Deform360: A Massive Multi-view Visuotactile Dataset for Deformable World Models Paper • 2607.05390 • Published 13 days ago • 10
A Cookbook of 3D Vision: Data, Learning Paradigms, and Application Paper • 2606.04291 • Published Jun 2 • 4
Causal-JEPA: Learning World Models through Object-Level Latent Interventions Paper • 2602.11389 • Published Feb 11 • 12
The Persona Paradox: Medical Personas as Behavioral Priors in Clinical Language Models Paper • 2601.05376 • Published Jan 8 • 1
Force Prompting: Video Generation Models Can Learn and Generalize Physics-based Control Signals Paper • 2505.19386 • Published May 26, 2025 • 11
Goal Force: Teaching Video Models To Accomplish Physics-Conditioned Goals Paper • 2601.05848 • Published Jan 9 • 16
How Good is your Explanation? Algorithmic Stability Measures to Assess the Quality of Explanations for Deep Neural Networks Paper • 2009.04521 • Published Sep 7, 2020
Unlocking Feature Visualization for Deeper Networks with MAgnitude Constrained Optimization Paper • 2306.06805 • Published Jun 11, 2023
A Holistic Approach to Unifying Automatic Concept Extraction and Concept Importance Estimation Paper • 2306.07304 • Published Jun 11, 2023
Look at the Variance! Efficient Black-box Explanations with Sobol-based Sensitivity Analysis Paper • 2111.04138 • Published Nov 7, 2021
Harmonizing the object recognition strategies of deep neural networks with humans Paper • 2211.04533 • Published Nov 8, 2022
The 3D-PC: a benchmark for visual perspective taking in humans and machines Paper • 2406.04138 • Published Jun 6, 2024