These are the papers/articles/repos/videos that our journal club members have shared, which might be worth presenting in the future or we think are interesting. This page will be updated once a month.
- Solving olympiad geometry without human demonstrations shared by Hongsup
- Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training shared by Kshitij
- TOFU: A Task of Fictitious Unlearning for LLMs shared by Sarah
- Quantifying the impact of uninformative features on the performance of supervised classification and dimensionality reduction algorithms shared by Kshitij
- Fine-tuning Aligned Language Models Compromises Safety, Even When Users Do Not Intend To! shared by Hongsup
- A Mulching Proposal shared by Hongsup
- Evaluating and Mitigating Discrimination in Language Model Decisions shared by Kshitij
- Dive into Deep Learning: Coding Session #4 Attention Mechanism I (MLT Artificial Intelligence) shared by Kshitij
- Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks shared by Brian
- MiniLLM: Large Language Models on Consumer GPUs shared by Hongsup
- The TinyLlama project shared by Kshitij
- On the Opportunities and Risks of Foundation Models shared by Hongsup
- Challenges in Deploying Machine Learning: a Survey of Case Studies shared by Hongsup
- Machine Learning and the Future of Bayesian Computation shared by Brian