ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:

20 results for “inference efficiency”

CS papers only

Hybrid search: Keyword + semantic, ranked by combined score.ⓘ

Want pure semantic search? Try claim verification →

cs.AIcs.CLcs.LGEmpiricalRecentSep 25, 2026

Learning to Stop without Learning to Stop: Self-Supervised Confidence Training Improves Reasoning Efficiency

Parsa Hosseini, Akasha Tigalappanavara, Sumit Nawathe, Chenrui Fan +5 more

The authors improve the efficiency of reasoning models by fine-tuning them to predict their confidence in their answers, resulting in reduced generated tokens without sacrificing accuracy.

View →
cs.AIRecentMay 30, 2026

Efficient Test-time Inference for Generative Planning Models

Robert Gieselmann, Mihai Samson, Federico Pecora, Jeremy L. Wyatt

The paper proposes an efficient inference procedure for generative planning models by modifying the Open-Closed List (OCL) search, achieving superior performance over existing baselines.

View →
cs.LGcs.AIcs.CLRecentMay 27, 2026

Extrapolative Weight Averaging Reveals Correctness-Efficiency Frontiers in Code RL

Kunhao Zheng, Pierre Chambon, Juliette Decugis, Jonas Gehring +3 more

The paper demonstrates that extrapolative weight averaging can effectively navigate and extend the correctness-efficiency frontier in code RL, leading to improved performance on complex programming ta…

View →
cs.SEcs.CLSurveyRecentJun 18, 2026

Token-Operations-Oriented Inference Optimization Techniques for Large Models

Shiguo Lian, Kai Wang, Zhaoxiang Liu, Wen Liu +21 more

This paper proposes a four-layer technical architecture for large model inference optimization, including Multi-model Fusion, Model Optimization, Compute-Model Fusion, and Compute-Network-Model Fusion…

View →
stat.MLcs.LGstat.COEmpiricalRecentOct 26, 2026

Intrinsic Information Rates of Summaries in Simulation-Based Inference

Vansh Bansal, Pradip Sharma Poudel, James G. Scott

This paper investigates the trade-off between the information budget and the distortion of summaries in simulation-based inference.

View →
cs.LGcs.CRRecentMay 25, 2026

On Reliability of Efficient Membership Inference Vulnerability Evaluation

Joonas Jälkö, Gauri Pradhan, Ossi Räisä, Antti Honkela

This paper analyzes the reliability of efficient membership inference attack (MIA) evaluation methods, demonstrating that standard aggregation techniques introduce biases that compromise accurate vuln…

View →
cs.LGcs.AIcs.ITEmpiricalRecentJul 3, 2026

Towards Diverse and Comprehensive Benchmarks for Mutual Information Estimation

Alberto Foresti, Ivan Butakov, Alexander Tolmachev, Giulio Franzese +2 more

This paper proposes a comprehensive benchmarking framework for evaluating mutual information estimation methods on complex, realistic data using copula theory.

View →
cs.AIcs.CLRecentMay 27, 2026

The Importance of Being Statistically Earnest: A Critical Re-evaluation of GSM-Symbolic

Dominika Agnieszka Długosz, Arlindo Oliveira, Natalia Díaz-Rodríguez

The paper challenges the conclusion that LLMs lack reasoning by demonstrating that reported performance drops on GSM-Symbolic are often statistically weak and partially attributable to dataset biases,…

View →
cs.CRcs.LGMar 19, 2026

Towards Verifiable AI with Lightweight Cryptographic Proofs of Inference

Pranay Anchuri, Matteo Campanelli, Paul Cesaretti, Rosario Gennaro +3 more

The paper introduces a lightweight, sampling-based cryptographic protocol for verifiable AI inference that drastically reduces proving overhead from minutes to milliseconds by leveraging statistical p…

View →
cs.LGcs.CLEmpiricalRecentJun 17, 2026

Structured Inference with Large Language Gibbs

Sanghyeok Choi, Henry Gouk, Esmeralda S. Whitammer

The paper proposes Large Language Gibbs, a scheme for structured probabilistic inference using conditional distributions of large language models as transition operators.

View →
cs.AIcs.LGRecentJun 1, 2026

Extreme Low-Bit Inference in Reasoning Models: Failure Modes and Targeted Recovery

Ekaterina Alimaskina, Darya Rudas, Denis Shveykin, Gleb Molodtsov +2 more

The paper analyzes the failure modes of aggressive 2-bit quantization in large reasoning models, proposing lightweight controls like FP16 planning and loop rescue to restore accuracy and achieve pract…

View →
cs.AIcs.LGstat.MERecentMay 29, 2026

Industrializing Prediction-Powered Inference: The GLIDE Library for Reliable GenAI and Agentic Systems Evaluation

Grégoire Martinon, Ibrahim Merad, Mohammed Raki

The paper introduces GLIDE, an open-source Python library that unifies multiple state-of-the-art Prediction-Powered Inference (PPI) estimators and samplers to provide reliable, debiased estimates and…

View →
stat.MLcs.LGEmpiricalRecentOct 25, 2026

HIFI: A Highly Efficient Framework for Statistical Inference with Foundation Models

Po-Wei Chen, Shan Yu, Chunlin Li

This paper introduces HIFI, a two-stage fine-tuning framework for statistical inference on parameters such as conditional means, which scales to large foundation models and reduces training compute.

View →
cs.DScs.LGTheoreticalRecentJun 17, 2026

Learning Augmented Exact Exponential Algorithms

Tatiana Belova, Yuriy Dementiev, Danil Sagunov

The paper proposes a general approach to augmenting exact exponential-time algorithms for NP-hard problems using machine-learned predictions.

View →
stat.MLcs.AIcs.LGRecentMay 28, 2026

Improved Distribution Estimation in $\ell_\infty$

Doron Cohen, Aryeh Kontorovich, Yonatan Livshitz

This paper improves the theoretical bounds for estimating discrete probability distributions using the $\ell_\infty$ norm, resolving several open questions in the field.

View →
cs.AIEmpiricalRecentJul 16, 2026

Can We Trust Item Response Theory for AI Evaluation?

Han Jiang, Sunbeom Kwon, Jinwen Luo, Ziang Xiao +1 more

This paper evaluates the reliability of using item response theory (IRT) models for AI benchmarking, comparing four estimation tools under various simulation conditions.

View →
cs.LGcs.CLEmpiricalRecentOct 16, 2026

Sample, Mix, or Verify? Allocating Test-Time Compute under Imperfect Verifiers

Srinivasan Iyengar

This paper introduces SPLIT, a method to optimize the allocation of compute resources for language models and agents to achieve accurate results.

View →
cs.AIRecentMay 28, 2026

ProjectionBench: Evaluating Scientific Hypothesis Generation in LLMs Under Progressive Information Disclosure

A. J. Lew, Y. Cao, M. J. Buehler

The paper introduces ProjectionBench, a novel benchmark that progressively discloses information to evaluate LLMs' ability to generate scientific hypotheses, demonstrating that advanced models like GP…

View →