Related papers: Physically Interpretable World Models via Weakly S…
Text-to-image (T2I) models today are capable of producing photorealistic, instruction-following images, yet they still frequently fail on prompts that require implicit world knowledge. Existing evaluation protocols either emphasize…
Action-conditioned video prediction models (often referred to as world models) have shown strong potential for robotics applications, but existing approaches are often slow and struggle to capture physically consistent interactions over…
Model-Based Reinforcement Learning distinguishes between physical dynamics models operating on proprioceptive inputs and latent dynamics models operating on high-dimensional image observations. A prominent latent approach is the Recurrent…
The modeling and simulation of high-dimensional multiscale systems is a critical challenge across all areas of science and engineering. It is broadly believed that even with today's computer advances resolving all spatiotemporal scales…
Though neural networks trained on large datasets have been successfully used to describe and predict many physical phenomena, there is a sense among scientists that, unlike traditional scientific models comprising simple mathematical…
Model interpretability is an increasingly important component of practical machine learning. Some of the most common forms of interpretability systems are example-based, local, and global explanations. One of the main challenges in…
Visual imitation learning enables robotic agents to acquire skills by observing expert demonstration videos. In the one-shot setting, the agent generates a policy after observing a single expert demonstration without additional fine-tuning.…
Physics-informed neural networks (PINNs) have made significant strides in modeling dynamical systems governed by partial differential equations (PDEs). However, their generalization capabilities across varying scenarios remain limited. To…
PiML (read $\pi$-ML, /`pai`em`el/) is an integrated and open-access Python toolbox for interpretable machine learning model development and model diagnostics. It is designed with machine learning workflows in both low-code and high-code…
State of the art machine learning algorithms are highly optimized to provide the optimal prediction possible, naturally resulting in complex models. While these models often outperform simpler more interpretable models by order of…
Our aim is to learn to solve long-horizon decision-making problems in complex robotics domains given low-level skills and a handful of short-horizon demonstrations containing sequences of images. To this end, we focus on learning abstract…
This letter proposes a physics-aware multi-modal contrastive learning framework designed to transform complex seismic wavefields into human-readable physical representations. Traditional data-driven inversion methods often focus on…
Probabilistic graphical models (PGMs) are widely used to discover latent structure in data, but their success hinges on selecting an appropriate model design. In practice, model specification is difficult and often requires iterative…
Physics-Informed Machine Learning (PIML) has successfully integrated mechanistic understanding into machine learning, particularly in domains governed by well-known physical laws. This success has motivated efforts to apply PIML to biology,…
World models learn to predict the temporal evolution of visual observations given a control signal, potentially enabling agents to reason about environments through forward simulation. Because of the focus on forward simulation, current…
Decision analysis deals with modeling and enhancing decision processes. A principal challenge in improving behavior is in obtaining a transparent description of existing behavior in the first place. In this paper, we develop an expressive,…
The recently developed Prior-Data Fitted Networks (PFNs) have shown very promising results for applications in low-data regimes. The TabPFN model, a special case of PFNs for tabular data, is able to achieve state-of-the-art performance on a…
Transformer-based models generate hidden states that are difficult to interpret. In this work, we analyze hidden states and modify them at inference, with a focus on motion forecasting. We use linear probing to analyze whether interpretable…
Language-guided robotic manipulation is a challenging task that requires an embodied agent to follow abstract user instructions to accomplish various complex manipulation tasks. Previous work trivially fitting the data without revealing the…
We propose Partially Interpretable Estimators (PIE) which attribute a prediction to individual features via an interpretable model, while a (possibly) small part of the PIE prediction is attributed to the interaction of features via a…