Seminar: Robot Learning

Organizer:
Prof. Dr. Abhinav Valada

Co-Organizers:
Yao Lu Akshay L Chandra Bahey Tharwat Seunggyu Song

Deep learning has become a key enabler of real world autonomous systems. Due to the significant advancement in deep learning, these systems are able to learn various tasks end-to-end, including for perception, state estimation, and control, thereby making important progress in object manipulation, scene understanding, visual recognition, object tracking, and learning-based control, amongst others. In this seminar, we will study a selection of state-of-the-art works that propose deep learning techniques for tackling various challenges in autonomous systems. In particular, we will analyze contributions in architecture design, and techniques selection that also include computer vision, reinforcement learning, imitation learning, and self-supervised learning.

Course Information

Details:	Course Number: 11LE13S-7317-M Places: 20 Room 00.021, building 080
Course Program:	Introduction: 22/10/2025 @ 13:00 How to Make a Presentation: 07/12/2026 @ 13:00 Block Seminar: 04/02/2027 @ 9:00
Evaluation Program:	Seminar Presentation: 04/02/2027 Summary Due Date: 11/02/2027
Requirements:	Basic knowledge of Deep Learning or Reinforcement Learning
Remarks:	Topics will be assigned for the seminar via a preference voting. If there are more interested students than places, places will be assigned based on priority suggestions of the HisInOne system and motivation. The date of registration is irrelevant. In particular, we want to avoid that students grab a topic and then leave the seminar. Please have a coarse look at all available papers to make an informed decision before you commit.

Course Material

Slides:	Introduction Lecture 2: TBD
Templates:	Summary Presentation

Additional Information

Enrollment Procedure

• Enroll through HISinOne, the course number is 11LE13S-7317-M.
• The registration period for the seminars is from 19/10/2026 to 26/10/2026.
• Attend the introductory session on 22/10/2026.
• Select three topics from the topic list and complete this form (disclosed only during the introduction session) by 26/10/2026.
• Places will be assigned based on priority suggestions of HISInOne and motivation of the student on 29/10/2026.

Evaluation Details

• Students are expected to prepare a 30-minute long presentation (as groups of three) and draft a summary (individual).
• The seminar will be held as a "Blockseminar".
• The slides of your presentation should be discussed with the supervisor two weeks before the Blockseminar.
• The summary should not exceed seven pages (excluding bibliography and figures). Significantly longer summaries will not be accepted.
• Ensure you cite all work you use including images and illustrations. Where possible, try to use your own illustrations.
• The final grade is based on the oral presentation, the summary, and participation in the blockseminar.

What should the Summary contain?

The summary should address the following questions:

• What are the connections and distinctions of the papers in your topic area?
• What is your paper's main contribution and why is it important?
• How does it relate to other techniques in the literature?
• What are the strengths and weaknesses of the paper?
• What would be some interesting follow-up work? Can you suggest any possible improvements in the proposed methods? Are there any further interesting applications that the authors might have overlooked?

Graded Component Submission

• Save your document as a PDF and directly submit it to your topic supervisor via email.
• The filename should be in the format "FirstName_LastName_X.pdf" where X is the evaluation component (Summary / Presentation).

Topics

1. Spatial-Temporal Memory for Robotics
   • Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulation (RA-L 2025)
   • ReMEmbR: Building and Reasoning Over Long-Horizon Spatio-Temporal Memory for Robot Navigation (ICRA 2025)
   Supervisor: Yao Lu
2. Interactive Perception and Learning Functional State Transitions
   • SpotLight: Robotic Scene Understanding through Interaction and Affordance Detection (Humanoids 2025)
   • Learning Causal Relationships of Object Properties and Affordances Through Human Demonstrations and Self-Supervised Intervention for Purposeful Action in Transfer Environments (R-AL 2022)
   Supervisor: Yao Lu
3. Online Functional Scene Graph Mapping
   • Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces (CVPR 2025)
   • Functional-SLAM: Interaction-Aware Mapping with Online Functional Scene Graphs (CoRL 2026)
   Supervisor: Seunggyu Song
4. Long Term Active Mapping with Imagined Gaussians
   • 3D Gaussian Splatting for Real-Time Radiance Field Rendering (ACM 2023)
   • MAGICIAN: Efficient Long-Term Planning with Imagined Gaussians for Active Mapping (CVPR 2026)
   Supervisor: Seunggyu Song
5. Physics Interpretability in World Models
   • Interpreting Physics in Video World Models (ICML 2026)
   • What Can Latent World Models Know? Physical Information in Multimodal Predictive Representations
   Supervisor: Akshay L Chandra
6. Post-Training of Robot Policies in Real-World
   • Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning
   • EXPO-FT: Sample-Efficient Reinforcement Learning Finetuning for Vision-Language-Action Models
   Supervisor: Akshay L Chandra
7. Continual Learning of Robot Policies
   • Simple Recipe Works: Vision-Language-Action Models are Natural Continual Learners with Reinforcement Learning (ICRA Workshop 2026)
   • CLARE: Continual Learning for Vision-Language-Action Models via Autonomous Adapter Routing and Expansion (R-AL 2026)
   Supervisor: Bahey Tharwat
8. In-Context Learning of Robot Policies
   • In-Context Imitation Learning via Next-Token Prediction (Neurips 2026)
   • RoboTTT: Context Scaling for Robot Policies
   Supervisor: Bahey Tharwat

Questions?

If you have any questions, please direct them to  Yao Lu before the topic allotment, and to your supervisor after you have received your topic.