Yen-Chen Lin
Research Scientist
NVIDIA
Email: yenchenl [at] nvidia (dot) com
Twitter / Google Scholar / Github
I am a research scientist at NVIDIA. I am interested in generative AI.
Previously, I was a Ph.D. student at MIT working with Phillip Isola and Alberto Rodriguez.
MIRA: Mental Imagery for Robotic Affordances
NeRF lets us synthesize novel orthographic views that work well with pixel-wise algorithms for robotic manipulation.
NeRF-Supervision: Learning Dense Object Descriptors from Neural Radiance Fields
Generating correspondences with Neural Radiance Fields (NeRF) enables robotic manipulation of objects (e.g., forks) that can't be reconstructed by RGB-D cameras or multi-view stereo.
iNeRF: Inverting Neural Radiance Fields for Pose Estimation
Performing differentiable rendering with Neural Radiance Fields (NeRF) enables object pose estimation and camera tracking.
Learning to See before Learning to Act: Visual Pre-training for Manipulation
Transferring pre-trained vision models to perform grasping results in better sample efficiency and accuracy.
Experience-embedded Visual Foresight
Meta-learning the video prediction models allows the robot to adapt to new objects' visual dynamics.
Omnipush: accurate, diverse, real-world dataset of pushing dynamics with RGBD images
A dataset for meta-learning dynamic models.
It consists of 250 pushes for each of 250 objects, all recorded with RGB-D camera and a high precision tracking system.
Tactics for Adversarial Attack on Deep Reinforcement Learning Agents
Strategies for adversarial attacks on deep RL agents.
Deep 360 Pilot: Learning a Deep Agent for Piloting through 360° Sports Videos
CVPR 2017
Oral Presentation
An agent that learns to guide users where to look in 360° sports videos.
Tell Me Where to Look: Investigating Ways for Assisting Focus in 360° Video
CHI 2017
A study about how to assist users when watching 360° videos.