Jianyuan Zhong

Reasoning Scaffolding: Distilling the Flow of Thought from LLMs

Mathesis: Towards Formal Theorem Proving from Natural Languages

Solve-Detect-Verify: Inference-Time Scaling with Flexible Generative Verifier

Making Slow Thinking Faster: Compressing LLM Chain-of-Thought via Step Entropy

Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding

DeepGate4: Efficient and Effective Representation Learning for Circuit Design at Scale

Beyond Trend and Periodicity: Guide Time Series Forecasting with Textual Cues

DeepCircuitX: Repository-Level RTL Dataset for Code Understanding, Generation, and Multimodal Analysis