification algorithm with frequentist uncertainty bounds for safety-critical applications.

Ax Xiang Li, Yixuan Jia, Xiao Li, Jeffrey A. Fessler, Rongrong Wang, Qing Qu 17d ago

MCLR: Improving Conditional Modeling via Inter-Class Likelihood-Ratio Maximization and Unifying Classifier-Free Guidance with Alignment Objectives

Theoretical framework unifying classifier-free guidance with alignment objectives in diffusion models for generative modeling.

Ax Noah Bergam, Samuel Deng, Daniel Hsu 17d ago

A One-Inclusion Graph Approach to Multi-Group Learning

Theoretical analysis of sample complexity bounds for multi-group learning using one-inclusion graph prediction strategy.

Ax Andi Nika, Debmalya Mandal, Parameswaran Kamalaruban, Adish Singla, Goran Radanovi\'c 17d ago

Corruption-robust Offline Multi-agent Reinforcement Learning From Human Feedback

Multi-agent reinforcement learning framework addressing robustness to data corruption in preference-based learning from human feedback.

Ax Chien-Ping Lu 17d ago

Continued AI Scaling Requires Repeated Efficiency Doublings

Analysis of AI scaling requiring repeated efficiency doublings, distinguishing logical compute from physical resource implementation efficiency.

Ax Anci Lin, Xiaohong Liu, Zhiwen Zhang, Wenju Zhao 17d ago

Biomimetic causal learning for microstructure-forming phase transitions

Biomimetic physics-informed neural networks for modeling microstructure-forming phase transitions in cellular matrices.

Ax Brandon Yee, Pairie Koh 17d ago

PI-JEPA: Label-Free Surrogate Pretraining for Coupled Multiphysics Simulation via Operator-Split Latent Prediction

Physics-informed label-free pretraining method for coupled multiphysics simulation surrogates using operator-split latent prediction.

Ax Dharmesh Tailor, Nicol\`o Felicioni, Kamil Ciosek 17d ago

A Bayesian Information-Theoretic Approach to Data Attribution

Bayesian information-theoretic approach to training data attribution that traces model predictions to influential training examples for interpretability.

Ax Minglu Liu, Cunchen Hu, Liangliang Xu, Fengming Tang, Ruijia Wang, Fu Yu 17d ago

STQuant: Spatio-Temporal Adaptive Framework for Optimizer Quantization in Large Multimodal Model Training

STQuant framework for adaptive spatio-temporal quantization of optimizer states during large multimodal model training to reduce memory costs.

Ax Nozomu Kobayashi, Yoshiyuki Suimon, Koichi Miyamoto 17d ago

Time series generation for option pricing on quantum computers using tensor network

Quantum computing approach for option pricing using tensor networks to prepare quantum states encoding asset price distributions.

Ax Tim Johnsen, Marco Levorato 17d ago

NaviSlim: Adaptive Context-Aware Navigation and Sensing via Dynamic Slimmable Networks

Adaptive neural networks for autonomous micro-drones with computational constraints via dynamic slimmable network architecture.

Ax Takuro Kutsuna 17d ago

A Probabilistic Formulation of Offset Noise in Diffusion Models

Theoretical analysis of offset noise in diffusion models to address brightness value generation challenges in large-scale models.

Ax Huawei Lin, Yingjie Lao, Weijie Zhao 17d ago

DMin: Scalable Training Data Influence Estimation for Diffusion Models

DMin framework for scalable training data influence estimation in diffusion models, enabling identification of influential training samples on generated outputs.

Ax Ximing Xing, Juncheng Hu, Ziteng Xue, Jing Zhang, Buyu Li, Sheng Wang, Dong Xu, Qian Yu 17d ago

SVGFusion: A VAE-Diffusion Transformer for Vector Graphic Generation

VAE-diffusion framework for generating high-quality SVG graphics from text with structural understanding.

Ax Antoni Kowalczuk, Jan Dubi\'nski, Franziska Boenisch, Adam Dziedzic 17d ago

Privacy Attacks on Image AutoRegressive Models

Comprehensive privacy attack analysis on image autoregressive models, identifying membership inference and extraction vulnerabilities.

Ax Mohammad Albinhassan, Pranava Madhyastha, Alessandra Russo 17d ago

$\texttt{SEM-CTRL}$: Semantically Controlled Decoding

Method for enforcing syntactic and semantic constraints in LLM decoding through MCTS-guided token-level control.

Ax Musfiqur Rahman, SayedHassan Khatoonabadi, Emad Shihab 17d ago

OpenClassGen: A Large-Scale Corpus of Real-World Python Classes for LLM Research

Large-scale corpus of 324,843 Python classes from open-source projects for training and evaluating LLMs on code generation.

Ax Dezheng Han, Yibin Jia, Ruxiao Chen, Wenjie Han, Shuaishuai Guo, Jianbo Wang 17d ago

ReCellTy: Domain-Specific Knowledge Graph Retrieval-Augmented LLMs Reasoning Workflow for Single-Cell Annotation

RAG-based LLM workflow using domain-specific knowledge graph for automated single-cell type annotation in biology.

Ax Rui Melo, Claudia Mamede, Andre Catarino, Rui Abreu, Henrique Lopes Cardoso 17d ago

Are Sparse Autoencoders Useful for Java Function Bug Detection?

Study evaluating sparse autoencoders for detecting bugs in Java code, addressing software vulnerability detection.