paper-with-me

Papers

Energy-Based Cross Attention for Bayesian Context Update in Text-to-Image Diffusion Models

2023-06-16 · NeurIPS 2023 11 · Geon Yeong Park, Jeongsol Kim, Beomsu Kim, Sang Wan Lee, Jong Chul Ye

Despite the remarkable performance of text-to-image diffusion models in image generation tasks, recent studies have raised the issue that generated images sometimes cannot capture the intended semantic contents of the text prompts, which phenomenon is often called semantic misalignment. To address this, here we present a novel energy-based model (EBM) framework for adaptive context control by modeling the posterior of context vectors. Specifically, we first formulate EBMs of latent image representations and text embeddings in each cross-attention layer of the denoising autoencoder. Then, we obtain the gradient of the log posterior of context vectors, which can be updated and transferred to the subsequent cross-attention layer, thereby implicitly minimizing a nested hierarchy of energy functions. Our latent EBMs further allow zero-shot compositional generation as a linear combination of cross-attention outputs from different contexts. Using extensive experiments, we demonstrate that the proposed method is highly effective in handling various image generation tasks, including multi-concept generation, text-guided image inpainting, and real and synthetic image editing. Code: https://github.com/EnergyAttention/Energy-Based-CrossAttention.

📄 PDF Abstract BibTeX arXiv:2306.09869

Code (1)

energyattention/energy-based-crossattention 공식 구현 pytorch

Tasks

DenoisingImage GenerationImage Inpainting

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…

Similar Papers 제목 키워드 기반

In-context denoising with one-layer transformers: connections between attention and associative memory retrieval

2025-02-07 · Matthew Smart, Alberto Bietti, Anirvan M. Sengupta

We introduce in-context denoising, a task that refines the connection between attention-based architectures and dense associative memory (DAM) networks, also known as modern Hopfield networks. Using a Bayesian framework,…

DenoisingIn-Context LearningRetrieval

Gradient Dynamics of Attention: How Cross-Entropy Sculpts Bayesian Manifolds

2025-12-27 · Naman Agarwal, Siddhartha R. Dalal, Vishal Misra arxiv

Transformers empirically perform precise probabilistic reasoning in carefully constructed ``Bayesian wind tunnels'' and in large-scale language models, yet the mechanisms by which gradient-based learning creates the requ…

Bayesian Inference

Tree Attention: Topology-aware Decoding for Long-Context Attention on GPU clusters

2024-08-07 · Vasudev Shyam, Jonathan Pilault, Emily Shepperd, Quentin Anthony 외

Self-attention is the core mathematical operation of modern transformer architectures and is also a significant computational bottleneck due to its quadratic complexity in the sequence length. In this work, we derive the…

GPU

BCL: Bayesian In-Context Learning Framework for Information Extraction

2026-06-17 · Haoliang Liu, Chengkun Cai, Xu Zhao, Han Zhu 외 arxiv

Existing information extraction (IE) tasks increasingly adopt in-context learning (ICL) with large language models. However, current approaches either show inconsistent performance across model scales or lack systematic …

Relation ClassificationInformation Extraction

The Bayesian Geometry of Transformer Attention

2025-12-27 · Naman Agarwal, Siddhartha R. Dalal, Vishal Misra arxiv

Transformers often appear to perform Bayesian reasoning in context, but verifying this rigorously has been impossible: natural data lack analytic posteriors, and large models conflate reasoning with memorization. We addr…

Bayesian Inference