Research, Interpretability, Code
June 2026
From Brewing to Resolution: Tracing the Internal Lifecycle of Code Reasoning in LLMs
LLMs first brew the answer — it becomes linearly recoverable many layers before the model can decode it itself — then diverge into four resolution...
Read More
Research
March 2025
NeurIPS 2025 SE-Agent Case Study
A detailed analysis and case study of the SE-Agent performance at NeurIPS 2025, exploring multimodal learning and agentic workflows.
Read More
Opinion
Upcoming
Future Research Directions in Multimodal Agents
Coming soon... I'll be sharing some insights on the next generation of
multimodal agents and their applications.
Stay tuned