Di Niu

Di Niu has 2 papers in our library, in 2026, most of them on Language models & pretraining.

2 papers in our library · 2026

No OpenAlex profile matched yet.

The profile is the library's match of the name; two people with one name are not always told apart.

Fields, topics and concepts

Of its works in our library, with the number of works on each.

The most cited first (OpenAlex and our library).

Guided by Gut: Efficient Test-Time Scaling with Reinforced Intrinsic Confidence (2026 · 4 citations)
Test-time scaling helps LLMs reason better, but common approaches are costly. Long chain-of-thought, Best-of-N sampling and search scored by a separate Process Reward Model (PRM) all demand a lot of compute and memory. The authors propose Guided by Gut (GG), which removes external verifiers entirely. GG runs a light…
PerfCoder: Large Language Models for Interpretable Code Performance Optimization (2026)
LLMs usually write functionally correct code, but they are weak at making programs run faster. The authors attribute this mainly to missing supervision that explains which optimization helps and why , not only to a lack of data. They present PerfCoder, a family of fine-tuned LLMs for C++ performance optimization.

Where their works here were published, the most works first, with the editions of those that have a page.

Papers of our library cite their works 4 times (of the 149,439 papers whose bibliographies we read); 1 citing paper with a page here →.

Updated 2 November 2026