Cover Image

Martingale Foresight Sampling: A Principled Approach to Inference-Time LLM Decoding

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Li, Huayu, He, ZhengXiao, Tian, Siyuan, Wen, Jinghao, Li, Ao
Format:	Preprint
Published:	2026
Subjects:	Machine Learning Artificial Intelligence
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

NeuroHD-RA: Neural-distilled Hyperdimensional Model with Rhythm Alignment
by: He, ZhengXiao, et al.
Published: (2025)

MedMamba: Recasting Mamba for Medical Time Series Classification
by: He, ZhengXiao, et al.
Published: (2026)

Learning Fingerprints for Medical Time Series with Redundancy-Constrained Information Maximization
by: Li, Huayu, et al.
Published: (2026)

$ϕ$-Decoding: Adaptive Foresight Sampling for Balanced Inference-Time Exploration and Exploitation
by: Xu, Fangzhi, et al.
Published: (2025)

MTS-LOF: Medical Time-Series Representation Learning via Occlusion-Invariant Features
by: Li, Huayu, et al.
Published: (2023)

Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement
by: Jeon, Wonseok, et al.
Published: (2024)

Martingale Score: An Unsupervised Metric for Bayesian Rationality in LLM Reasoning
by: He, Zhonghao, et al.
Published: (2025)

RAP: Runtime Adaptive Pruning for LLM Inference
by: Liu, Huanrong, et al.
Published: (2025)

Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration
by: Wen, Zhuofan, et al.
Published: (2024)

Semi-Clairvoyant Scheduling of Speculative Decoding Requests to Minimize LLM Inference Latency
by: Li, Ruixiao, et al.
Published: (2025)

Multimodal Cardiovascular Risk Profiling Using Self-Supervised Learning of Polysomnography
by: He, Zhengxiao, et al.
Published: (2025)

Accelerating LLM Inference Throughput via Asynchronous KV Cache Prefetching
by: Dong, Yanhao, et al.
Published: (2025)

Dr-CiK: A Testbed for Foresight-Driven Agents
by: Tang, Yihong, et al.
Published: (2026)

Current Agents Fail to Leverage World Model as Tool for Foresight
by: Qian, Cheng, et al.
Published: (2026)

Martingale-Consistent Self-Supervised Learning
by: Gögl, Moritz, et al.
Published: (2026)

EEG-EMG FAConformer: Frequency Aware Conv-Transformer for the fusion of EEG and EMG
by: He, ZhengXiao, et al.
Published: (2024)

Decocted Experience Improves Test-Time Inference in LLM Agents
by: Shen, Maohao, et al.
Published: (2026)

When LLM Meets Time Series: Can LLMs Perform Multi-Step Time Series Reasoning and Inference
by: Ye, Wen, et al.
Published: (2025)

Note on Martingale Theory and Applications
by: Zou, Xiandong
Published: (2026)

Inference-Time Computations for LLM Reasoning and Planning: A Benchmark and Insights
by: Parashar, Shubham, et al.
Published: (2025)

IdealTSF: Can Non-Ideal Data Contribute to Enhancing the Performance of Time Series Forecasting Models?
by: Wang, Hua, et al.
Published: (2025)

A Contextual Combinatorial Bandit Approach to Negotiation
by: Li, Yexin, et al.
Published: (2024)

Energy-Efficient Wireless LLM Inference via Uncertainty and Importance-Aware Speculative Decoding
by: Park, Jihoon, et al.
Published: (2025)

Align-Pro: A Principled Approach to Prompt Optimization for LLM Alignment
by: Trivedi, Prashant, et al.
Published: (2025)

CHESS: Optimizing LLM Inference via Channel-Wise Thresholding and Selective Sparsification
by: He, Junhui, et al.
Published: (2024)

HeadInfer: Memory-Efficient LLM Inference by Head-wise Offloading
by: Luo, Cheng, et al.
Published: (2025)

Advancing time series completion via RFAMoE and MDFF
by: Zhang, Ci, et al.
Published: (2025)

Thermodynamic Focusing for Inference-Time Search: Practical Methods for Target-Conditioned Sampling and Prompted Inference
by: Zhang, Zhan
Published: (2025)

Sampling for Quality: Training-Free Reward-Guided LLM Decoding via Sequential Monte Carlo
by: Markovic-Voronov, Jelena, et al.
Published: (2026)

RelayLLM: Efficient Reasoning via Collaborative Decoding
by: Huang, Chengsong, et al.
Published: (2026)

WebLLM: A High-Performance In-Browser LLM Inference Engine
by: Ruan, Charlie F., et al.
Published: (2024)

CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
by: Zhu, Xiao, et al.
Published: (2026)

Sample, Scrutinize and Scale: Effective Inference-Time Search by Scaling Verification
by: Zhao, Eric, et al.
Published: (2025)

SDMixer: Sparse Dual-Mixer for Time Series Forecasting
by: Ao, Xiang
Published: (2026)

Reason for Future, Act for Now: A Principled Framework for Autonomous LLM Agents with Provable Sample Efficiency
by: Liu, Zhihan, et al.
Published: (2023)

Adaptive Layer Splitting for Wireless LLM Inference in Edge Computing: A Model-Based Reinforcement Learning Approach
by: Chen, Yuxuan, et al.
Published: (2024)

Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies
by: Timor, Nadav, et al.
Published: (2025)

The Geometric Reasoner: Manifold-Informed Latent Foresight Search for Long-Context Reasoning
by: Zhuang, Ren, et al.
Published: (2026)

WATCH: Adaptive Monitoring for AI Deployments via Weighted-Conformal Martingales
by: Prinster, Drew, et al.
Published: (2025)

A Versatile Graph Learning Approach through LLM-based Agent
by: Wei, Lanning, et al.
Published: (2023)