Spring 2025
| Date | Title | Presenter | Resources |
|---|---|---|---|
| January 17th 2025 |
Agenda Discussion
planning |
||
| January 24th 2025 |
KernMLOps
presentation |
Dr. Rossbach |
📊 Slides 🔗 GitHub repo |
| January 31st 2025 |
Evolutionary Policy Optimization
presentation |
Lain |
📊 Slides |
| February 7th 2025 |
Cautious Optimizers
presentation |
Kaizhao |
📊 Slides |
| February 14th 2025 |
PrefixRL: Optimization of Parallel Prefix Circuits using Deep Reinforcement Learning
presentation |
Kayvan |
📊 Slides 📄 PrefixRL Paper |
| February 21st 2025 |
Tensor Evolution
presentation |
Samarth |
📊 Slides 📄 Tensor Evolution Paper |
| February 28th 2025 |
Monte Carlo Methods for Estimating Expectations and Gradients of Expectations in Reinforcement Learning
presentation |
Dr. Pingali |
📊 Slides |
| March 7th 2025 |
Imitation Learning
presentation |
Lain |
📊 Slides |
| March 7th 2025 |
Reinforcement and Imitation Learning to Control Contact-Rich Interaction by Dr. Roberto Martín-Martín
guest |
Dr. Roberto Martín-Martín |
📊 Slides 📄 VICES Paper 📄 ScrewMimic Paper 📄 BaRiFlex Paper |
| March 21st 2025 |
Spring Break - No Meeting
break |
||
| March 28th 2025 |
No Meeting
break |
||
| April 4th 2025 |
Physics-Informed Neural Networks
guest |
Dr. Maciej Paszynski |
📊 Slides 📄 Physics-informed machine learning (Karniadakis et al. 2021) 📄 Collocation-based Robust Variational Physics-Informed Neural Networks (CRVPINN 2024) 📄 Robust Variational Physics-Informed Neural Networks (Computer Methods in Applied Mechanics and Engineering 2024) 📄 hp-VPINNs: Variational physics-informed neural networks with domain decomposition (Kharazmi et al. 2021) |
| April 11th 2025 |
Scheduling Languages: Past, Present & Future
guest |
Dr. Elster |
📊 Slides 📄 Scheduling Languages Paper |
| April 18th 2025 |
AI Coding Agents for Hardware-Optimized Code
presentation |
Dhairya, Irene, Pranoy |
📊 Slides 📄 KernelBench: Can LLMs Write Efficient GPU Kernels? 📄 Baldur: Whole-Proof Generation and Repair with Large Language Models |
| April 25th 2025 |
The world's simplest presentation of policy-gradient methods
presentation |
Dr. Pingali |
📊 Slides |
| May 2nd 2025 |
The world's simplest presentation of baseline methods in policy-gradients
presentation |
Dr. Pingali |
📊 Slides |
| May 16th 2025 |
Measure once, optimize twice: trust regions and step-size restrictions in policy gradient methods
presentation |
William Ruys |
📊 Slides |