Ax Zhuoqian Yang, Mathieu Salzmann, Sabine S\"usstrunk 20d ago

Weight Space Representation Learning via Neural Field Adaptation

Weight space representation learning via neural field adaptation using LoRA constraints for reconstruction and generation tasks.

Ax Caleb Ju, Guanghui Lan 20d ago

Auto-exploration for online reinforcement learning

Auto-exploration reinforcement learning methods address exploration-exploitation trade-off with implementable algorithms.

Ax Mantas Baksys, Stefan Zetzsche, Olivier Bouissou, Sean B. Holden 20d ago

MINIF2F-DAFNY: LLM-Guided Mathematical Theorem Proving via Auto-Active Verification

MINIF2F-Dafny uses LLMs with auto-active verification in Dafny to improve theorem proving over interactive theorem provers.

Ax Xin Li 20d ago

The Urysohn Ladder: Recursive Metric Contraction for Scalable Continual Learning

Metric contraction approach for continual learning that prevents catastrophic interference on fixed-capacity manifolds.

Ax Kasper Green Larsen, Chirag Pabbaraju, Abhishek Shetty 20d ago

Learning with Monotone Adversarial Corruptions

Study of machine learning algorithms under monotone adversarial corruptions to understand data independence assumptions.

Ax Zhongyu Xiao, Zhiwei Hao, Jianyuan Guo, Yong Luo, Jia Liu, Jie Xu, Han Hu 20d ago

Streaming-dLLM: Accelerating Diffusion LLMs via Suffix Pruning and Dynamic Decoding

Streaming-dLLM accelerates diffusion language models through suffix pruning and dynamic decoding, improving inference efficiency.

Ax Yuexin Bian, Jie Feng, Tao Wang, Yijiang Li, Sicun Gao, Yuanyuan Shi 20d ago

RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning

Discretized categorical actors for on-policy reinforcement learning improve stability and reduce brittleness of gradient-based optimization.

Ax Saeid Jamshidi, Omar Abdul Wahab, Rolando Herrero, Foutse Khomh 20d ago

Securing Time Integrity in Energy IoT Against Clock Drift and Y2K38 Failures

Methods to secure time integrity in IoT energy systems against clock drift and Y2K38 failures using anomaly detection.

Ax Xiyuan Wei, Linli Zhou, Bokun Wang, Chih-Jen Lin, Tianbao Yang 20d ago

A Geometry-Aware Efficient Algorithm for Compositional Entropic Risk Minimization

Geometry-aware algorithm for compositional entropic risk minimization using Log-Expectation-Exponential formulation.

Ax Daniel Barzilai, Ohad Shamir 20d ago

Limitations of SGD for Multi-Index Models Beyond Statistical Queries

Theoretical study analyzing limitations of SGD for multi-index models beyond the Statistical Queries framework.

Ax Maosen Tang, Alex Townsend 20d ago

Rational Neural Networks have Expressivity Advantages

Neural networks with trainable rational activation functions demonstrate superior expressivity and parameter efficiency compared to standard activations like ReLU and SiLU.

Ax Sungwoo Kang 20d ago

Learning Structural Hardness for Combinatorial Auctions: Instance-Dependent Algorithm Selection via Graph Neural Networks

Graph neural networks for algorithm selection in combinatorial auction winner determination via structural hardness prediction.

Ax Beatrix M. G. Nielsen, Emanuele Marconato, Luigi Gresele, Andrea Dittadi, Simon Buchholz 20d ago

Logit Distance Bounds Representational Similarity

Theoretical analysis of representational similarity in discriminative models through logit distance bounds.

Ax Stefan Wahl, Raphaela Schenk, Ali Farnoud, Jakob H. Macke, Daniel Gedon 20d ago

A Probabilistic Framework for LLM-Based Model Discovery

Probabilistic framework for using LLMs to autonomously discover mechanistic simulator models from observational data with explicit probabilistic structure.

Ax Chika Maduabuchi 20d ago

Entropy-Controlled Flow Matching

Flow matching approach for vision generative models with entropy control to prevent semantic mode depletion.

Ax Shuhei Sugiura, Ichiro Takeuchi, Shion Takeno 20d ago

Randomized Kriging Believer for Parallel Bayesian Optimization with Regret Bounds

Parallel Bayesian optimization method for expensive black-box functions with theoretical regret bounds.

Ax Yair Ashlagi, Roi Livni, Shay Moran, Tom Waknine 20d ago

Margin in Abstract Spaces

Theoretical analysis of margin-based learning in abstract metric spaces and generalization guarantees independent of parameter count.

Ax Erin Carson, Xinye Chen 20d ago

Estimating condition number with Graph Neural Networks

Graph neural network method for efficiently estimating sparse matrix condition numbers with O(nnz+n) complexity.

Ax Haoyu He, Hao Wang, Jiashan Wang, Qiankun Shi 20d ago

The Effective Number of Nonzeros: Theory and Regularization for Sparse Recovery

Entropy-based effective sparsity measure with regularization technique for sparse matrix recovery problems.

Ax Anand Jerry George, Nicolas Macris 20d ago

Asymptotic Learning Curves for Diffusion Models with Random Features Score and Manifold Data

Theoretical analysis of denoising score matching for diffusion models on low-dimensional manifolds using random features.

Ax Aditya Kakade, Vivek Srivastava, Shirish Karande 20d ago

Polaris: A G\"odel Agent Framework for Small Language Models through Experience-Abstracted Policy Repair

Polaris framework enabling recursive self-improvement in small language models through policy repair and experience abstraction.

Ax Mingqing Xiao, Yansen Wang, Dongqi Han, Caihua Shan, Dongsheng Li 20d ago

Kuramoto Oscillatory Phase Encoding: Neuro-inspired Synchronization for Improved Learning Efficiency

Kuramoto oscillatory phase encoding as neuro-inspired addition to deep learning for improved learning efficiency.

Ax Julian Hatzky, Thomas Bartz-Beielstein, A. E. Eiben, Anil Yaman 20d ago

Multi-Task Optimization over Networks of Tasks

MONET algorithm for multi-task optimization over large task sets using population-based methods with task topology awareness.

Ax Lichen Li, Hengguang Zhou, Yijun Liang, Tianyi Zhou, Cho-Jui Hsieh 20d ago

Do Prompt-Elicited Trajectories Reflect Training-Time Reward Hacking? A Systematic Study on Monitoring Trainig-Time Reward Hacking in Code Generation

Study on detecting reward hacking in code generation models trained with reinforcement learning via monitoring and analysis.

Ax Andreas Pattichis, Constantine Dovrolis 20d ago

Continual Knowledge Updating in LLM Systems: Learning Through Multi-Timescale Memory Dynamics

Memini system with multi-timescale memory dynamics for continual knowledge updating in deployed LLM systems.

Ax Feng Liu (Beijing Jiaotong University), Kejia Li (Beijing Jiaotong University), Zhiwei Yang (DiDi Company), Chunwei Yang (DiDi Company), Qun Li (DiDi Company), Guobin Wu (DiDi Company), Qiang Ni (Lancaster University), Ruipeng Gao (Beijing Jiaotong University) 20d ago

Tracking Large-scale Shared Bikes with Inertial Motion Learning in GNSS Blocked Environments

Inertial navigation system using machine learning for tracking bikes in GNSS-blocked urban environments.

Ax Xikai Zhang, Yongzhi Li, Likang Xiao, Yingze Zhang, Yanhua Cheng, Quan Chen, Peng Jiang, Wenjun Wu, Liu Liu 20d ago

FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning

FBOS-RL algorithm combining bi-objective optimization with feedback for reinforcement learning and LLM alignment.

Ax Jian Xu, Delu Zeng, John Paisley, Qibin Zhao 20d ago

Onsager-Machlup Posterior Transport for Deep Gaussian Processes

Posterior transport method for approximate inference in Deep Gaussian Processes using Onsager-Machlup framework.

Ax Yunbei Xu 20d ago

Bellman-sufficient Information Complexity

Bellman-sufficient information complexity framework for sequential decision-making and state representation learning.

Ax Guanyu Liu, Weiyi Kong, Zeyu Wang, Boer Zhang, Baiqing Li, Peiyu Zhang, Tianyu Shi 20d ago

CARE: Controlling LLM-Generated Policies through Auditable Review of Evidence in Scientific Experimentation

CARE framework for auditable control of LLM-generated policies in high-throughput scientific experimentation with human oversight.

Ax Matthias Chung, Yutong Bu, Deepanshu Verma 20d ago

Physics-conforming Latent Twins

Physics-conforming latent twin surrogate models that preserve conservation laws and physical invariants for time-dependent systems.

Ax Dayuan Fu, Mohan Jiang, Tongyu Wang, Dian Yang, Jiarui Hu, Liming Liu, Jinlong Hou, Pengfei Liu 20d ago

daVinci-kernel: Co-Evolving Skill Selection, Summarization, and Utilization via RL for GPU Kernel Optimization

daVinci-kernel uses reinforcement learning with three coordinated agents and LLM backbone for GPU kernel optimization.

Ax Dara Goldar, Geir Kjetil Ferkingstad Sandve, Martin Jullum 20d ago

Beyond Defensive Reporting: Machine Learning for Active Anti-Money Laundering Control in Insurance

Machine learning system for detecting suspicious insurance claims to prevent money laundering, tested on production data.

Ax Abhishek Bhardwaj, Arnav Doshi, Anusri Nagarajan, Thanh Quynh Nhu Ta, Mohammad Masum, Robert Chun, Jaydip Sen, Saptarshi Sengupta 20d ago

MorphStrata: Layer-Specific Perturbations for Generating Morphence Students in Time-Series Moving Target Defense

MorphStrata defense mechanism against adversarial attacks on time-series forecasting models using layer-specific perturbations.

Ax Lennon J. Shikhman 20d ago

Operator Boosting Produces Pareto-Efficient PDE Surrogates

Operator Boosting framework for creating compact neural operator surrogate models for PDEs through stagewise residual learning.

Ax Matin Fallahi, Patricia Arias-Cabarcos, Thorsten Strufe 20d ago

NeuroShield: A Device-Agnostic Foundation Model for EEG Authentication

Foundation model for EEG-based biometric authentication that handles heterogeneous hardware and channel configurations across datasets.

Ax Hugo Attali, Rachid El Jouhri 20d ago

Ramanujan Graph Rewiring with Non Negative Resistance Curvature

Method to improve graph neural networks by addressing over-squashing through Ramanujan graph rewiring for better long-range dependency learning.

Ax Laurent Caraffa 20d ago

The Cost Geometry of Belief: finite-resource inference under noisy observation

Theoretical framework on belief representation and inference costs for bounded reasoners under noisy observations using information geometry.

Ax Zewen Liu 20d ago

Memory Contagion: Cross-Temporal Propagation of Evaluator Bias via Agent Memory

Study identifying how evaluator bias propagates through agent memory systems over time, affecting LLM agents with memory-based long-term coherence.

Ax Advik Raj Basani, Anshuman Chhabra 20d ago

Exposing the Illusion of Erasure in Knowledge Editing for LLMs

Research on knowledge editing in LLMs revealing that edited knowledge often persists and resurfaces across model architectures, examining reliability and mechanisms.

Ax Xiran Wang, Jian Zhang, Lei Qi, Yang Gao, Yinghuan Shi 20d ago

Exploring Dualistic Meta-Learning to Enhance Domain Generalization in Open Set Scenarios

Dualistic meta-learning approach for open set domain generalization to recognize unseen classes in unseen domains with label mismatch.

Ax Konstantin Yatsenko, Arvind Thiagarajan 20d ago

Sesame: Structure-Aware Molecular Generation via Spatial Density-Map Conditioning

Sesame generative model for drug discovery using spatial density-map conditioning to generate molecules with protein-ligand interaction awareness.

Ax Zixin Ding, Shaghayegh Emami, Giovanna Salvi, Cecilia Tosciri, Abhijith Gandrakota, Jennifer Ngadiuba, Nhan Tran, Christian Herwig, David W. Miller, Yuxin Chen 20d ago

Learning to Trigger: Reinforcement Learning at the Large Hadron Collider

Applies reinforcement learning to real-time event triggering at Large Hadron Collider, tuning thresholds under bandwidth and latency constraints.

Ax Feihong Nan, Zhengyi Zhong, Pan Wang, Weidong Bao, Xiongtao Zhang, Quan Wen, Ji Wang 20d ago

FedUP: One-Shot Federated Unlearning via Centroid-Guided Plug-in Filters

FedUP one-shot federated unlearning framework using centroid-guided plug-in filters to remove target data while preserving knowledge.

Ax Feiyang Fu, Hehe Fan 20d ago

A Time-Reparameterized Cumulative Intensity Extrapolation Sampler for Discrete Flow Matching

Proposes time-reparameterized cumulative intensity extrapolation sampler for efficient sampling in discrete flow matching generative models.

Ax Kunyu Ni, Lei Cao, Jie He, Xiaotong Zhang, Jianfeng Jin, Junyu Dong, Yanwei Yu 20d ago

FlowPipe: LLM-Enhanced Conditional Generative Flow Networks for Data Preparation Pipeline Construction

FlowPipe uses LLM-enhanced conditional generative flow networks for automated data preparation pipeline construction with improved optimization.

Ax Saptarshi Chakraborty, Debolina Paul, Swagatam Das 20d ago

Robust Linear Predictions: Analyses of Uniform Concentration, Fast Rates and Model Misspecification

Analyzes robust linear prediction through Median of Means framework with concentration bounds and fast learning rates.

Ax Keaton Hamm, Varun Khurana 20d ago

Structured Approximations of Measures

Theoretical analysis of approximating probability measures in Wasserstein distance using structured function approximators.

Ax Haolin Xiong, Sairisheek Muttukuru, Hanyuan Xiao, Rishi Upadhyay, Pradyumna Chari, Yajie Zhao, Achuta Kadambi 20d ago

SparseGS: Sparse View Synthesis using 3D Gaussian Splatting

SparseGS enables efficient 3D novel view synthesis from sparse input views using Gaussian splatting for real-time rendering.

Ax Xun Jiao, Fred Lin, Harish D. Dixit, Joel Coburn, Sajin Nair, Abhinav Pandey, Han Wang, Venkat Ramesh, Jianyu Huang, Daniel Moore, Sriram Sankar 20d ago

PVF:Understanding AI Vulnerability Against SDCs

Studies AI system reliability against silent data corruptions in hardware, analyzing vulnerability of model parameters during inference.