Ax Juwei Yue, Chuanrui Hu, Jiawei Sheng, Zuyi Zhou, Wenyuan Zhang, Tingwen Liu, Li Guo, Yafeng Deng 2d ago

HyperMem: Hypergraph Memory for Long-Term Conversations

HyperMem: hypergraph-based memory architecture for conversational agents enabling long-term context tracking and high-order associations.

Ax Nishikanta Mohanty, Bikash K. Behera, Badshah Mukherjee, Pravat Dash 2d ago

QARIMA: A Quantum Approach To Classical Time Series Analysis

Quantum-inspired ARIMA methodology combining quantum autocorrelation with variational quantum circuits for time series analysis.

Ax Rui Gan, Junyi Ma, Pei Li, Xingyou Yang, Kai Chen, Sikai Chen, Bin Ran 2d ago

CrashSight: A Phase-Aware, Infrastructure-Centric Video Benchmark for Traffic Crash Scene Understanding and Reasoning

Vision-language benchmark (CrashSight) for evaluating traffic crash scene understanding from infrastructure perspective.

Ax Yunsong Zhou, Hangxu Liu, Xuekun Jiang, Xing Shen, Yuanzhen Zhou, Hui Wang, Baole Fang, Yang Tian, Mulin Yu, Qiaojun Yu, Li Ma, Hengjie Li, Hanqing Wang, Jia Zeng, Jiangmiao Pang 2d ago

SIM1: Physics-Aligned Simulator as Zero-Shot Data Scaler in Deformable Worlds

Physics-aligned simulator (SIM1) for generating synthetic data in deformable object robotic manipulation tasks.

Ax Ruiyao Xu, Kaize Ding 2d ago

GNN-as-Judge: Unleashing the Power of LLMs for Graph Learning with GNN Feedback

Framework combining LLMs with graph neural networks for text-attributed graph learning in low-resource settings using GNN feedback.

Ax Abhilasha Saroj, Shaked Regev, Guanhao Xu, Jinghui Yuan, Roy Luo, Ross Wang 2d ago

Memory-Guided Trust-Region Bayesian Optimization (MG-TuRBO) for High Dimensions

Bayesian optimization method (MG-TuRBO) for high-dimensional traffic simulation calibration, comparing genetic algorithms with Bayesian approaches.

Ax Ali Slim, Haydar Hamieh, Jawad Kotaich, Yehya Ghosn, Mahdi Chehimi, Ammar Mohanna, Hasan Abed Al Kader Hammoud, Bernard Ghanem 2d ago

QuanBench+: A Unified Multi-Framework Benchmark for LLM-Based Quantum Code Generation

QuanBench+ unified benchmark for LLM quantum code generation across Qiskit, PennyLane, Cirq with 42 aligned executable tasks.

Ax Pavel Golikov, Evgenii Opryshko, Gennady Pekhimenko, Mark C. Jeffrey 2d ago

Robust Reasoning Benchmark

Benchmark evaluating robustness of LLM reasoning with 14 perturbation techniques applied to mathematical reasoning tasks.

Ax Matheus Vin\'icius Todescato, Joel Lu\'is Carbonera 2d ago

Silhouette Loss: Differentiable Global Structure Learning for Deep Representations

Silhouette loss function for learning discriminative representations with explicit geometric properties in embedding space.

Ax Rasched Haidari, Sam Martin, Maxime Allard 2d ago

Distilling Genomic Models for Efficient mRNA Representation Learning via Embedding Matching

Distillation framework compressing genomic foundation models for efficient mRNA representation learning.

Ax Syed Rameez Naqvi, Lu Peng 2d ago

MolPaQ: Modular Quantum-Classical Patch Learning for Interpretable Molecular Generation

Quantum-classical hybrid molecular generator using VAE and quantum computing for interpretable drug discovery.

Ax Yeping Jin, Jiaming Hu, Ioannis Ch. Paschalidis 2d ago

Distributionally Robust Token Optimization in RLHF

DRTO combines token-level RLHF with distributional robustness to improve LLM resilience to input perturbations and formatting changes.

Ax Phong Lam, Ha-Linh Nguyen, Thu-Trang Nguyen, Son Nguyen, Hieu Dinh Vo 2d ago

Structured Exploration and Exploitation of Label Functions for Automated Data Annotation

Automated label function generation for data annotation using LLMs with structured exploration-exploitation strategy.

Ax Krisanu Sarkar 2d ago

On the Spectral Geometry of Cross-Modal Representations: A Functional Map Diagnostic for Multimodal Alignment

Analysis of cross-modal alignment between vision and language encoders using functional map framework from computational geometry.

Ax Abdulrahman Albaiz, Fathi Amsaad 2d ago

Fully Autonomous Z-Score-Based TinyML Anomaly Detection on Resource-Constrained MCUs Using Power Side-Channel Data

TinyML Z-score anomaly detection system running on resource-constrained microcontrollers using power side-channel data.

Ax Jun Liu, Ying Chen, Ziqian Lu, Qinyue Tong, Jun Tang 2d ago

Multivariate Time Series Anomaly Detection via Dual-Branch Reconstruction and Autoregressive Flow-based Residual Density Estimation

Dual-branch reconstruction method for multivariate time series anomaly detection using autoregressive flow-based density estimation.

Ax Chuxu Song, Zhencan Peng, Jiuqi Wei, Chuanhui Yang 2d ago

CSAttention: Centroid-Scoring Attention for Accelerating LLM Inference

CSAttention: sparse attention mechanism for accelerating LLM inference by reducing KV-cache bottlenecks through centroid-scoring without retraining.

Ax David Ramos, Lucas Lacasa, Ferm\'in Guti\'errez, Eusebio Valero, Gonzalo Rubio 2d ago

FluidFlow: a flow-matching generative model for fluid dynamics surrogates on unstructured meshes

Flow-matching generative model for CFD surrogate modeling on unstructured meshes as alternative to deep learning approaches.

Ax Matthew DosSantos DiSorbo, Harang Ju 2d ago

Act or Escalate? Evaluating Escalation Behavior in Automation with Language Models

Framework evaluating when LLMs should act versus escalate decisions using uncertainty estimation across five real-world domains.

Ax Ha Na Cho, Daniel Eisenberg, Cheryl King, Kai Zheng 2d ago

EngageTriBoost: Predictive Modeling of User Engagement in Digital Mental Health Intervention Using Explainable Machine Learning

Machine learning system predicting user engagement in digital mental health interventions using explainable ML methods.

Ax Brendan R. Hogan, Xiwen Chen, James T. Wilson, Kashif Rasul, Adel Boyarsky, Thomas Kamei, Anderson Schneider, Yuriy Nevmyvaka 2d ago

AlphaLab: Autonomous Multi-Agent Research Across Optimization Domains with Frontier LLMs

AlphaLab autonomous research system using frontier LLMs as agents to automate full experimental cycles in optimization domains without human intervention.

Ax Ivan Viakhirev, Kirill Borodin, Grach Mkrtchian 2d ago

From Dispersion to Attraction: Spectral Dynamics of Hallucination Across Whisper Model Scales

Analysis of hallucination phase transitions in Whisper ASR models using spectral sensitivity theorem and eigenspectra analysis.

Ax H. Xu, B. He, S. Wang 2d ago

Joint Interference Detection and Identification via Adversarial Multi-task Learning

Multi-task learning for wireless interference detection and identification using adversarial training methods.

Ax Zhuang Qi, Ying-Peng Tang, Lei Meng, Guoqing Chao, Lei Wu, Han Yu, Xiangxu Meng 2d ago

From Selection to Scheduling: Federated Geometry-Aware Correction Makes Exemplar Replay Work Better under Continual Dynamic Heterogeneity

Federated learning approach using exemplar replay to reduce catastrophic forgetting in continual learning with dynamic heterogeneity.

Ax Ivo Nowak 2d ago

StructRL: Recovering Dynamic Programming Structure from Learning Dynamics in Distributional Reinforcement Learning

StructRL: recovers dynamic programming structure from distributional RL learning dynamics. Bridges data-driven and structured approaches for stable learning.

Ax Yesmine Abdennadher, Philip N. Garner 2d ago

Practical Bayesian Inference for Speech SNNs: Uncertainty and Loss-Landscape Smoothing

Bayesian inference for spiking neural networks in speech processing. Explores weight uncertainty and loss landscape smoothing for temporal tasks.

Ax Yongchan Chun, Chanhee Park, Jeongho Yoon, Jaehyung Seo, Heuiseok Lim 2d ago

Evidential Transformation Network: Turning Pretrained Models into Evidential Models for Post-hoc Uncertainty Estimation

Evidential Transformation Network: adapts pretrained models for post-hoc uncertainty estimation. Efficient alternative to ensembles/MC dropout for deployed models.

Ax Rahul D Ray, Utkarsh Srivastava 2d ago

VOLTA: The Surprising Ineffectiveness of Auxiliary Losses for Calibrated Deep Learning

VOLTA: benchmark comparing uncertainty quantification methods for deep learning. Evaluates 10 UQ baselines across modalities and distribution shifts.

Ax Ramakrishnan Krishnamurthy, Arpit Agarwal, Lakshminarayanan Subramanian, Maximilian Nickel 2d ago

Creator Incentives in Recommender Systems: A Cooperative Game-Theoretic Approach for Stable and Fair Collaboration in Multi-Agent Bandits

Game-theoretic analysis of creator incentives in multi-agent recommender systems. Cooperative game formulation for fair collaboration in bandit problems.

Ax Maxim Ostroukhov, Ruslan Mikhailov, Vladimir Iashin, Artem Sokolov, Andrei Akshonov, Vitaly Protasov, Dmitrii Beloborodov, Vince Mullin, Roman Yokunda Enzmann, Georgios Kolovos, Jason Renders, Pavel Nesterov, Anton Repushko 2d ago

PRAGMA: Revolut Foundation Model

PRAGMA: foundation models for banking event sequences. Transformer-based architecture with self-supervised pretraining on financial transaction data.

Ax Fengwei Teng, Jinyi Bai, Xinhao Yao, Demi Ruohan Wang, Jiahao Zhao, Zhijiang Guo 2d ago

Skip-Connected Policy Optimization for Implicit Advantage

Skip-Connected Policy Optimization (SKPO) for reinforcement learning with reasoning tasks. Improves upon GRPO by addressing high-variance advantage estimation.

Ax Nan Huang, Xiaoxiao Zhou, Junxia Cui, Mario Tapia-Pacheco, Tiffany Amariuta, Yang Li, Jingbo Shang 2d ago

EvoLen: Evolution-Guided Tokenization for DNA Language Model

EvoLen: evolution-guided tokenization approach for DNA language models. Addresses fundamental tokenization design challenges in biological sequence modeling.

Ax Charles Arnal, Vivien Cabannes, Taco Cohen, Julia Kempe, Remi Munos 2d ago

Efficient RL Training for LLMs with Experience Replay

Experience replay for LLM post-training RL formalizing optimal buffer design as trade-off between sample efficiency and data freshness.

Ax Tiejin Chen, Huaiyuan Yao, Jia Chen, Evangelos E. Papalexakis, Hua Wei 2d ago

Every Response Counts: Quantifying Uncertainty of LLM-based Multi-Agent Systems through Tensor Decomposition

Tensor decomposition method quantifying uncertainty in LLM-based multi-agent systems accounting for communication and role dependencies.

Ax Diyi Hu, Bhaskar Krishnamachari 2d ago

Wireless Communication Enhanced Value Decomposition for Multi-Agent Reinforcement Learning

CLOVER framework for multi-agent RL cooperation conditioning value decomposition on realistic wireless communication graphs.

Ax Hananel Hazan, Yanbo Zhang, Benedikt Hartl, Michael Levin 2d ago

A Little Rank Goes a Long Way: Random Scaffolds with LoRA Adapters Are All You Need

LottaLoRA training paradigm showing frozen random backbones with trained LoRA adapters recover 96-100% performance across diverse tasks.

Ax Julian Quick, Marcus Binder Nilsen, Andreas Bechmann, Tran Nguyen Le, Pierre-Elouan Mikael Rethore 2d ago

Adversarial Sensor Errors for Safe and Robust Wind Turbine Fleet Control

Adversarial sensor error framework for robust wind turbine fleet control against measurement errors and hacking.

Ax Mingjie Hu, Siyang Gao, Jian-qiang Hu, Enlu Zhou 2d ago

Adaptive Simulation Experiment for LLM Policy Optimization

Adaptive simulation experiment framework using pairwise comparisons to optimize LLM policies for operations management tasks.

Ax Zhaolin Gao (Sid), Yu (Sid), Wang, Bo Liu, Thorsten Joachims, Kiant\'e Brantley, Wen Sun 2d ago

$p1$: Better Prompt Optimization with Fewer Prompts

Prompt optimization method decomposing reward variance into response and prompt variance to identify task amenability to optimization.

Ax Yashodhan D. Hakke, Almuatazbellah M. Boker, Lamine Mili, Michael von Spakovsky, Hoda Eldardiry 2d ago

Alleviating Community Fear in Disasters via Multi-Agent Actor-Critic Reinforcement Learning

Multi-agent actor-critic reinforcement learning for disaster resilience controlling power, communication, and emergency response systems.

Ax Haonan Zhu, Adrienne Deganutti, Elad Hirsch, Purvanshi Mehta 2d ago

Structural Evaluation Metrics for SVG Generation via Leave-One-Out Analysis

Evaluation metrics for SVG generation via element-level structural analysis using leave-one-out evaluation.

Ax Mehran Taghian, Yunke Peng, Xing Huang, Yao Wang, Yaoyuan Wang, Wei Guo, Yuanyong Luo, Tianchi Hu, Junsong Wang, Xin Wang, Hu Liu, Yu Cheng, Ziwei Yu, Hongliang Li, Mehdi Rahimifar, Lei Yan, Xuefei Wang, Zhuang Ma, Lei Liu, Hui Yu, Anandharaju Durai Raju, Hoang Le, Hei Yi Mak, Tanzila Rahman, Shadan Golestan 2d ago

HiFloat4 Format for Language Model Pre-training on Ascend NPUs

4-bit floating-point format (HiFloat4) for efficient language model pre-training on Ascend NPU hardware.

Ax Chia-Hong Hsu, Randall Balestriero 2d ago

Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning

Guidance method for consistency models using joint flow distribution learning to enable classifier-free guidance without separate teacher model.

Ax Chia-Hong Hsu, Frank Wood 2d ago

Discrete Meanflow Training Curriculum

Training curriculum method for discrete flow-based image generation models to improve one-step sampling stability and quality.

Ax Roi Paul 2d ago

Spectral Geometry of LoRA Adapters Encodes Training Objective and Predicts Harmful Compliance

Analysis of LoRA adapter spectral geometry to identify fine-tuning objectives and predict harmful model behavior in language models.

Ax Jinqi Luo, Jinyu Yang, Tal Neiman, Lei Fan, Bing Yin, Son Tran, Mubarak Shah, Ren\'e Vidal 2d ago

Dictionary-Aligned Concept Control for Safeguarding Multimodal LLMs

Safety steering mechanism for multimodal LLMs using dictionary-aligned concept control to prevent unsafe outputs without retraining.

Ax Yuwen Jiang 2d ago

Finite-Sample Analysis of Nonlinear Independent Component Analysis:Sample Complexity and Identifiability Bounds

Theoretical analysis of finite-sample properties and identifiability bounds for nonlinear Independent Component Analysis algorithms.

Ax Rafael da Silva, Jeff Eicher, Gregory Longo 2d ago

Temporal Dropout Risk in Learning Analytics: A Harmonized Survival Benchmark Across Dynamic and Early-Window Representations

Survival analysis benchmark for predicting student dropout in learning analytics using OULAD dataset with dynamic and static representations.

Ax Amrut Nadgir, Vijay Balasubramanian, Pratik Chaudhari 2d ago

How does Chain of Thought decompose complex tasks?

Demonstrates power-law scaling of classification error with number of classes and how chain-of-thought decomposition reduces error through task splitting.

Ax Rafael da Silva, Jeff Eicher, Gregory Longo 2d ago

A Mathematical Framework for Temporal Modeling and Counterfactual Policy Simulation of Student Dropout

Temporal modeling framework for predicting student dropout using LMS data and logistic regression with counterfactual policy simulation.