Imagen de Portada

GHOST: Unmasking Phantom States in Mamba2 via Grouped Hidden-state Output-aware Selection & Truncation

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Menezes, Michael, Kyrillidis, Anastasios
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning Systems and Control
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Unveiling Hidden Pivotal Players with GoalNet: A GNN-Based Soccer Player Evaluation System
por: Jiang, Jacky Hao, et al.
Publicado: (2025)

One Model, Two Roles: Emergent Specialization in a Shared Recurrent Transformer
por: Shen, Jucheng, et al.
Publicado: (2026)

SGD at the Edge of Stability: The Stochastic Sharpness Gap
por: Liao, Fangshuo, et al.
Publicado: (2026)

One Rank at a Time: Cascading Error Dynamics in Sequential Learning
por: Vandchali, Mahtab Alizadeh, et al.
Publicado: (2025)

An Offline Risk-aware Policy Selection Method for Bayesian Markov Decision Processes
por: Angelotti, Giorgio, et al.
Publicado: (2021)

Lyapunov-stable Neural Control for State and Output Feedback: A Novel Formulation
por: Yang, Lujie, et al.
Publicado: (2024)

Learning Hidden Subgoals under Temporal Ordering Constraints in Reinforcement Learning
por: Xu, Duo, et al.
Publicado: (2024)

Selecting Offline Reinforcement Learning Algorithms for Stochastic Network Control
por: Helson, Nicolas, et al.
Publicado: (2026)

Convergence Analysis of Two-Layer Neural Networks under Gaussian Input Masking
por: Kolomvaki, Afroditi, et al.
Publicado: (2026)

A cGAN Ensemble-based Uncertainty-aware Surrogate Model for Offline Model-based Optimization in Industrial Control Problems
por: Feng, Cheng
Publicado: (2022)

A Selective Quantization Tuner for ONNX Models
por: Louloudakis, Nikolaos, et al.
Publicado: (2025)

Naga: Vedic Encoding for Deep State Space Models
por: Schaller, Melanie, et al.
Publicado: (2025)

Secure Hierarchical Federated Learning in Vehicular Networks Using Dynamic Client Selection and Anomaly Detection
por: HaghighiFard, M. Saeid, et al.
Publicado: (2024)

EMFusion: An Uncertainty-Aware Conditional Diffusion Framework for Frequency-Selective EMF Forecasting in Wireless Networks
por: Yan, Zijiang, et al.
Publicado: (2025)

Faster Reinforcement Learning by Freezing Slow States
por: Wang, Yijia, et al.
Publicado: (2023)

Thinking Out of the Box: Hybrid SAT Solving by Unconstrained Continuous Optimization
por: Zhang, Zhiwei, et al.
Publicado: (2025)

Long-Term Client Selection for Federated Learning with Non-IID Data: A Truthful Auction Approach
por: Tan, Jinghong, et al.
Publicado: (2025)

Guided by the Experts: Provable Feature Learning Dynamic of Soft-Routed Mixture-of-Experts
por: Liao, Fangshuo, et al.
Publicado: (2025)

Provable Accelerated Convergence of Nesterov's Momentum for Deep ReLU Neural Networks
por: Liao, Fangshuo, et al.
Publicado: (2023)

Stable-by-Design Neural Network-Based LPV State-Space Models for System Identification
por: Sertbaş, Ahmet Eren, et al.
Publicado: (2025)

Implicit Bias of Policy Gradient in Linear Quadratic Control: Extrapolation to Unseen Initial States
por: Razin, Noam, et al.
Publicado: (2024)

Understanding the differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
por: Sieber, Jerome, et al.
Publicado: (2024)

Physics-Informed State Space Models for Reliable Solar Irradiance Forecasting in Off-Grid Systems
por: Abdullah, Mohammed Ezzaldin Babiker
Publicado: (2026)

A Closed-loop, State-centric, Multi-agent Framework for Passenger Load Estimation from Heterogeneous Data Streams
por: Xu, Yiyao, et al.
Publicado: (2026)

Stabilizing Policy Gradient Methods via Reward Profiling
por: Ahmed, Shihab, et al.
Publicado: (2025)

SEAL: SEmantic-Augmented Imitation Learning via Language Model
por: Gu, Chengyang, et al.
Publicado: (2024)

Stochastic Actor-Critic: Mitigating Overestimation via Temporal Aleatoric Uncertainty
por: Özalp, Uğurcan
Publicado: (2026)

Worst-Case Regret Bounds for Exploration via Randomized Value Functions
por: Russo, Daniel
Publicado: (2019)

RL for Mitigating Cascading Failures: Targeted Exploration via Sensitivity Factors
por: Dwivedi, Anmol, et al.
Publicado: (2024)

Fail Fast, or Ask: Mitigating the Deficiencies of Reasoning LLMs with Human-in-the-Loop Systems Engineering
por: Zellinger, Michael J., et al.
Publicado: (2025)

Unifying Goal-Conditioned RL and Unsupervised Skill Learning via Control-Maximization
por: Modirshanechi, Alireza, et al.
Publicado: (2026)

RL in Latent MDPs is Tractable: Online Guarantees via Off-Policy Evaluation
por: Kwon, Jeongyeol, et al.
Publicado: (2024)

Safe Deployment of Offline Reinforcement Learning via Input Convex Action Correction
por: Durkin, Alex, et al.
Publicado: (2025)

Contingency-constrained economic dispatch with safe reinforcement learning
por: Eichelbeck, Michael, et al.
Publicado: (2022)

Fully Dynamic Rebalancing in Dockless Bike-Sharing Systems via Deep Reinforcement Learning
por: Scarpel, Edoardo, et al.
Publicado: (2026)

Fitted Q-Iteration via Max-Plus-Linear Approximation
por: Liu, Y., et al.
Publicado: (2024)

Outperforming Self-Attention Mechanisms in Solar Irradiance Forecasting via Physics-Guided Neural Networks
por: Abdullah, Mohammed Ezzaldin Babiker, et al.
Publicado: (2026)

Test Time Training for AC Power Flow Surrogates via Physics and Operational Constraint Refinement
por: Dogoulis, Panteleimon, et al.
Publicado: (2025)

Hereditary Geometric Meta-RL: Nonlocal Generalization via Task Symmetries
por: Nitschke, Paul, et al.
Publicado: (2026)

CORL: Reinforcement Learning of MILP Policies Solved via Branch and Bound
por: Anand, Akhil S, et al.
Publicado: (2025)