16 citations · 41 across the 12 of their papers we have counts for
3 papers · 1 filter
Peekaboo: Text to Image Diffusion Models are Zero-Shot Segmentors
Ryan Burgert, Kanchana Ranasinghe, Xiang Li +1
Recently, text-to-image diffusion models have shown remarkable capabilities in creating realistic images from natural language prompts. However, few works have explored using these…
Neural Neural Textures Make Sim2Real Consistent
Ryan Burgert, Jinghuan Shang, Xiang Li +1
Unpaired image translation algorithms can be used for sim2real tasks, but many fail to generate temporally consistent results. We present a new approach that combines differentiabl…
Does Self-supervised Learning Really Improve Reinforcement Learning from Pixels?
Xiang Li, Jinghuan Shang, Srijan Das +1
We investigate whether self-supervised learning (SSL) can improve online reinforcement learning (RL) from pixels. We extend the contrastive reinforcement learning framework (e.g.,…