CS269: Rethinking Motion Representation in Robot Learning (Spring 2026)

---

Course Info

• Semester: Spring 2026
• Units: 4
• Time: Mon/Wed 10-11:50am
• Location: BOELTER 4413
• Website: https://yuchencui.cc/spring2026/cs269.html
• Instructor: Yuchen Cui
• Email: yuchencui@cs.ucla.edu
• Office Hour: by appointment

---

Course Objectives

This seminar-style course examines how robot actions and skills are represented, learned, and grounded from human data for manipulation. The course centers on major debates in action representation: low-level control versus task-level abstractions; instantaneous actions versus trajectories; structured representations versus end-to-end learning; teleoperation versus passive observation; imitation versus reinforcement learning; robot-centric versus object-centric actions; explicit versus latent skills; and how action representation shapes perception. We will read classical and state-of-the-art papers, discuss their assumptions and inductive biases, and connect these ideas to manipulation, contact-rich interaction, and humanoid embodiment. The goal is to develop deep understanding of action representation choices in robot learning and to strengthen students' ability to critically evaluate and communicate technical ideas.

There will be no textbook. Links to all required readings will be provided in the class schedule.

Prerequisites

• Proficient in programming (Python preferred)
• Understanding of linear algebra and probability
• Machine learning basics

---

Schedule

Week 1	Fundamentals of Offline Imitation Learning 3/30: (no paper) 4/1: What Matters in Learning from Offline Human Demonstrations for Robot Manipulation
Week 2	Visuomotor Policies & Diffusion Models 4/6: Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware 4/8: Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
Week 3	Vision-Language-Action (VLA) Representations 4/13: LaVA-Man: Learning Visual Action Representations for Robot Manipulation 4/15: Steerable Vision-Language-Action Policies for Embodied Reasoning and Hierarchical Control
Week 4	Advanced Policy Architectures (Energy Models & In-Context Learning) 4/20: Composable Energy Policies for Reactive Motion Generation and Reinforcement Learning 4/22: Instant Policy: In-Context Imitation Learning via Graph Diffusion
Week 5	Learning from Video & Latent Action Spaces 4/27: Dexterous Manipulation Policies from RGB Human Videos via 3D Hand-Object Trajectory Reconstruction 4/29: UniVLA: Learning to Act Anywhere with Task-centric Latent Actions 5/1: Project Proposal Due
Week 6	Scaling Data & Mobile Manipulation via Foundation Models 5/4: HoMMI: Learning Whole-Body Mobile Manipulation from Human Demonstrations 5/6: Scaling Robot Policy Learning via Zero-Shot Labeling with Foundation Models
Week 7	Zero-Shot Transfer & Sim-to-Real 5/11: LAP: Language-Action Pre-Training Enables Zero-shot Cross-Embodiment Transfer 5/13: SimToolReal: An Object-Centric Policy for Zero-Shot Dexterous Tool Manipulation
Week 8	Reinforcement Learning Fine-Tuning & Planning 5/18: Posterior Behavioral Cloning: Pretraining BC Policies for Efficient RL Finetuning 5/20: Bilevel Learning for Bilevel Planning
Week 9	World Models & Unified Pretraining 5/25: Unified Video Action Model 5/27: Unified World Models: Coupling Video and Action Diffusion for Pretraining on Large Robotic Datasets
Week 10	Student Project Presentations 6/1 & 6/3 6/5: Project Report Due

Grading (Course Policies)

20% Paper Presentation
20% Participation
60% Final Project

Generative AI Policy
UCLA GenAI Guidance

Academic Honesty Statement
UCLA Academic Integrity Statement

Title IX and Equity, Diversity and Inclusion

Advocacy and Confidential Services:
Please note that Title IX prohibits gender discrimination, including sexual harassment, domestic and dating violence, sexual assault, and stalking. If you have experienced sexual harassment or sexual violence, you can receive confidential support and advocacy at the CARE Advocacy Office for Sexual and Gender-Based Violence, 205 Covel Commons, Los Angeles, CA, 90095, care@careprogram.ucla.edu, (310) 206-2465. Counseling and Psychological Services (CAPS) provides confidential counseling to all students and can be reached 24/7 at (310) 825-0768.

Reporting and Non-confidential Services:
Your professor is required under the UC Policy on Sexual Violence and Sexual Harassment to inform the Title IX Coordinator should he become aware that you or any other student has experienced sexual violence or sexual harassment. In addition, you can also report sexual violence or sexual harassment directly to the University’s Title IX Coordinator, 2255 Murphy Hall, titleix@equity.ucla.edu, (310) 206-3417. Reports to law enforcement can be made to UCPD at (310) 825-1491.

Engineering EDI Resources:
There are a number of specific resources on Equity, Diversity, and Inclusion available to students in the Samueli School of Engineering, including trained faculty officers in each department who can be consulted if you have a question on EDI issues and are not sure where else to turn. Please see here for information.