- Topological Signatures of Deception: Detecting Unfaithful Reasoning via Sentence-Level Causal Graphs
- A Mechanistic Switch for Heuristic vs. Algorithmic Processing in Small Language Models
- The Non-linear Privilege: How Feedforward Networks enable neuron Interpretability
- Scaling Laws for LLMs
- Sliding Window Attention Training
- What is Knowledge Graph and GraphRAG