Marco Pavone

14

Papers

378

Total Citations

Papers (14)

Dolphins: Multimodal Language Model for Driving

Driving Everywhere with Large Language Model Policy Adaptation

Describe Anything: Detailed Localized Image and Video Captioning

Producing and Leveraging Online Map Uncertainty in Trajectory Prediction

Closed-Loop Supervised Fine-Tuning of Tokenized Traffic Models

Language-Image Models with 3D Understanding

STORM: Spatio-TempOral Reconstruction Model For Large-Scale Outdoor Scenes

Scaling Vision Pre-Training to 4K Resolution

LoRA3D: Low-Rank Self-Calibration of 3D Geometric Foundation models

Cocoon: Robust Multi-Modal Perception with Uncertainty-Aware Sensor Fusion

Extrapolated Urban View Synthesis Benchmark

Bias in Gender Bias Benchmarks: How Spurious Features Distort Evaluation

PARA-Drive: Parallelized Architecture for Real-time Autonomous Driving

Parallelized Spatiotemporal Slot Binding for Videos