Kiana Ehsani

16

Papers

148

Total Citations

Papers (16)

Molmo and PixMo: Open Weights and Open Data for State-of-the-Art Vision-Language Models

SPOC: Imitating Shortest Paths in Simulation Enables Effective Navigation and Manipulation in the Real World

Who Let the Dogs Out? Modeling Dog Behavior From Visual Data

SeGAN: Segmenting and Generating the Invisible

Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning

Use the Force, Luke! Learning to Predict Physical Forces by Simulating Effects

ManipulaTHOR: A Framework for Visual Object Manipulation

Objaverse: A Universe of Annotated 3D Objects

Phone2Proc: Bringing Robust Robots Into Our Chaotic World

Contrasting Contrastive Self-Supervised Representation Learning Pipelines

Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery

Object Manipulation via Visual Target Localization

Continuous Scene Representations for Embodied AI

Promptable Behaviors: Personalizing Multi-Objective Rewards from Human Preferences

🏘️ ProcTHOR: Large-Scale Embodied AI Using Procedural Generation

Objaverse-XL: A Universe of 10M+ 3D Objects