Recap / Quiz | | 1030 - 1100: Break A | Break | Break | Break | Break | Break | | | Break | Break | Break | Break | Break | | 1100 - 1230: Session B | Intro to ML | Intro to Transformers | Responsible AI Aspects - Gokul S. Krishnan | Abhijnan Chakraborty | Privacy / Fairness - Arun | | | RLHF: Stephen Casper, MIT | panel discussion: Tanuja, Sameep, Prof. Ravi, Amlan | Unlearning - Shashwat Goel | Evaluation & Deployability - Gokul | Anand Raghunathan & Gopalakrishnan Srinivasan | | 1230 - 1400: Lunch | Lunch | Lunch | Lunch | Lunch | Lunch | | | Lunch | Lunch | Lunch | Lunch | Lunch | | 1400 - 1530: Session C | ML in Practice | Using LLMs | Fine-tuning LMs & Guardrails - Satya Swaroop Gudipudi | Interpretability Using dictionary learning methods - Taufeque | Recap / Quiz | | | LLM Consistency - Vamshi Krishna | panel discussion: Tanuja, Sameep, Prof. Ravi, Amlan | RepE - Shashwat Goel | Gender bias in Vision-Language - Prachi Jain | Project presentation | | 1530 - 1600: Break B | Break | Break | Break | Break | Break | | | Break | Break | Break | Break | Break | | 1600 - 1730: Session D | Deep Learning in Practice Training Neural Networks | Bias in LLMs - Priyanshul Govil | Removing Safety Guardrails - Taufeque | Projects Discussion | Projects Discussion | | | Adversarial Attacks - Vamshi Krishna | Project Discussions | Project Discussion | Gender bias in Vision-Language - Prachi Jain | Project Presentation | | 1730 - 2000: Break + Dinner | Dinner / Break | Dinner / Break | Dinner / Break | Dinner / Break | Dinner / Break | | | Dinner / Break | Dinner / Break | Dinner / Break | Dinner / Break | Dinner / Break | | 2000 - 2130: Session E | Team Formation | Paper reading | Projects Discussion | Prof PK | Usman Anwar, Oxford Unviersity | | | Prof. Ramayya Krishan, CMU; talk + interactions | Megha, Palantir | Human Allied AI - Sriraam Nagarajan | David Kraueger, Oxford | |