1

FindingDory: A Benchmark to Evaluate Memory in Embodied Agents

FindingDory evaluates long-range memory and reasoning in embodied agents.

Let's Think in Two Steps: Mitigating Agreement Bias in MLLMs with Self-Grounded Verification

Self-Grounded Verification mitigates agreement bias in MLLM verifiers for web navigation, computer use, and robotic manipulation.

Memo: Training Memory-Efficient Embodied Agents with Reinforcement Learning

Memo enables efficient memory formation and usage for long-horizon embodied RL tasks, improving generalization and efficiency.

Pre-trained Text-to-Image Diffusion Models Are Versatile Representation Learners for Control

We investigate representations from pre-trained text-to-image diffusion models for control tasks and showcase competitive performance across a wide range of tasks.

OpenEQA: Embodied Question Answering in the Era of Foundation Models

We present a new embodied question answering (EQA) dataset with open vocabulary questions.

What Do We Learn from a Large-Scale Study of Pre-Trained Visual Representations in Sim and Real Environments?

We conduct a study on using pre-trained visual representations (PVRs) to train robots for real-world tasks.

Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?

We present the largest and most comprehensive empirical study of visual foundation models for Embodied AI (EAI).

HomeRobot: Open-Vocabulary Mobile Manipulation

We propose a combined simulation and real-world benchmark on the problem of Open-Vocabulary Mobile Manipulation (OVMM).

Navigating to Objects Specified by Images

We present a modular system that can perform well on the Instance ImageNav task in both simulation and the real world.

Habitat-matterport 3d semantics dataset

We present Habitat-Matterport 3D Semantics (HM3DSEM), the largest dataset of 3D real-world spaces with densely annotated semantics.