Marco Pavone

AccidentBench: Benchmarking Multimodal Understanding and Reasoning in Vehicle Accidents and Beyond

ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning

E3D-Bench: A Benchmark for End-to-End 3D Geometric Foundation Models

PRISM: Robust VLM Alignment with Principled Reasoning for Integrated Safety in Multimodality

Accelerating Structured Chain-of-Thought in Autonomous Vehicles

FoundationMotion: Auto-labeling and Reasoning about Spatial Movement in Videos

Uncovering And Correcting Perception Model Weaknesses Using VLM-Based Analysis

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

OmniRe: Omni Urban Scene Reconstruction

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

Offline Hierarchical Reinforcement Learning via Inverse Optimization

Learning Multiple Initial Solutions to Optimization Problems

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

Language-Image Models with 3D Understanding

Learning Multiple Initial Solutions to Optimization Problems

Wolf: Accurate Video Captioning with a World Summarization Framework

VILA^2: VLM Augmented VLM with Self-Improvement

FAVEN: Fast Audio-Visual Embodied Navigation in 3D Environments