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.

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…

SharedRequest introduces a model-agnostic framework that enhances LLM privacy and efficiency by batching and mixing prompts with noisy variants, achieving high utility and significant cost reduction.

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

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

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…

This paper introduces gradient inference, a new approach to developing sound and efficient gradient estimators for probabilistic programs by reducing gradient estimation to a related probabilistic inf…

EviLink addresses the ambiguity of schema linking in Text-to-SQL by treating it as an uncertainty-aware inference over multiple plausible SQL paths, significantly improving recall and efficiency.

This paper argues that the choice of divergence in statistical inference can be justified by requiring invariance to problem reformulations, leading to the selection of the Kullback-Leibler divergence…

This paper proposes Learning to Allocate (L2A), an end-to-end framework for resource-adaptive inference in Large Language Models (LLMs) using budget-conditioned and input-aware gating networks.

The paper introduces Hierarchical Adaptive Budgeter (HAB), a framework that improves LLM reasoning efficiency by adaptively allocating computational resources to match the intrinsic complexity of both…