Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving?
Paper • 2610.09695 • Published • 18
🔄 In a Training Loop
Tianyu Li
sephyli
AI & ML interests
PhD student at OpenDriveLab and Shanghai Innovation Institute
Autonomous Driving, 3D Reconstruction
Recent Activity
authored a paper 4 days ago
Do Better Visual Representations Always Lead to Better End-to-End Autonomous Driving? authored a paper 4 days ago
SimVTA: Simulation-Grounded Video-Trajectory Alignment for Driving World Action ModelsOrganizations
authored 2
papers 4 days ago
upvoted 2
papers 5 days ago
upvoted a paper 12 days ago
upvoted a paper about 2 months ago
authored 3
papers 2 months ago
World Engine: Towards the Era of Post-Training for Autonomous Driving
Paper • 2606.19836 • Published • 2
123D: Unifying Multi-Modal Autonomous Driving Data at Scale
Paper • 2605.08084 • Published
SMASH: Mastering Scalable Whole-Body Skills for Humanoid Ping-Pong with Egocentric Vision
Paper • 2604.01158 • Published
upvoted a paper 2 months ago
updated a
model 7 months ago
authored 5
papers 8 months ago
TopoPoint: Enhance Topology Reasoning via Endpoint Detection in Autonomous Driving
Paper • 2505.17771 • Published
Fully Sparse 3D Occupancy Prediction
Paper • 2312.17118 • Published
Delving into the Devils of Bird's-eye-view Perception: A Review, Evaluation and Recipe
Paper • 2209.05324 • Published
3D Data Augmentation for Driving Scenes on Camera
Paper • 2303.10340 • Published
LatentVLA: Efficient Vision-Language Models for Autonomous Driving via Latent Action Prediction
Paper • 2601.05611 • Published
upvoted 3
papers 8 months ago
Sparse Video Generation Propels Real-World Beyond-the-View Vision-Language Navigation
Paper • 2602.05827 • Published • 18
RISE: Self-Improving Robot Policy with Compositional World Model
Paper • 2602.11075 • Published • 30
EgoHumanoid: Unlocking In-the-Wild Loco-Manipulation with Robot-Free Egocentric Demonstration
Paper • 2602.10106 • Published • 23
published a
model 8 months ago