Deyang Kong

Peking University, IQuest Research

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Eval Frameworks & Benchmarks (1)Reasoning & Chain-of-Thought (1)RLHF & Preference Learning (1)

Frequent co-authors

Zhaoyi Li (1)Zhaoyi Li (1)Deyang Kong (1)Yuan Wei (1)

Papers (1)

Aug 17, 2026

1w ago·also Affiliation:, IQuest Research, PKU, ZJU

Every Coin Has Two Sides: On the Dual Nature of Generalization in On-Policy Distillation of Large Language Models

OPD transfers reasoning skills rather than answers, revealing a complex interplay between teacher-student origins that can either enhance or hinder model capabilities.

Zhaoyi Li, Zhaoyi Li, Deyang Kong +27

Eval Frameworks & Benchmarks Reasoning & Chain-of-Thought RLHF & Preference Learning

Search

Deyang Kong

Publication activitypapers/week, last 8 weeks

Research focus

Frequent co-authors

Papers (1)