Ax Qingxiu Liu, Cyril Y. He, Hanser Jiang, Zion Wang, Alan Zhao, Patrick P. C. Lee 1d ago

FluxMoE: Decoupling Expert Residency for High-Performance MoE Serving

FluxMoE system decouples expert residency to improve inference serving throughput in Mixture-of-Experts LLMs.

Ax Patrick Pynadath, Jiaxin Shi, Ruqi Zhang 1d ago

Generative Frontiers: Why Evaluation Matters for Diffusion Language Models

Technical analysis of evaluation methodology challenges for diffusion language models at scale.

Ax Jing Gu, Morteza Mardani, Wonjun Lee, Dongmian Zou, Gilad Lerman 1d ago

Understanding Latent Diffusability via Fisher Geometry

Theoretical analysis of diffusion model degradation in latent spaces using Fisher geometry framework.

Ax Zijin Liu, Xu Geng, Wenshuai Xu, Xiang Zhao, Yan Xia, You Song 1d ago

STDDN: A Physics-Guided Deep Learning Framework for Crowd Simulation

Physics-guided deep learning framework combining microscopic and macroscopic approaches for crowd simulation.

Ax Zhiming Xu, Baile Xu, Jian Zhao, Furao Shen, Suorong Yang 1d ago

Towards Realistic Class-Incremental Learning with Free-Flow Increments

Free-flow class-incremental learning framework handling realistic variable-sized task streams without fixed task schedules.

Ax Giyeong Oh, Junghyun Lee, Jaehyun Park, Youngjae Yu, Wonho Bae, Junhyug Noh 1d ago

Random Is Hard to Beat: Active Selection in online DPO with Modern LLMs

Study comparing active preference learning vs random sampling for online DPO data selection in modern LLMs.

Ax Guangwen Wang, Jiaqi Wu, Yang Weng, Baosen Zhang 1d ago

Structure-Aware Commitment Reduction for Network-Constrained Unit Commitment with Solver-Preserving Guarantees

Learning-guided approach for reducing computational burden in network-constrained unit commitment optimization.

Ax Valentin Mercier (Toulouse INP, IRIT, EPE UT), Serge Gratton (IRIT, EPE UT, Toulouse INP), Lapeyre Corentin (NVIDIA), Gwena\"el Chevallet 1d ago

Toward an Operational GNN-Based Multimesh Surrogate for Fast Flood Forecasting

GNN-based surrogate model for accelerating hydraulic flood forecasting simulations.

Ax Haseeb Tariq, Marwan Hassani 1d ago

Extracting Money Laundering Transactions from Quasi-Temporal Graph Representation

Graph-based ML approach for detecting money laundering transactions in financial networks.

Ax Federico Di Gennaro, Saptarshi Chakraborty, Nikita Zhivotovskiy 1d ago

Efficient Logistic Regression with Mixture of Sigmoids

Computational analysis of exponential weights algorithm for online logistic regression with improved complexity bounds.

Ax Andreas Boltres, Niklas Freymuth, Benjamin Schichtholz, Michael K\"onig, Gerhard Neumann 1d ago

Towards Near-Real-Time Telemetry-Aware Routing with Neural Routing Algorithms

Neural routing algorithms for network traffic optimization using live telemetry data with near-real-time latency.

Ax Md. Rashadul Islam 1d ago

Explainable Machine Learning Reveals 12-Fold Ucp1 Upregulation and Thermogenic Reprogramming in Female Mouse White Adipose Tissue After 37 Days of Microgravity: First AI/ML Analysis of NASA OSD-970

ML analysis of NASA space biology dataset revealing thermogenic reprogramming in female mouse adipose tissue.

Ax Shinnosuke Ono, Johannes Ackermann, Soichiro Nishimori, Takashi Ishida, Masashi Sugiyama 1d ago

Mitigating Reward Hacking in RLHF via Advantage Sign Robustness

Addresses reward hacking in RLHF by using advantage sign robustness to prevent policy degradation.

Ax Cristian P\'erez-Corral, Jose I. Mestre, Alberto Fern\'andez-Hern\'andez, Manuel F. Dolz, Jos\'e Duato, Enrique S. Quintana-Ort\'i 1d ago

FedSQ: Optimized Weight Averaging via Fixed Gating

Federated learning optimization via fixed gating for weight averaging under statistical heterogeneity.

Ax Xinyu Wang, Hanwei Wu, Jingwei Song, Shuyuan Zhang, Jiayi Zhang, Fanqi Kong, Tung Sum Thomas Kwok, Xiao-Wen Chang, Yuyu Luo, Chenglin Wu, Bang Liu 1d ago

Co-Evolution of Policy and Internal Reward for Language Agents

Self-Guide framework for LLM agents using co-evolved internal rewards to address sparse reward problem in long-horizon tasks.

Ax Chenxu Yang, Chuanyu Qin, Qingyi Si, Minghui Chen, Naibin Gu, Dingyu Yao, Zheng Lin, Weiping Wang, Jiaqi Wang, Nan Duan 1d ago

Self-Distilled RLVR

On-policy self-distillation training paradigm for LLMs combining dense signals from larger teacher models.

Ax Yingxu Wang, Kunyu Zhang, Jiaxin Huang, Mengzhu Wang, Mingyan Xiao, Siyang Gao, Nan Yin 1d ago

DSBD: Dual-Aligned Structural Basis Distillation for Graph Domain Adaptation

Graph domain adaptation method addressing structural discrepancies in graph neural networks under topology shifts.

Ax Gengwei Zhang, Jie Peng, Zhen Tan, Mufan Qiu, Hossein Nourkhiz Mahjoub, Vaishnav Tadiparthi, Kwonjoon Lee, Yanyong Zhang, Tianlong Chen 1d ago

Understanding the Role of Hallucination in Reinforcement Post-Training of Multimodal Reasoning Models

arXiv paper analyzes hallucination's role in RL post-training of multimodal LLMs, investigating whether models genuinely learn visual information under RL.

Ax Connor Douglas, Utkucan Balci, Joseph Aylett-Bullock 1d ago

PRISM: LLM-Guided Semantic Clustering for High-Precision Topics

arXiv paper proposes PRISM, combining LLM-guided labeling with semantic clustering for interpretable topic modeling with low computational cost.

Ax Nikita Vassilyev, William Berrios, Ruowang Zhang, Bo Han, Douwe Kiela, Shikib Mehri 1d ago

Reflective Context Learning: Studying the Optimization Primitives of Context Space

arXiv paper studies context space optimization for generally capable agents, examining credit assignment, forgetting, and overfitting in context learning.

Ax Sokratis J. Anagnostopoulos, George Rovas, Vasiliki Bikia, Theodore G. Papaioannou, Athanase D. Protogerou, Nikolaos Stergiopulos 1d ago

Real-Time Surrogate Modeling for Personalized Blood Flow Prediction and Hemodynamic Analysis

arXiv paper on surrogate modeling for real-time blood flow prediction and hemodynamic cardiovascular analysis.

Ax Van Sy Mai, Kushal Chakrabarti, Richard J. La, Dipankar Maity 1d ago

Enhancing Robustness of Federated Learning via Server Learning

arXiv paper exploring server learning to enhance federated learning robustness against malicious attacks with non-IID client data.

Ax Heng Zhang, Xiaohong Deng, Sijing Duan, Wu Ouyang, KM Mahfujul, Yiqin Deng, Zhigang Chen 1d ago

MLFCIL: A Multi-Level Forgetting Mitigation Framework for Federated Class-Incremental Learning in LEO Satellites

arXiv paper on federated class-incremental learning for LEO satellites addressing non-IID data, memory, and communication constraints.

Ax Yonas Kassa, James Bonacci, Ping Wang 1d ago

Fighting AI with AI: AI-Agent Augmented DNS Blocking of LLM Services during Student Evaluations

arXiv paper proposes AI-agent-augmented DNS blocking to prevent LLM access during student evaluations, addressing academic integrity concerns.

Ax Raul Suzuki, Rodrigo Moreira, Pedro Henrique A. Damaso de Melo, Larissa F. Rodrigues Moreira, Fl\'avio de Oliveira Silva 1d ago

TRACE: Traceroute-based Internet Route change Analysis with Ensemble Learning

arXiv paper introducing TRACE, ML pipeline for detecting Internet routing changes using traceroute latency data with ensemble learning.

Ax O\u{g}uzhan Ersoy, Nikolay Blagoev, Jona te Lintelo, Stefanos Koffas, Marina Kr\v{c}ek, Stjepan Picek 1d ago

Backdoor Attacks on Decentralised Post-Training

arXiv paper analyzing backdoor attacks on decentralized LLM post-training via pipeline parallelism, examining vulnerabilities from malicious participants.

Ax Saurabh Ranjan, Sonika Thakral, Amit Sehgal 1d ago

Photonic convolutional neural network with pre-trained in-situ training

arXiv paper proposing fully photonic convolutional neural network with pre-trained in-situ training to overcome CMOS energy bottlenecks.

Ax Kevin Song 1d ago

PlayGen-MoG: Framework for Diverse Multi-Agent Play Generation via Mixture-of-Gaussians Trajectory Prediction

PlayGen-MoG: Mixture-of-Gaussians framework for diverse multi-agent trajectory generation in team sports with spatial coordination.

Ax Onur Selim Kilic, Yeti Z. Gurbuz, Cem O. Yaldiz, Afra Nawar, Etrit Haxholli, Ogul Can, Eli Waxman 1d ago

Guideline2Graph: Profile-Aware Multimodal Parsing for Executable Clinical Decision Graphs

Guideline2Graph: LLM/VLM-based parser converting multimodal clinical guidelines into executable decision graphs with cross-page control flow.

Ax Ayush Rajesh Jhaveri, Anthony GX-Chen, Ilia Sucholutsky, Eunsol Choi 1d ago

Failing to Falsify: Evaluating and Mitigating Confirmation Bias in Language Models

Examination of confirmation bias in LLMs through rule-discovery tasks, evaluating and mitigating systematic reasoning failures.

Ax Dmitry Kovalev 1d ago

Optimal Projection-Free Adaptive SGD for Matrix Optimization

Projection-free adaptive SGD for matrix optimization achieving dimension-independent convergence without costly quadratic projections.

Ax Pangpang Liu, Chengchun Shi, Will Wei Sun 1d ago

Reinforcement Learning from Human Feedback: A Statistical Perspective

Statistical survey of RLHF for LLM alignment, examining noisy subjective feedback for reward models and policy optimization.

Ax Malik Hassanaly, Corey R. Randall, Peter J. Weddle, Paul J. Gasper, Conlain Kelly, Tanvir R. Tanim, Kandler Smith 1d ago

Neural posterior estimation for scalable and accurate inverse parameter inference in Li-ion batteries

Neural posterior estimation for Bayesian parameter inference in Li-ion batteries using probabilistic calibration.

Ax Jiyoon Kim, Chuhong Wang, Aayush R. Singh, Tyler Sours, Shivang Agarwal, AJ Nish, Paul Abruzzo, Ang Xiao, Omar Allam 1d ago

AQVolt26: High-Temperature r$^2$SCAN Halide Dataset for Universal ML Potentials and Solid-State Batteries

AQVolt26: High-temperature halide dataset with r²SCAN calculations for training universal ML potentials for solid-state batteries.

Ax Seyyed Amirhossein Moayyedi, David Y. Yang 1d ago

Interpretable Deep Reinforcement Learning for Element-level Bridge Life-cycle Optimization

Deep reinforcement learning for element-level bridge lifecycle optimization using condition state proportions.

Ax Kamalasankari Subramaniakuppusamy, Jugal Gajjar 1d ago

Feature Attribution Stability Suite: How Stable Are Post-Hoc Attributions?

Feature Attribution Stability Suite: Evaluates post-hoc attribution method stability under realistic input perturbations with improved metrics.

Ax Ansel Kaplan Erol, Seohee Yoon, Keenan Hom, Xisheng Zhang 1d ago

Synapse: Evolving Job-Person Fit with Explainable Two-phase Retrieval and LLM-guided Genetic Resume Optimization

Synapse: LLM-guided two-phase retrieval and genetic algorithm optimization for job-person matching under information imbalance.

Ax Ji Young Byun, Young-Jin Park, Jean-Philippe Corbeil, Asma Ben Abacha 1d ago

Overconfidence and Calibration in Medical VQA: Empirical Findings and Hallucination-Aware Mitigation

Empirical study of confidence calibration and hallucination in vision-language models for medical VQA, spanning three model families.

Ax Ye Mao, Weixun Luo, Ranran Huang, Junpeng Jing, Krystian Mikolajczyk 1d ago

Contrastive Language-Colored Pointmap Pretraining for Unified 3D Scene Understanding

UniScene3D: Transformer-based 3D scene encoder jointly modeling appearance and geometry from multi-view colored pointmaps with CLIP alignment.

Ax Guy Blanc 1d ago

Robust Learning with Optimal Error

Optimal error algorithms for adversarial learning using randomized hypotheses, improving deterministic hypothesis bounds by factor of 1/2.

Ax Haiyu Wang, Yutong Wang, Jack Jiang, Sai Qian Zhang 1d ago

WSVD: Weighted Low-Rank Approximation for Fast and Efficient Execution of Low-Precision Vision-Language Models

WSVD: Weighted SVD technique for efficient low-precision execution of vision-language models with reduced computational burden.

Ax John T. Halloran 1d ago

Understanding the Effects of Safety Unalignment on Large Language Models

Study examining safety alignment bypass methods in LLMs via jailbreak-tuning and weight orthogonalization, analyzing disabled safety guardrails.

Ax Viska Wei, Fei Lu 1d ago

Learning interacting particle systems from unlabeled data

Trajectory-free self-test loss function for learning interacting particle system potentials from unlabeled discrete time-point data.

Ax Rafael Pereira Eufrazio, Eduardo Fernandes Montesuma, Charles Casimiro Cavalcante 1d ago

Structure-Preserving Multi-View Embedding Using Gromov-Wasserstein Optimal Transport

Gromov-Wasserstein optimal transport methods for geometry-aware multi-view data embedding under heterogeneous geometries and nonlinear distortions.

Ax Yuntao Du, Minh Dinh, Kaiyuan Zhang, Ninghui Li 1d ago

AutoVerifier: An Agentic Automated Verification Framework Using Large Language Models

AutoVerifier: LLM-based agentic framework automating end-to-end verification of technical claims across scientific literature without domain expertise required.

Ax Yiyang Shen, Lifu Tu, Weiran Wang 1d ago

Reinforcement Learning-based Knowledge Distillation with LLM-as-a-Judge

RL framework using LLM-as-judge for label-free knowledge distillation and reasoning improvement in small and large language models without ground truth labels.

Ax Zilong Wang, Ali Abdeen, Turgay Ayer 1d ago

Transfer Learning for Meta-analysis Under Covariate Shift

Placebo-anchored transport framework for meta-analysis addressing covariate shift across randomized controlled trials.

Ax Yihong Dong, Xiaoha Jian, Xue Jiang, Xuyuan Guo, Zhiyuan Fan, Jiaru Qian, Kechi Zhang, Jia Li, Zhi Jin, Ge Li 1d ago

Evaluating the Formal Reasoning Capabilities of Large Language Models through Chomsky Hierarchy

Systematic evaluation of LLM formal reasoning capabilities using Chomsky hierarchy and computation theory complexity metrics.

Ax Mirali Purohit, Bimal Gajera, Irish Mehta, Bhanu Tokas, Jacob Adler, Steven Lu, Scott Dickenshied, Serina Diniega, Brian Bue, Umaa Rebbapragada, Hannah Kerner 1d ago

MOMO: Mars Orbital Model Foundation Model for Mars Orbital Applications

MOMO: Foundation model merging multi-sensor Mars remote sensing data (HiRISE, CTX, THEMIS) using Equal Validation Loss alignment.

Ax Peng Sun, Ruoyu Wang, Xue Luo 1d ago

State estimations and noise identifications with intermittent corrupted observations via Bayesian variational inference

Variational Bayesian adaptive Kalman filter for state estimation in sensor networks with packet dropouts and corrupted observations.