影响力指数

58.68/100

前 5.1%

全站排名 #3,300

发表论文11 篇

平均评分5.5

年均产出3.7 篇/年

Zijun Yao

PhD student@Department of Computer Science and Technology, Tsinghua University·中国·OpenReview

研究方向

Mechanistic Interpretability · Pre-trained Language Models · Dependency Parsing · Information Extraction

5.5

On Predictability of Reinforcement Learning Dynamics for Large Language Models

ICLR 2026Poster

4.5

MSearcher: Self-Reflective Search Agent Empowered by Monte Carlo Tree Search Based Data Synthesis

ICLR 2026Withdrawn

二作

2.5

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

NeurIPS 2025Poster

三作

5.5

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

ICLR 2025Rejected

一作

4.9

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

ICML 2025Poster

4.7

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

ICLR 2025Rejected

三作

4.0

Aligning Teacher with Student Preferences for Tailored Instruction Tuning Dataset Generation

合作者 (20)

Zijun Yao

On Predictability of Reinforcement Learning Dynamics for Large Language Models

MSearcher: Self-Reflective Search Agent Empowered by Monte Carlo Tree Search Based Data Synthesis

StockBench:Can Llm Agents Trade Stocks Profitably In Real-world Markets?

RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style

How do Transformers Learn Implicit Reasoning?

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

SeaKR: Self-aware Knowledge Retrieval for Adaptive Retrieval Augmented Generation

T1: Advancing Language Model Reasoning through Reinforcement Learning and Inference Scaling

Towards Understanding Safety Alignment: A Mechanistic Perspective from Safety Neurons

Aligning Teacher with Student Preferences for Tailored Instruction Tuning Dataset Generation