Week 1 Jan 23

LecIntroduction TutHPC tutorial

• Introduction
• History of self-driving cars
• Embodied learning
• Suggested readings
  • Turing (1950) Computing Machinery and Intelligence
  • Pomerleau (1988) ALVINN: An Autonomous Land Vehicle in a Neural Network
  • [Video] History Channel 1998 : Driverless Car Technology Overview at Carnegie Mellon University
  • Smith & Gasser (2005) The Development of Embodied Cognition: Six Lessons from Babies

Week 2 Jan 30

LecDeep Learning for Structured Outputs TutSimulator Tutorial

• Suggested readings
  • LeCun (2006) A Tutorial on Energy-Based Learning
  • Girshick et al. (2013) Rich feature hierarchies for accurate object detection and semantic segmentation
  • Long et al. (2014) Fully Convolutional Networks for Semantic Segmentation
  • Zheng et al. (2015) Conditional Random Fields as Recurrent Neural Networks
  • Chen et al. (2016) DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs
  • Kingma & Dhariwal (2018) Glow: Generative Flow with Invertible 1x1 Convolutions
  • Ho et al. (2020) Denoising Diffusion Probabilistic Models
• Additional readings
  • Carion et al. (2020) End-to-End Object Detection with Transformers
  • Kamath et al. (2021) MDETR – Modulated Detection for End-to-End Multi-Modal Understanding
  • Cheng et al. (2021) Per-Pixel Classification is Not All You Need for Semantic Segmentation
  • Rombach et al. (2022) High-Resolution Image Synthesis with Latent Diffusion Models
  • Kirillov et al. (2023) Segment Anything
  • Bai et al. (2023) Sequential Modeling Enables Scalable Learning for Large Vision Models
  • Chi et al. (2023) Diffusion Policy: Visuomotor Policy Learning via Action Diffusion

Week 3 Feb 6

Lec3D Vision, Mapping TutVideo Learning Tutorial

• Suggested readings:
  • Fischer et al. (2015) FlowNet: Learning Optical Flow with Convolutional Networks
  • Godard et al. (2016) Unsupervised Monocular Depth Estimation with Left-Right Consistency
  • Qi et al. (2016) PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation
  • Tamar et al. (2016) Value Iteration Networks
  • Parisotto et al. (2017) Neural Map: Structured Memory for Deep Reinforcement Learning
  • Gupta et al. (2017) Cognitive Mapping and Planning for Visual Navigation
• Additional readings:
  • Chaplot et al. (2020) Neural Topological SLAM for Visual Navigation
  • Huang et al. (2022) FlowFormer: A Transformer Architecture for Optical Flow
  • Wu et al. (2023) Policy Pre-training for Autonomous Driving via Self-supervised Geometric Modeling
  • Sun et al. (2023) Dynamo-Depth: Fixing Unsupervised Depth Estimation for Dynamical Scenes
  • Yang et al. (2024) Depth Anything: Unleashing the Power of Large-Scale Unlabeled Data
  • Wang et al. (2025) Continuous 3D Perception Model with Persistent State

Week 4 Feb 13

LecSelf-Supervised Representation Learning and Object Discovery TutEgocentric Video Tutorial

• Suggested readings:
  • Sermanet et al. (2017) Time-Contrastive Networks: Self-Supervised Learning from Video
  • Van den Oord et al. (2018) Representation Learning with Contrastive Predictive Coding
  • Wu et al. (2018) Unsupervised Feature Learning via Non-Parametric Instance-level Discrimination
  • Chen et al. (2020) A Simple Framework for Contrastive Learning of Visual Representations
  • Grill et al. (2020) Bootstrap Your Own Latent: A New Approach to Self-Supervised Learning
  • He et al. (2021) Masked Autoencoders Are Scalable Vision Learners
• Additional readings:
  • Weinzaepfel et al. (2022) CroCo v2: Improved Cross-view Completion Pre-training for Stereo Matching and Optical Flow
  • Wang et al. (2022) Self-Supervised Transformers for Unsupervised Object Discovery using Normalized Cut
  • Seo et al. (2022) Masked World Models for Visual Control
  • Venkataramanan et al. (2023) Is ImageNet Worth 1 Video? Learning Strong Image Encoders from 1 Long Unlabelled Video
  • van Steenkiste et al. (2024) Moving Off-the-Grid: Scene-Grounded Video Representations
  • Cui et al. (2024) DynaMo: In-Domain Dynamics Pretraining for Visuo-Motor Control
  • Wang et al. (2024) PooDLe: Pooled and Dense Self-Supervised Learning from Naturalistic Videos

Week 5 Feb 20

LecWorld Models and Forecasting TutMotion Learning Tutorial