Imagen de Portada

Beyond the Frontier: Stochastic Backtracking for Efficient Test-Time Scaling

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Tran, Dao, Le, Duc Anh, Luu, Ngoc, Pham, Quan, Pham, Tung, Bui, Hung
Formato:	Preprint
Publicado:	2026
Materias:	Artificial Intelligence Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

FAIREDU: A Multiple Regression-Based Method for Enhancing Fairness in Machine Learning Models for Educational Applications
por: Pham, Nga, et al.
Publicado: (2024)

DmC: Nearest Neighbor Guidance Diffusion Model for Offline Cross-domain Reinforcement Learning
por: Van, Linh Le Pham, et al.
Publicado: (2025)

Policy Learning for Off-Dynamics RL with Deficient Support
por: Van, Linh Le Pham, et al.
Publicado: (2024)

Learning to Stop Overthinking at Test Time
por: Bao, Hieu Tran, et al.
Publicado: (2025)

Hybrid Cross-domain Robust Reinforcement Learning
por: Van, Linh Le Pham, et al.
Publicado: (2025)

Virtual Fusion with Contrastive Learning for Single Sensor-based Activity Recognition
por: Nguyen, Duc-Anh, et al.
Publicado: (2023)

HybridoNet-Adapt: A Domain-Adapted Framework for Accurate Lithium-Ion Battery RUL Prediction
por: Tran, Khoa, et al.
Publicado: (2025)

AdaFRUGAL: Adaptive Memory-Efficient Training with Dynamic Control
por: Bui, Quang-Hung, et al.
Publicado: (2025)

Beyond the Known: Decision Making with Counterfactual Reasoning Decision Transformer
por: Nguyen, Minh Hoang, et al.
Publicado: (2025)

Smooth-Distill: A Self-distillation Framework for Multitask Learning with Wearable Sensor Data
por: Vu, Hoang-Dieu, et al.
Publicado: (2025)

Flatness-aware Sequential Learning Generates Resilient Backdoors
por: Pham, Hoang, et al.
Publicado: (2024)

Energy-Efficient and Real-Time Sensing for Federated Continual Learning via Sample-Driven Control
por: Luu, Minh Ngoc, et al.
Publicado: (2023)

Cross-Subject Intracranial EEG Reconstruction from Scalp Recordings Using Multi-Scale Cross-Attention Transformers
por: Pham, Tien-Dat, et al.
Publicado: (2026)

Scalable AI Inference: Performance Analysis and Optimization of AI Model Serving
por: Pham, Hung Cuong, et al.
Publicado: (2026)

The Graphon Limit Hypothesis: Understanding Neural Network Pruning via Infinite Width Analysis
por: Pham, Hoang, et al.
Publicado: (2025)

A Robust Deep Learning System for Motor Bearing Fault Detection: Leveraging Multiple Learning Strategies and a Novel Double Loss Function
por: Tran, Khoa, et al.
Publicado: (2023)

PHEATPRUNER: Interpretable Data-centric Feature Selection for Multivariate Time Series Classification through Persistent Homology
por: Pham, Anh-Duy, et al.
Publicado: (2025)

Metacognitive Sensitivity for Test-Time Dynamic Model Selection
por: Trinh, Le Tuan Minh, et al.
Publicado: (2025)

Beyond Losses Reweighting: Empowering Multi-Task Learning via the Generalization Perspective
por: Phan, Hoang, et al.
Publicado: (2022)

Beyond Similarity: Temporal Operator Attention for Time Series Analysis
por: Twitty, Jevon, et al.
Publicado: (2026)

MP-PINN: A Multi-Phase Physics-Informed Neural Network for Epidemic Forecasting
por: Nguyen, Thang, et al.
Publicado: (2024)

FedKDX: Federated Learning with Negative Knowledge Distillation for Enhanced Healthcare AI Systems
por: Pham, Quang-Tu, et al.
Publicado: (2026)

$i$REPO: $i$mplicit Reward Pairwise Difference based Empirical Preference Optimization
por: Le, Long Tan, et al.
Publicado: (2024)

Deep Backtracking Counterfactuals for Causally Compliant Explanations
por: Kladny, Klaus-Rudolf, et al.
Publicado: (2023)

Generalization Bounds for Robust Contrastive Learning: From Theory to Practice
por: Tran, Ngoc N., et al.
Publicado: (2023)

Sharpness-Aware Teleportation on Riemannian Manifolds
por: Truong, Tuan, et al.
Publicado: (2023)

Using Synthetic Data to estimate the True Error is theoretically and practically doable
por: Thanh, Hai Hoang, et al.
Publicado: (2025)

Tree-Sliced Wasserstein Distance with Nonlinear Projection
por: Tran, Thanh, et al.
Publicado: (2025)

Reinforcement Learning with Backtracking Feedback
por: Sel, Bilgehan, et al.
Publicado: (2026)

Backtracking Improves Generation Safety
por: Zhang, Yiming, et al.
Publicado: (2024)

Beyond Memorization: Extending Reasoning Depth with Recurrence, Memory and Test-Time Compute Scaling
por: Rodkin, Ivan, et al.
Publicado: (2025)

A New Approach to Backtracking Counterfactual Explanations: A Unified Causal Framework for Efficient Model Interpretability
por: Fatemi, Pouria, et al.
Publicado: (2025)

Rethinking Optimal Verification Granularity for Compute-Efficient Test-Time Scaling
por: Chen, Hao Mark, et al.
Publicado: (2025)

wav2graph: A Framework for Supervised Learning Knowledge Graph from Speech
por: Le-Duc, Khai, et al.
Publicado: (2024)

Tree-Sliced Wasserstein Distance: A Geometric Perspective
por: Tran, Viet-Hoang, et al.
Publicado: (2024)

SequenceMatch: Imitation Learning for Autoregressive Sequence Modelling with Backtracking
por: Cundy, Chris, et al.
Publicado: (2023)

Spectral Entropy Collapse as a Phase Transition in Delayed Generalisation: An Interventional and Predictive Framework for Grokkin
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

The Norm-Separation Delay Law of Grokking: A First-Principles Theory of Delayed Generalization
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

First-Passage Prediction of Grokking Delay: ACalibrated Law under AdamW with Causal Validation
por: Khanh, Truong Xuan, et al.
Publicado: (2026)

A Novel Approach in Solving Stochastic Generalized Linear Regression via Nonconvex Programming
por: Anh, Vu Duc, et al.
Publicado: (2024)