Alexandre Alahi

RAP: 3D Rasterization Augmented End-to-End Planning

Stable Video Infinity: Infinite-Length Video Generation with Error Recycling

Loc$^{2}$: Interpretable Cross-View Localization via Depth-Lifted Local Feature Matching

Social-Mamba: Efficient Human Trajectory Forecasting with State-Space Models

JointDiff: Bridging Continuous and Discrete in Multi-Agent Trajectory Generation

LayerSync: Self-aligning Intermediate Layers

Combining Auxiliary Losses for Safer and More Robust Trajectory Prediction

X-GRM: Large Gaussian Reconstruction Model for Sparse-view X-rays to Computed Tomography

Rethinking Visual Intelligence: Insights From Video Pretraining

VoxDet: Rethinking 3D Semantic Scene Completion as Dense Object Detection

EvoLM: In Search of Lost Language Model Training Dynamics

TAROT: Targeted Data Selection via Optimal Transport

OSKAR: Omnimodal Self-supervised Knowledge Abstraction and Representation

Weak-for-Strong: Training Weak Meta-Agent to Harness Strong Executors

Towards Self-Supervised Covariance Estimation in Deep Heteroscedastic Regression