20 results for “inference efficiency”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
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.
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.
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…
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…
This paper investigates the trade-off between the information budget and the distortion of summaries in simulation-based inference.
This paper analyzes the reliability of efficient membership inference attack (MIA) evaluation methods, demonstrating that standard aggregation techniques introduce biases that compromise accurate vuln…
This paper proposes a comprehensive benchmarking framework for evaluating mutual information estimation methods on complex, realistic data using copula theory.
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,…
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…
The paper proposes Large Language Gibbs, a scheme for structured probabilistic inference using conditional distributions of large language models as transition operators.
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…
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…
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.
The paper proposes a general approach to augmenting exact exponential-time algorithms for NP-hard problems using machine-learned predictions.
This paper improves the theoretical bounds for estimating discrete probability distributions using the $\ell_\infty$ norm, resolving several open questions in the field.
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.
This paper introduces SPLIT, a method to optimize the allocation of compute resources for language models and agents to achieve accurate results.
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…