Picture for Katerina Fragkiadaki

Katerina Fragkiadaki

DreamScene4D: Dynamic Multi-Object Scene Generation from Monocular Videos

Add code
May 03, 2024
Viaarxiv icon

HELPER-X: A Unified Instructable Embodied Agent to Tackle Four Interactive Vision-Language Domains with Memory-Augmented Language Models

Add code
Apr 29, 2024
Viaarxiv icon

Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving

Add code
Mar 12, 2024
Figure 1 for Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
Figure 2 for Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
Figure 3 for Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
Figure 4 for Tractable Joint Prediction and Planning over Discrete Behavior Modes for Urban Driving
Viaarxiv icon

3D Diffuser Actor: Policy Diffusion with 3D Scene Representations

Add code
Feb 16, 2024
Viaarxiv icon

Diffusion-ES: Gradient-free Planning with Diffusion for Autonomous Driving and Zero-Shot Instruction Following

Add code
Feb 09, 2024
Viaarxiv icon

ODIN: A Single Model for 2D and 3D Perception

Add code
Jan 04, 2024
Viaarxiv icon

Diffusion-TTA: Test-time Adaptation of Discriminative Models via Generative Feedback

Add code
Nov 29, 2023
Viaarxiv icon

Gen2Sim: Scaling up Robot Learning in Simulation with Generative Models

Add code
Oct 27, 2023
Viaarxiv icon

Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models

Add code
Oct 23, 2023
Viaarxiv icon

Zero-Shot Open-Vocabulary Tracking with Large Pre-Trained Models

Add code
Oct 10, 2023
Viaarxiv icon