Weak-to-Strong Generalization Even in Random Feature Networks, Provably

Machine Unlearning Today: Are we there yet?

Understanding the Underlying Computation of Large Language Models and Large-brained Mammals

Enhancing Evaluation Coverage and Validation with Language Models

Vanishing Gradients in Reinforcement Finetuning of Language Models and Interpretability Insights for Localized Fine-tuning on LLM Representations

PLI Lunch Series: Edoardo Debenedetti and Javier Rando

Understanding Complex Processing in Temporal Models - From Implicit Biases to Mechanistic Interpretability

Model-aware dataset selection with data models

Spectral State Space Models

Towards Effective NLP Systems: Cultural Norms and Reasoning Enhancement

Interpreting Modeling Training

Building Architectures Towards High Throughput Data Processing Systems

Algorithmic LLM alignment

Reinforcement Learning from Human Feedback: Algorithms & Applications

Whispers in the Weight: Unraveling the Mysteries of LLM Compression

Making LLMs Right

Physics of Language Models: Knowledge Storage, Extraction, and Manipulation

Beyond Test Accuracies for Studying Deep Neural Networks