Related papers: Embodied Interpretability: Linking Causal Understa…
In the context of having an instrumental variable, the standard practice in causal inference begins by targeting an effect of interest and proceeds by formulating assumptions enabling its identification. We turn this around by adhering to…
Leveraging pretrained Vision-Language Models (VLMs) to map language instruction and visual observations to raw low-level actions, Vision-Language-Action models (VLAs) hold great promise for achieving general-purpose robotic systems. Despite…
Recent advancements have enhanced the capability of Multimodal Large Language Models (MLLMs) to comprehend multi-image information. However, existing benchmarks primarily evaluate answer correctness, overlooking whether models genuinely…
Learning policies that effectively utilize language instructions in complex, multi-task environments is an important problem in sequential decision-making. While it is possible to condition on the entire language instruction directly, such…
One promise that Vision-Language-Action (VLA) models hold over traditional imitation learning for robotics is to leverage the broad generalization capabilities of large Vision-Language Models (VLMs) to produce versatile, "generalist" robot…
Current research on Vision-Language-Action (VLA) models predominantly focuses on enhancing generalization through established reasoning techniques. While effective, these improvements invariably increase computational complexity and…
This paper addresses intervention-based causal representation learning (CRL) under a general nonparametric latent causal model and an unknown transformation that maps the latent variables to the observed variables. Linear and general…
The visual representation of a pre-trained model prioritizes the classifiability on downstream tasks, while the widespread applications for pre-trained visual models have posed new requirements for representation interpretability. However,…
Vision-based imitation learning has enabled impressive robotic manipulation skills, but its reliance on object appearance while ignoring the underlying 3D scene structure leads to low training efficiency and poor generalization. To address…
In settings where Machine Learning (ML) algorithms automate or inform consequential decisions about people, individual decision subjects are often incentivized to strategically modify their observable attributes to receive more favorable…
Instrumental variable methods have been widely used to identify causal effects in the presence of unmeasured confounding. A key identification condition known as the exclusion restriction states that the instrument cannot have a direct…
Interpretability research on large language models (LLMs) has yielded important insights into model behaviour, yet recurring pitfalls persist: findings that do not generalise, and causal interpretations that outrun the evidence. Our…
A common approach to mechanistic interpretability is to causally manipulate model representations via targeted interventions in order to understand what those representations encode. Here we ask whether such interventions create…
Instrumental variable methods are fundamental to causal inference when treatment assignment is confounded by unobserved variables. In this article, we develop a general nonparametric causal framework for identification and learning with…
Mendelian randomization (MR) considers using genetic variants as instrumental variables (IVs) to infer causal effects in observational studies. However, the validity of causal inference in MR can be compromised when the IVs are potentially…
Principal stratification is a popular framework for causal inference in the presence of an intermediate outcome. While the principal average treatment effects are the standard target of inference, they may be insufficient when interest lies…
Implicit neural representation (INR) has become the standard approach for arbitrary-scale image super-resolution (ASSR). To date, no empirical study has systematically examined the effectiveness of existing methods, nor investigated the…
We study causal representation learning, the task of inferring latent causal variables and their causal relations from high-dimensional mixtures of the variables. Prior work relies on weak supervision, in the form of counterfactual pre- and…
Evaluating the causal effect of an intervention on multivariate outcomes is challenging when the outcomes are interdependent and derived rather than directly observed. Effective connectivity, which summarizes the directional neural…
Machine learning systems show significant promise for forecasting patient adverse events via risk scores. However, these risk scores implicitly encode assumptions about future interventions that the patient is likely to receive, based on…