Zeju Li

Reasoning Scaffolding: Distilling the Flow of Thought from LLMs

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

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

DeepRTL: Bridging Verilog Understanding and Generation with a Unified Representation Model

Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding

Spatial 3D-LLM: Progressive Spatial Awareness for Advanced 3D Vision-Language Understanding

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