Related papers: Controllable Sequence Editing for Biological and C…

Neural sequence to sequence models are well established for applications which can be cast as mapping a single input sequence into a single output sequence. In this work, we focus on cases where generation is conditioned on both a short…

We present GO-CBED, a goal-oriented Bayesian framework for sequential causal experimental design. Unlike conventional approaches that select interventions aimed at inferring the full causal model, GO-CBED directly maximizes the expected…

Controllable text generation concerns two fundamental tasks of wide applications, namely generating text of given attributes (i.e., attribute-conditional generation), and minimally editing existing text to possess desired attributes (i.e.,…

Generative models lack rigorous statistical guarantees for their outputs and are therefore unreliable in safety-critical applications. In this work, we propose Sequential Conformal Prediction for Generative Models (SCOPE-Gen), a sequential…

Counterfactual explanations (CFs) provide human-interpretable insights into model's predictions by identifying minimal changes to input features that would alter the model's output. However, existing methods struggle to generate multiple…

Machine learning models are widely used in real-world applications. However, their complexity makes it often challenging to interpret the rationale behind their decisions. Counterfactual explanations (CEs) have emerged as a viable solution…

In a controlled experiment of sequence-to-sequence approaches for the task of sentence correction, we find that character-based models are generally more effective than word-based models and models that encode subword information via…

Counterfactual Explanations (CEs) help address the question: How can the factors that influence the prediction of a predictive model be changed to achieve a more favorable outcome from a user's perspective? Thus, they bear the potential to…

AI-assisted protein design has emerged as a critical tool for advancing biotechnology, as deep generative models have demonstrated their reliability in this domain. However, most existing models primarily utilize protein sequence or…

Partial observations of continuous time-series dynamics at arbitrary time stamps exist in many disciplines. Fitting this type of data using statistical models with continuous dynamics is not only promising at an intuitive level but also has…

Machine learning models perform well on several healthcare tasks and can help reduce the burden on the healthcare system. However, the lack of explainability is a major roadblock to their adoption in hospitals. \textit{How can the decision…

Estimating causal effects from observational data is inherently challenging due to the lack of observable counterfactual outcomes and even the presence of unmeasured confounding. Traditional methods often rely on restrictive, untestable…

Background: Stepped wedge cluster randomized trials (SW-CRTs) involve sequential measurements within clusters over time. Initially, all clusters start in the control condition before crossing over to the intervention on a staggered…

Classifier-Free Guidance (CFG) is widely used to improve conditional fidelity in diffusion models, but its impact on sampling dynamics remains poorly understood. Prior studies, often restricted to unimodal conditional distributions or…

As large-scale language models become the standard for text generation, there is a greater need to tailor the generations to be more or less concise, targeted, and informative, depending on the audience/application. Existing control…

Predictive process analytics focuses on predicting future states, such as the outcome of running process instances. These techniques often use machine learning models or deep learning models (such as LSTM) to make such predictions. However,…

We present a training-free framework for continuous and controllable image editing at test time for text-conditioned generative models. In contrast to prior approaches that rely on additional training or manual user intervention, we find…

Simulating in silico cellular responses to interventions is a promising direction to accelerate high-content image-based assays, critical for advancing drug discovery and gene editing. To support this, we introduce MorphGen, a…

Controllable text generation systems often leverage control codes to direct various properties of the output like style and length. Inspired by recent work on causal inference for NLP, this paper reveals a previously overlooked flaw in…

Counterfactual simulation - exploring hypothetical consequences under alternative clinical scenarios - holds promise for transformative applications such as personalized medicine and in silico trials. However, it remains challenging due to…