bayesian

This paper presents the first implementation of an infra-Bayesian reinforcement learning agent, demonstrating that it outperforms classical RL in worst-case regret and handles Newcomb's problem optimally, offering a step toward robustness under model misspecification.

This paper proposes a model-agnostic probabilistic token attribution measure for LLMs using Bayes' rule to invert next-token log probabilities, capturing the model's internal representation of token sequences and improving interpretability through entropy analysis.

The paper introduces the Bayesian Filtering Transformer (BFT), which incorporates uncertainty into Transformers via precision-weighted attention and Kalman update residuals, improving performance on sequential recommendation and noisy LLM fine-tuning.

This paper introduces a new energy-based model for linear inverse problems that learns normalized posterior densities, overcoming limitations of diffusion models. It enables unbiased sampling, adaptive sampling, and blind degradation estimation, with competitive performance on ImageNet, CelebA, and AFHQ.

Introduces Bayesian Model Merging (BMM), a plug-and-play bi-level optimization framework for combining multiple task-specific experts into a single model, achieving state-of-the-art performance on vision and language benchmarks.