2026 - Thesis & Poster - SSL
USZ
References
- ViT: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale, ICLR 2021.
- Large-scale pancreatic cancer detection via non-contrast CT and deep learning, Nature 2023.
- BYOL: Bootstrap your own latent: A new approach to self-supervised Learning, GDM, NeurIPS 2020.
- CLIP: Learning Transferable Visual Models From Natural Language Supervision, ICML 2021.
- AlexNet: ImageNet Classification with Deep Convolutional Neural Networks, NeurIPS 2012.
- đ ResNet: Deep Residual Learning, CVPR 2015.
- 2017 - FLAME: Learning a model of facial shape and expression from 4D scans ( + SMPL)
- Epochs
Representation Learning
â˛
â
Small / Limited Supervision ââââ Tabular / Medical Data
- Moderate clustering metrics across PCA, t-SNE, and UMAP indicate non-random latent structure but insufficient outcome separability, highlighting the need for representation learning beyond geometric proximity in raw tabular space.
The âRight Abstractionâ for A System
Category | Focus Area / Topics
----------------------------------|------------------------------------------------------------
Representation & Inductive Bias | Network architecture design
| Multimodal alignment (visionâlanguageâaction)
| World models
|
| Impact of good inductive bias:
| - 10Ă less data required
| - 100Ă lower training cost
Learning Ă Control | Model-based reinforcement learning
| Differentiable MPC
| Latent dynamics models
| Structured sim-to-real methods
|
| Key insight:
| - Control background is a major advantage
| - Not brute-force learning
System-level AI | ML compilers
| Scheduling on heterogeneous hardware
| Memory-aware training
| Inference optimization
|
| These areas strongly reward intelligent
| system and structure design
Robotics / Embodied AI | Not actuators, SEA, or motors
| (These are constrained by physics)
|
| Instead focus on:
| - Contact representation
| - Hybrid system abstraction
| - Task decomposition
| - Perceptionâcontrol interfaces
| - Failure-aware planning
|
| Goal:
| - Replace large sets of heuristics with
| a unified abstraction