On Generalizability of 'Competition of Mechanisms' 🍎This project reproduces and extends the findings of “Competition of Mechanisms: Tracing How Language Models Handle Facts and Counterfactuals” [1]. We validate the original study’s results on GPT-2 ... Jun 25, 2025 Interpretability
Re-DreamerV3 🤖Abstract We enhance DreamerV3 by integrating Transformer-based SSMs and a novel stochastic replay prioritization, combining TD-error based PER with novelty-driven CR. The modifications improved sa... May 31, 2025 RL
