The paper addresses the failure of fixed-price inference in resource-constrained pricing controllers by developing a target-aware controller that tracks local densities and provides certified, shrinki…

The paper proposes EPIC, an efficient and parallel decoding framework that significantly speeds up the process of constraining diffusion language model outputs using Context-Free Grammars (CFG).

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 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.

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…

The paper establishes information-theoretic lower bounds for stochastic optimization using low-bit gradients by reducing the problem to compressed Gaussian mean estimation, yielding sharp bounds on co…

This paper improves the foundations of neural likelihood approximation for Bayesian inverse problems by making the learning problem strictly convex and showing convergence to the true likelihood.

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 argues that large language models have fundamental limitations as general-purpose solvers due to the capacity-limited nature of language as a communication channel and alignment constraints…

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 MINTS, a minimalist Bayesian framework that simplifies sequential decision-making by placing priors only on the optimum location, allowing for the incorporation of structural cons…

This paper proposes a Bayesian framework to enhance membership inference attacks against released statistics by incorporating prior knowledge about the population's attribute dependency structure, out…

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…

The paper proposes a unified, constrained optimization framework using KL divergence and likelihood constraints to achieve effective and principled unlearning in diffusion models.

The paper develops a general framework to exactly characterize the composition of mechanisms satisfying multiple differential privacy constraints, extending known results to arbitrary numbers of const…

The paper introduces an optimal black-box auditing framework using Donsker-Varadhan estimators to estimate Rényi differential privacy (RDP) guarantees for machine learning algorithms.

This paper introduces Generalized Constraint Projection (GCP), a zero-annotation inference framework for dynamically typed languages, which separates sources of evidence for function parameters and pr…