cs.LG papers | Gist.Science

LF2L: Loss Fusion Horizontal Federated Learning Across Heterogeneous Feature Spaces Using External Datasets Effectively: A Case Study in Second Primary Cancer Prediction

This paper proposes a Loss Fusion Horizontal Federated Learning (LF2L) framework that effectively integrates heterogeneous external SEER data with local Taiwanese hospital records to significantly improve the prediction accuracy of second primary lung cancer while preserving patient privacy and addressing feature inconsistencies.

Chia-Fu Lin, Yi-Ju Tseng2026-03-10🤖 cs.LG

Turning Time Series into Algebraic Equations: Symbolic Machine Learning for Interpretable Modeling of Chaotic Time Series

This paper introduces two interpretable symbolic machine learning methods, the Symbolic Neural Forecaster (SyNF) and the Symbolic Tree Forecaster (SyTF), which successfully learn explicit algebraic equations to forecast chaotic time series with accuracy competitive to deep learning while providing transparent insights into the underlying dynamics.

Madhurima Panja, Grace Younes, Tanujit Chakraborty2026-03-10🤖 cs.LG

Adaptive Double-Booking Strategy for Outpatient Scheduling Using Multi-Objective Reinforcement Learning

This paper proposes an adaptive outpatient scheduling framework that integrates individualized no-show predictions with a novel multi-policy reinforcement learning approach, utilizing a KL-divergence-based knowledge transfer mechanism to dynamically optimize booking decisions and balance competing objectives like patient wait times and clinic productivity.

Ninda Nurseha Amalina, Heungjo An2026-03-10🤖 cs.LG

Variational Flow Maps: Make Some Noise for One-Step Conditional Generation

This paper introduces Variational Flow Maps (VFMs), a framework that enables high-quality, single-step conditional generation and inverse problem solving by learning a noise adapter to align the initial noise distribution with observations, thereby bypassing the need for iterative sampling trajectories required by traditional diffusion models.

Abbas Mammadov, So Takao, Bohan Chen, Ricardo Baptista, Morteza Mardani, Yee Whye Teh, Julius Berner2026-03-10🤖 cs.LG

Fast and Flexible Audio Bandwidth Extension via Vocos

This paper proposes a fast and flexible Vocos-based bandwidth extension model that generates missing high-frequency audio content up to 48 kHz using a single neural network and a lightweight refiner, achieving competitive quality with extreme real-time throughput on both GPU and CPU hardware.

Yatharth Sharma2026-03-10🤖 cs.LG

Spectral Discovery of Continuous Symmetries via Generalized Fourier Transforms

This paper proposes a novel framework for discovering continuous one-parameter symmetries by leveraging the Generalized Fourier Transform to detect structured sparsity patterns in the spectral domain, offering a principled and interpretable alternative to existing generator-based optimization methods.

Pavan Karjol, Kumar Shubham, Prathosh AP2026-03-10🤖 cs.LG

AutoResearch-RL: Perpetual Self-Evaluating Reinforcement Learning Agents for Autonomous Neural Architecture Discovery

AutoResearch-RL is a perpetual, human-free reinforcement learning framework that autonomously discovers competitive neural architectures and hyperparameters by iteratively modifying training scripts and optimizing validation performance through Proximal Policy Optimization.

Nilesh Jain, Rohit Yadav, Sagar Kotian, Claude AI2026-03-10🤖 cs.LG

Retrieval-Augmented Multi-scale Framework for County-Level Crop Yield Prediction Across Large Regions

This paper proposes a retrieval-augmented multi-scale framework that effectively captures both short-term daily crop dynamics and long-term temporal patterns while adapting to spatial variability, thereby significantly improving the accuracy and robustness of county-level crop yield predictions across large regions compared to existing methods.

Yiming Sun, Qi Cheng, Licheng Liu, Runlong Yu, Yiqun Xie, Xiaowei Jia2026-03-10🤖 cs.LG

StructSAM: Structure- and Spectrum-Preserving Token Merging for Segment Anything Models

This paper introduces StructSAM, a novel token merging framework that preserves structural boundaries and spectral properties in Segment Anything Models (SAM) by using gradient-based energy scores and grid-based screening to achieve significant computational savings with minimal accuracy loss across natural and medical imaging benchmarks.

Duy M. H. Nguyen, Tuan A. Tran, Duong Nguyen, Siwei Xie, Trung Q. Nguyen, Mai T. N. Truong, Daniel Palenicek, An T. Le, Michael Barz, TrungTin Nguyen, Tuan Dam, Ngan Le, Minh Vu, Khoa Doan, Vien Ngo, Pengtao Xie, James Zou, Daniel Sonntag, Jan Peters, Mathias Niepert2026-03-10🤖 cs.LG

Adversarial Latent-State Training for Robust Policies in Partially Observable Domains

This paper introduces an adversarial latent-initial-state POMDP framework that theoretically establishes a minimax principle and finite-sample guarantees, while empirically demonstrating that targeted adversarial training significantly reduces robustness gaps in partially observable reinforcement learning.

Angad Singh Ahuja2026-03-10🤖 cs.LG

Shutdown Safety Valves for Advanced AI

This paper explores the unorthodox proposal of programming advanced AI systems with a primary goal of being turned off to mitigate the risk of them resisting shutdown, while analyzing the conditions under which such an approach would be effective.

Vincent Conitzer2026-03-10🤖 cs.LG

ShakyPrepend: A Multi-Group Learner with Improved Sample Complexity

The paper introduces ShakyPrepend, a multi-group learning method that utilizes differential privacy-inspired tools to achieve improved theoretical guarantees and adapt to group structure and spatial heterogeneity, while offering practical guidance for real-world deployment.

Lujing Zhang, Daniel Hsu, Sivaraman Balakrishnan2026-03-10🤖 cs.LG

Norm-Hierarchy Transitions in Representation Learning: When and Why Neural Networks Abandon Shortcuts

This paper introduces the Norm-Hierarchy Transition (NHT) framework, which explains that neural networks delay learning structured representations in favor of spurious shortcuts because weight decay slowly drives the model from high-norm solutions to lower-norm ones, with the transition delay logarithmically scaling to the ratio between these norms.

Truong Xuan Khanh, Truong Quynh Hoa2026-03-10🤖 cs.LG

Explainable and Hardware-Efficient Jamming Detection for 5G Networks Using the Convolutional Tsetlin Machine

This paper proposes and validates a hardware-efficient, explainable Convolutional Tsetlin Machine (CTM) for real-time 5G jamming detection that achieves comparable accuracy to convolutional neural networks while significantly reducing training time, memory usage, and enabling deterministic FPGA deployment.

Vojtech Halenka, Mohammadreza Amini, Per-Arne Andersen, Ole-Christoffer Granmo, Burak Kantarci2026-03-10🤖 cs.LG

Learning Concept Bottleneck Models from Mechanistic Explanations

This paper introduces Mechanistic CBM (M-CBM), a novel pipeline that extracts concepts directly from black-box models using Sparse Autoencoders and Multimodal LLMs to create interpretable Concept Bottleneck Models that outperform prior methods in predictive accuracy and explanation quality while maintaining strict control over information leakage.

Antonio De Santis, Schrasing Tong, Marco Brambilla, Lalana Kagal2026-03-10🤖 cs.LG

Learning Clinical Representations Under Systematic Distribution Shift

This paper proposes a practice-invariant representation learning framework that combines supervised risk minimization with adversarial environment regularization and invariant risk penalties to suppress institution-specific artifacts in multimodal clinical data, thereby significantly improving out-of-distribution performance and calibration across different hospitals.

Yuanyun Zhang, Shi Li2026-03-10🤖 cs.LG

A Distributed Gaussian Process Model for Multi-Robot Mapping

The paper introduces DistGP, a distributed sparse Gaussian process model that enables multi-robot collaborative mapping through local computation and Gaussian belief propagation, achieving performance comparable to centralized training while outperforming distributed neural network optimizers in accuracy, robustness, and continual learning capabilities.

Seth Nabarro, Mark van der Wilk, Andrew J. Davison2026-03-10🤖 cs.LG

AgrI Challenge: A Data-Centric AI Competition for Cross-Team Validation in Agricultural Vision

The AgrI Challenge introduces a data-centric competition framework featuring Cross-Team Validation to demonstrate that while single-source training suffers from significant generalization gaps in agricultural vision, collaborative multi-source training on independently collected, heterogeneous datasets dramatically improves model robustness and real-world performance.

Mohammed Brahimi, Karim Laabassi, Mohamed Seghir Hadj Ameur, Aicha Boutorh, Badia Siab-Farsi, Amin Khouani, Omar Farouk Zouak, Seif Eddine Bouziane, Kheira Lakhdari, Abdelkader Nabil Benghanem2026-03-10🤖 cs.LG

Latent Generative Models with Tunable Complexity for Compressed Sensing and other Inverse Problems

This paper introduces tunable-complexity priors for generative models like diffusion models, normalizing flows, and VAEs by leveraging nested dropout, demonstrating that adaptively adjusting model dimensionality significantly improves reconstruction performance across various inverse problems compared to fixed-complexity baselines.

Sean Gunn, Jorio Cocola, Oliver De Candido, Vaggos Chatziafratis, Paul Hand2026-03-10🤖 cs.LG

N-Tree Diffusion for Long-Horizon Wildfire Risk Forecasting

The paper introduces N-Tree Diffusion (NT-Diffusion), a hierarchical diffusion model that improves long-horizon wildfire risk forecasting by sharing early denoising stages across prediction horizons to reduce computational redundancy while maintaining probabilistic accuracy.

Yucheng Xing, Xin Wang2026-03-10🤖 cs.LG

← Previous Next →