Deepak Pathak
Carnegie Mellon University Africa · 98 works · 11,857 citations · h-index 30
Top works
- Context Encoders: Feature Learning by Inpainting
- Curiosity-Driven Exploration by Self-Supervised Prediction
- Learning Features by Watching Objects Move
- Toward Multimodal Image-to-Image Translation
- Fully Convolutional Multi-Class Multiple Instance Learning
- RMA: Rapid Motor Adaptation for Legged Robots
- Large-Scale Study of Curiosity-Driven Learning
- Detector discovery in the wild: Joint multiple instance and representation learning
- Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents
- Zero-Shot Visual Imitation
- Your Diffusion Model is Secretly a Zero-Shot Classifier
- FLAVR: Flow-Agnostic Video Representations for Fast Frame Interpolation
- LEAP Hand: Low-Cost, Efficient, and Anthropomorphic Hand for Robot Learning
- Multimodality Helps Unimodality: Cross-Modal Few-Shot Learning with Multimodal Models
- Affordances from Human Videos as a Versatile Representation for Robotics
- Evaluating Text-to-Visual Generation with Image-to-Text Generation
- Compositional GAN: Learning Image-Conditional Binary Composition
- Adapting Rapid Motor Adaptation for Bipedal Robots
- Investigating Human Priors for Playing Video Games
- Legs as Manipulator: Pushing Quadrupedal Agility Beyond Locomotion