| 1 | Spatial Memory Augmented Reinforcement Learning |
| 2 | Object Tracking in Egocentric Videos |
| 3 | Enhancing Visual-Motor Policies with Surface Normal Estimation |
| 4 | Diffusion Model Predictive Control |
| 5 | GAM: Graph-Augmented Memory for Egocentric Video Understanding |
| 6 | Exploring Data-Efficient World Modeling and Representation Learning Based On Equivariant Architectures and Foundational 3D Models |
| 7 | Continual Reinforcement Learning for Autonomous Robotic Tasks |
| 8 | Adapting World and Human Action Models for Spatial Navigation |
| 9 | Enhancing Information Retrieval of World Models by Augmenting Latents |
| 10 | Self-Supervised End-to-End RL for Autonomous Driving in Simulation |
| 11 | LLM Guided Motion Planning: Instruction-Tuned Models for Human-Aligned Autonomous Driving |
| 12 | Exo-Ego Transfer with Foundation Model on Object-Centric Videos |
| 13 | Finetuning Robotic MLLMs to Enhance Language Perception Capabilities |
| 14 | BabyGenie |