Related papers: The Attribution Contract: Feature Attribution for …

Text-to-image generative models have recently garnered significant attention due to their ability to generate images based on prompt descriptions. While these models have shown promising performance, concerns have been raised regarding the…

Diffusion models have achieved remarkable results in image generation, and have similarly been used to learn high-performing policies in sequential decision-making tasks. Decision-making diffusion models can be trained on lower-quality…

Large language models benefit from training with a large amount of unlabeled text, which gives them increasingly fluent and diverse generation capabilities. However, using these models for text generation that takes into account target…

Current approaches for explaining machine learning models fall into two distinct classes: antecedent event influence and value attribution. The former leverages training instances to describe how much influence a training point exerts on a…

Text-to-image (T2I) models have recently gained widespread adoption. This has spurred concerns about safeguarding intellectual property rights and an increasing demand for mechanisms that prevent the generation of specific artistic styles.…

Most large language models are autoregressive: they generate tokens one at a time. Discrete diffusion language models can generate multiple tokens in parallel, but sampling from them requires a denoising order: a strategy for deciding which…

Text is a vehicle to convey information that reflects the writer's linguistic style and communicative patterns. By studying these attributes, we can discover latent insights about the author and their underlying message. This article uses…

Deep generative models have garnered significant attention in low-level vision tasks due to their generative capabilities. Among them, diffusion model-based solutions, characterized by a forward diffusion process and a reverse denoising…

Diffusion models are a class of generative models that learn to synthesize samples by inverting a diffusion process that gradually maps data into noise. While these models have enjoyed great success recently, a full theoretical…

Large Language Models (LLMs)-based question answering (QA) systems play a critical role in modern AI, demonstrating strong performance across various tasks. However, LLM-generated responses often suffer from hallucinations, unfaithful…

Neural language models are a critical component of state-of-the-art systems for machine translation, summarization, audio transcription, and other tasks. These language models are almost universally autoregressive in nature, generating…

We present Prompt Diffusion, a framework for enabling in-context learning in diffusion-based generative models. Given a pair of task-specific example images, such as depth from/to image and scribble from/to image, and a text guidance, our…

A key question in Reinforcement Learning is which representation an agent can learn to efficiently reuse knowledge between different tasks. Recently the Successor Representation was shown to have empirical benefits for transferring…

Attribution methods explain which input features drive a model's prediction, making them central to model debugging and mechanistic interpretability. Yet backward attribution methods, including gradients, LRP, and transformer-specific…

Recent efforts to address hallucinations in Large Language Models (LLMs) have focused on attributed text generation, which supplements generated texts with citations of supporting sources for post-generation fact-checking and corrections.…

Diffusion models have shown promising results in speech enhancement, using a task-adapted diffusion process for the conditional generation of clean speech given a noisy mixture. However, at test time, the neural network used for score…

RNN models have achieved the state-of-the-art performance in a wide range of text mining tasks. However, these models are often regarded as black-boxes and are criticized due to the lack of interpretability. In this paper, we enhance the…

Gradient-based attribution methods can aid in the understanding of convolutional neural networks (CNNs). However, the redundancy of attribution features and the gradient saturation problem, which weaken the ability to identify significant…

Diffusion models have shown their effectiveness in generation tasks by well-approximating the underlying probability distribution. However, diffusion models are known to suffer from an amplified inherent bias from the training data in terms…

Diffusion models have demonstrated impressive capabilities in synthesizing diverse content. However, despite their high-quality outputs, these models often perpetuate social biases, including those related to gender and race. These biases…