Search Results for author:
Found 13 papers, 1 papers with code
Can Transformers Capture Spatial Relations between Objects?
Spatial relationships between objects represent key scene information for humans to understand and interact with the world.
General Flow as Foundation Affordance for Scalable Robot Learning
Our predicted flow offers actionable geometric and physics guidance, thus facilitating stable zero-shot skill transfer in real-world scenarios. We deploy our method with a policy based on closed-loop flow prediction.
Any-point Trajectory Modeling for Policy Learning
Learning from demonstration is a powerful method for teaching robots new skills, and having more demonstration data often improves policy learning.
Imitation Learning from Observation with Automatic Discount Scheduling
Nonetheless, we identify that tasks characterized by a progress dependency property pose significant challenges for such approaches; in these tasks, the agent needs to initially learn the expert's preceding behaviors before mastering the subsequent ones.
Seer: Language Instructed Video Prediction with Latent Diffusion Models
Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals.
Delving into Transformer for Incremental Semantic Segmentation
In contrast, a Transformer based method has a natural advantage in curbing catastrophic forgetting due to its ability to model both long-term and short-term tasks.
Predictive Inference with Feature Conformal Prediction
Conformal prediction is a distribution-free technique for establishing valid prediction intervals.
Resolving Copycat Problems in Visual Imitation Learning via Residual Action Prediction
This is especially the case with image observations, where a single image only includes one view of the scene, and it suffers from a lack of motion information and object occlusions.
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor changes in the data distribution.
Fight fire with fire: countering bad shortcuts in imitation learning with good shortcuts
When operating in partially observed settings, it is important for a control policy to fuse information from a history of observations.
Keyframe-Focused Visual Imitation Learning
Imitation learning trains control policies by mimicking pre-recorded expert demonstrations.
Fighting Copycat Agents in Behavioral Cloning from Observation Histories
Imitation learning trains policies to map from input observations to the actions that an expert would choose.
Handwritten Chinese Font Generation with Collaborative Stroke Refinement
Automatic character generation is an appealing solution for new typeface design, especially for Chinese typefaces including over 3700 most commonly-used characters.
