Shijin Wang

~Shijin_Wang1

论文总数

8.0

年均投稿

6.4

平均评分

接收情况13/16

会议分布

NeurIPS

ICML

ICLR

发表论文 (16 篇)

202511 篇

6.8

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation

NeurIPS 2025Poster

6.3

CursorCore: Assist Programming through Aligning Anything

ICML 2025Poster

6.4

Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning

NeurIPS 2025Poster

6.0

CursorCore: Assist Programming through Aligning Anything

ICLR 2025Rejected

6.0

Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study

ICLR 2025Poster

6.3

Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving

ICML 2025Poster

7.2

am-ELO: A Stable Framework for Arena-based LLM Evaluation

ICML 2025Spotlight

4.3

CogMath: Evaluating LLMs' Authentic Mathematical Ability from a Cognitive Perspective

ICLR 2025withdrawn

8.2

FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training

NeurIPS 2025Poster

6.4

A Closed-Form Solution for Fast and Reliable Adaptive Testing

NeurIPS 2025Poster

6.8

CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective

ICML 2025Poster

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

NeurIPS 2024Poster

6.7

Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation

NeurIPS 2024Poster

4.0

Efficiently Measuring the Cognitive Ability of LLMs: An Adaptive Testing Perspective

合作者 (20)

Shijin Wang

发表论文 (16 篇)

202511 篇

How Does Sequence Modeling Architecture Influence Base Capabilities of Pre-trained Language Models? Exploring Key Architecture Design Principles to Avoid Base Capabilities Degradation

CursorCore: Assist Programming through Aligning Anything

Investigating and Mitigating Catastrophic Forgetting in Medical Knowledge Injection through Internal Knowledge Augmentation Learning

CursorCore: Assist Programming through Aligning Anything

Evaluating Large Language Models through Role-Guide and Self-Reflection: A Comparative Study

Evaluating LLMs Across Multi-Cognitive Levels: From Medical Knowledge Mastery to Scenario-Based Problem Solving

am-ELO: A Stable Framework for Arena-based LLM Evaluation

CogMath: Evaluating LLMs' Authentic Mathematical Ability from a Cognitive Perspective

FACT: Mitigating Inconsistent Hallucinations in LLMs via Fact-Driven Alternating Code-Text Training

A Closed-Form Solution for Fast and Reliable Adaptive Testing

CogMath: Assessing LLMs' Authentic Mathematical Ability from a Human Cognitive Perspective

20245 篇

SocraticLM: Exploring Socratic Personalized Teaching with Large Language Models

Computerized Adaptive Testing via Collaborative Ranking

JiuZhang3.0: Efficiently Improving Mathematical Reasoning by Training Small Data Synthesis Models

Towards Accurate and Fair Cognitive Diagnosis via Monotonic Data Augmentation

Efficiently Measuring the Cognitive Ability of LLMs: An Adaptive Testing Perspective