← Search

Dongming Jin

2 accepted papers

2026

Weights to Code: Extracting Interpretable Algorithms from the Discrete Transformer

ICML 2026poster

Algorithm extraction aims to synthesize executable programs directly from models trained on algorithmic tasks, enabling *de novo* algorithm discovery without relying on human-written code. However, applying this paradigm to Transformer is hindered by representation entanglement (e.g., superposition)…

Cited by 0SourceScholar
2025

Finite State Automata Inside Transformers with Chain-of-Thought: A Mechanistic Study on State Tracking

ACL 2025long

Chain-of-thought (CoT) significantly enhances the performance of large language models (LLMs) across a wide range of tasks, and prior research shows that CoT can theoretically increase expressiveness. However, there is limited mechanistic understanding of the algorithms that Transformer+CoT can lear…