Search research

Topics & fields

Mechanistic Interpretability435 papers Model Interpretability269 papers Mechanistic Interpretability159 papers Interpretable Models38 papers Interpretable Diabetic Retinopathy Grading25 papers Interpretive Openness25 papers

4,921–4,950 of 6,027

Papers

Explainability of Recurrent Neural Networks for Enhancing P300-based Brain-Computer Interfaces
May 11, 2026Christian Oliva, Vinicio Changoluisa, Francisco B Rodríguez +1Brain-Computer Interface Explainability
Accurate Evaluation of Quickest Changepoint Detectors via Non-parametric Survival Analysis
May 11, 2026Taiki Miyagawa, Akinori F. EbiharaChange-Point Detection Survival Analysis
Metis: Learning to Jailbreak LLMs via Self-Evolving Metacognitive Policy Optimization
May 11, 2026Huilin Zhou, Jian Zhao, Yilu Zhong +7Large Language Model Jailbreaks Metacognition
STAR: Failure-Aware Markovian Routing for Multi-Agent Spatiotemporal Reasoning
May 11, 2026Ruiyi Yang, Lihuan Li, Hao Xue +1Multi-Agent Reasoning Adaptive Routing
PlantMarkerBench: A Multi-Species Benchmark for Evidence-Grounded Plant Marker Reasoning
May 11, 2026Sajib Acharjee Dip, Song Li, Liqing ZhangBiomedical Text Human-Annotated Benchmark
Medical Incident Causal Factors and Preventive Measures Generation Using Tag-based Example Selection in Few-shot Learning
May 11, 2026Yuna Haseyama, Tomoki Ito, Hiroki Sakaji +1Few-Shot Learning Annotated Data
Chebyshev Center-Based Direction Selection for Multi-Objective Optimization and Training PINNs
May 11, 2026Hoyeol Yoon, Seoungbin Bae, Nam Ho-Nguyen +1Conventional Physics-Informed Neural Networks Partial Differential Equation Benchmarks
The Truth Lies Somewhere in the Middle (of the Generated Tokens)
May 11, 2026Sophie L. Wang, Phillip Isola, Brian CheungSemantic Representations Center
JODA: Composable Joint Dynamics for Articulated Objects
May 11, 2026Tianhong Gao, Cheng Yu, Yinghao Xu +1Pose-Guided Kinematic Reasoning Articulated Objects
From Syntax to Semantics: Unveiling the Emergence of Chirality in SMILES Translation Models
May 11, 2026Zehao Li, Yasuhiro Yoshikai, Shumpei Nemoto +2Graph Language Models Representation Learning
Explicit Stair Geometry Conditioning for Robust Humanoid Locomotion
May 11, 2026Jianguo Zhang, Wentai Xu, Shusheng Ye +5Perceptive Locomotion Policies Long-Tail Humanoid Whole-Body Control
Urban-ImageNet: A Large-Scale Multi-Modal Dataset and Evaluation Framework for Urban Space Perception
May 11, 2026Yiwei Ou, Chung Ching Cheung, Jun Yang Ang +5Urban Environments Multimodal Dataset
Evidence-based Decision Modeling for Synthetic Face Detection with Uncertainty-driven Active Learning
May 11, 2026Qingchao Jiang, Zhenxuan Hou, Zhiying Zhu +3Synthetic Image Detection Detection Performance
PruneTIR: Inference-Time Tool Call Pruning for Effective yet Efficient Tool-Integrated Reasoning
May 11, 2026Luan Zhang, Dandan Song, Zhijing Wu +8Large Language Model Reasoning Fewer Tool-Call Errors
Separate First, Fuse Later: Mitigating Cross-Modal Interference in Audio-Visual LLMs Reasoning with Modality-Specific Chain-of-Thought
May 11, 2026Xuanchen Li, Yuheng Lu, Chenrui Cui +6Audio-Visual Reasoning Cross-Modal Learning
The Geometric Wall: Manifold Structure Predicts Layerwise Sparse Autoencoder Scaling Laws
May 11, 2026Eslam Zaher, Maciej Trzaskowski, Quan Nguyen +1Improving Sparse Autoencoders Scaling Laws
Cross-Family Universality of Behavioral Axes via Anchor-Projected Representations
May 11, 2026Su-Hyeon Kim, Yo-Sub HanLarge Language Model Alignment Model Activations
Fairness of Explanations in Artificial Intelligence (AI): A Unifying Framework, Axioms, and Future Direction toward Responsible AI
May 11, 2026Gideon Popoola, John SheppardExplainable Artificial Intelligence Implicit Bias
Pretraining large language models with MXFP4 on Native FP4 Hardware
May 11, 2026Musa Cim, Poovaiah Palangappa, Miro Hodak +3W4A4 Quantization Fp8
Attribution-based Explanations for Markov Decision Processes
May 10, 2026Paul Kobialka, Andrea Pferscher, Francesco Leofante +3Markov Decision Processes Artificial Intelligence Models
Language Models Without a Trainable Input Embedding Table: Learning from Fixed Minimal Binary Token Codes
May 10, 2026A. BochkovTrainable Parameter Affine
Sequential Feature Selection for Efficient Landslide Segmentation from Multi-Spectral Data
May 10, 2026Arsalaan Ahmad, Oktay Karakus, Paul L. RosinLandslides Feature Selection
From Code-Centric to Intent-Centric Software Engineering: A Reflexive Thematic Analysis of Generative AI, Agentic Systems, and Engineering Accountability
May 10, 2026Elyson De La CruzSoftware Engineering Generative Artificial Intelligence
Ambig-DS: A Benchmark for Task-Framing Ambiguity in Data-Science Agents
May 10, 2026Josefa Lia Stoisser, Marc Boubnovski Martell, Sidsel Boldsen +2Evaluation Harnesses Disambiguation
Quantum Circuit Simulation of Compartmental Drug Dynamics: Leveraging Variational Algorithms for Nonlinear Mixed-Effects Population Pharmacokinetics
May 10, 2026Isshaan Singh, Nandan PatelHybrid Quantum Neural Networks Quantum Circuit Simulation
Can We Trust LLMs for Mental Health Screening? Consistency, ASR Robustness, and Evidence Faithfulness
May 10, 2026Erfan Loweimi, Sofia de la Fuente Garcia, Samira Loveymi +2Large Language Model Reliability Depression
Statistical Scouting Finds Debate-Safe but Not Debate-Useful Cases: A Matched-Ceiling Study of Open-Weight LLM Reasoning Protocols
May 10, 2026Julia Hu, Alfred Shen, Kumar LakshmipathiDebate Multi-Agent Debate
Uncertainty-Guided Dual-Domain Learning for Reliable Skin Lesion Segmentation
May 10, 2026Duwei Dai, Caixia Dong, Guowei Dai +6Lesion Segmentation Uncertainty-Aware Fusion
SwordBench: Evaluating Orthogonality of Steering Image Representations
May 10, 2026Vladimir Zaigrajew, Dawid Pludowski, Hubert Baniecki +1Vision Foundation Models Adversarial Evaluation
Annotation-free deep learning for detection and segmentation of fetal germinal matrix-intraventricular hemorrhage in brain MRI
May 10, 2026Mingxuan Liu, Yingqi Hao, Yi Liao +17Brain Magnetic Resonance Imaging Prenatal Ultrasound

May 11, 2026 · cs.LGJ/K move · Enter open · S save

Explainability of Recurrent Neural Networks for Enhancing P300-based Brain-Computer Interfaces

Christian Oliva, Vinicio Changoluisa, Francisco B Rodríguez, Luis F Lago-Fernández

Grupo de Neurocomputación Biológica, Departamento de Ingeniería Informática, Escuela Politécnica Superior, Universidad Autónoma de Madrid, c/ Francisco Tomas y Valiente, 11, Madrid, 28049, Madrid, Spain · Grupo de Investigación en Electrónica y Telemática, Universidad Politécnica Salesiana, Campus el Girón, Ave 12 de Octubre 24-22, Quito, 170143, Quito, Ecuador

Brain-Computer Interfaces (BCIs) based on P300 event-related potentials offer promising applications in health, education, and assistive technologies. However, challenges related to inter- and intra-subject variability and the explainability of Deep Learning (DL) models limit their practical deployment. In this work, we present the Post-Recurrent Module (PRM), an additional layer designed to improve both performance and transparency, incorporated into a Recurrent Neural Network (RNN) architecture for classifying P300 signals from EEG data. Our approach enables a dual analysis of spatio-temporal signals through both global and local explainability techniques, allowing us not only to identify the most relevant brain regions and critical time intervals involved in classification, but also to interpret model decisions in terms of spatio-temporal EEG patterns consistent with well-stablished neurophysiological descriptions of the P300. Experimental results show a 9% improvement in performance over state of the art, while also revealing the importance of inter- and intra-subject variability, in alignment with established neuroscience literature. By making model decisions transparent and efficient, we present a framework for explainable EEG-based models. This framework is not limited to more efficient P300 detection, but can be generalized to a wide range of EEG-based tasks. Its ability to identify key spatial and temporal features makes it suitable for applications such as motor imagery, steady-state visual evoked potentials, and even cognitive workload assessment.

Brain-Computer Interface Explainability Motor Imagery Recurrent Neural Networks Neural Network

Open paper Ask about it PDF