Ax Seonggon Kim, Alireza Khodamoradi, Kristof Denolf, Eunhyeok Park 23h ago

AdaHOP: Fast and Accurate Low-Precision Training via Outlier-Pattern-Aware Rotation

Low-precision training method for LLMs using adaptive Hadamard transforms based on outlier patterns in weights, activations, and gradients.

Ax Adam Bayley, Xiaodan Zhu, Raquel Aoki, Yanshuai Cao, Kevin H. Wilson 23h ago

Jump Start or False Start? A Theoretical and Empirical Evaluation of LLM-initialized Bandits

Research on using LLM-generated synthetic data to warm-start contextual bandits, examining alignment between LLM choices and actual user preferences.

Ax Zeyang Huang, Angelos Chatzimparmpas, Thomas H\"ollt, Takanori Fujiwara 23h ago

A Spectral Framework for Multi-Scale Nonlinear Dimensionality Reduction

Spectral framework for multi-scale nonlinear dimensionality reduction balancing global-local structure preservation and expressiveness-transparency.

Ax Xiangbo Qi, Chaoyi Jiang, Murali Annavaram 23h ago

Fast NF4 Dequantization Kernels for Large Language Model Inference

Optimized NF4 dequantization kernels for fast LLM inference on NVIDIA GPUs, addressing FP16 conversion bottleneck.

Ax Xiaoxing Ren, Yuwen Ma, Nicola Bastianello, Karl H. Johansson, Thomas Parisini, Andreas A. Malikopoulos 23h ago

Communication-Efficient Distributed Learning with Differential Privacy

Communication-efficient distributed learning algorithm with differential privacy using local training and gradient clipping.

Ax Gonzalo Uribarri 23h ago

ROMAN: A Multiscale Routing Operator for Convolutional Time Series Models

ROMAN operator for time series that creates multiscale representations by building antialiased pyramids for convolutional classifiers.

Ax Yan Zheng, Florian Bordes 23h ago

VoxelCodeBench: Benchmarking 3D World Modeling Through Code Generation

VoxelCodeBench platform benchmarking code generation models for 3D spatial reasoning with execution in Unreal Engine.

Ax Mohammed Suhail B Nadaf 23h ago

Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens

Analysis of function vectors in LLMs showing they steer behavior beyond logit lens interpretability across 4,032 cross-template transfer pairs.

Ax Samuel Honor, Mohamed Abdelnaby, Kevin Leahy 23h ago

Complex-Valued GNNs for Distributed Basis-Invariant Control of Planar Systems

Complex-valued GNNs for distributed control of networked systems with basis-invariance for GPS and compass-denied environments.

Ax Lei Song, Shihan Guan, Youyong Kong 23h ago

Analytic Drift Resister for Non-Exemplar Continual Graph Learning

Continual graph learning without storing exemplars, using class-level prototypes and analytic continual learning to address catastrophic forgetting.

Ax Yasushi Nishida 23h ago

AXELRAM: Quantize Once, Never Dequantize

AXELRAM smart SRAM architecture computing attention scores from quantized KV cache without dequantization using orthogonal-transform quantization.

Ax Cunyang Wei, Siddharth Singh, Aishwarya Sarkar, Daniel Nichols, Tisha Patel, Aditya K. Ranjan, Sayan Ghosh, Ali Jannesari, Nathan R. Tallent, Abhinav Bhatele 23h ago

Communication-free Sampling and 4D Hybrid Parallelism for Scalable Mini-batch GNN Training

Distributed GNN training with communication-free sampling and 4D hybrid parallelism for scaling mini-batch learning on large graphs.

Ax Haruhi Shida, Koo Imai, Keigo Kansa 23h ago

Generalization Limits of Reinforcement Learning Alignment

Study of generalization limits in RLHF alignment, proposing compound jailbreaks targeting LLM safety through redistribution of existing capabilities.

Ax Eric Gan 23h ago

Product-Stability: Provable Convergence for Gradient Descent on the Edge of Stability

Theoretical analysis of gradient descent training at edge of stability with product-stability property for convergence guarantees.

Ax Farhad Pourkamali-Anaraki 23h ago

Low-Rank Compression of Pretrained Models via Randomized Subspace Iteration

Low-rank compression of pretrained models using randomized subspace iteration for efficient SVD-based model reduction.

Ax Jeesuk Shin, Donggyun Seo, Sihyeong Yu, Joongoo Jeon 23h ago

A Numerical Method for Coupling Parameterized Physics-Informed Neural Networks and FDM for Advanced Thermal-Hydraulic System Simulation

Physics-informed neural networks coupled with finite difference methods for thermal-hydraulic system simulation.

Ax Zitao Lin, Chang Zhu, Wei Meng 23h ago

Cross-subject Muscle Fatigue Detection via Adversarial and Supervised Contrastive Learning with Inception-Attention Network

Muscle fatigue detection from sEMG signals using adversarial and contrastive learning with neural networks.

Ax Matthew Levinson 23h ago

Finding Belief Geometries with Sparse Autoencoders

Mechanistic interpretability research on whether LLMs encode belief geometries like transformers trained on hidden Markov models.

Ax Yuheng Zhang, Mingyue Huo, Minghao Zhu, Mengxue Zhang, Nan Jiang 23h ago

Beyond Semantic Manipulation: Token-Space Attacks on Reward Models

Token-space attacks on reward models used in RLHF, introducing TOMPA framework for adversarial optimization beyond semantic manipulation.

Ax Haowen Wan, Qianqian Yang 23h ago

Adaptive Semantic Communication for Wireless Image Transmission Leveraging Mixture-of-Experts Mechanism

Semantic communication for wireless image transmission using mixture-of-experts to adapt to diverse image contents and channel conditions.

Ax Haijian Shao, Dalong Zhao, Xing Deng, Wenzheng Zhu, Yingtao Jiang 23h ago

LieTrunc-QNN: Lie Algebra Truncation and Quantum Expressivity Phase Transition from LiePrune to Provably Stable Quantum Neural Networks

Algebraic-geometric framework for quantum neural networks addressing barren plateaus and noise robustness.

Ax Qingxiu Liu, Cyril Y. He, Hanser Jiang, Zion Wang, Alan Zhao, Patrick P. C. Lee 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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 23h 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.