PaperHub

Junxian He

~Junxian_He1

23
论文总数
11.5
年均投稿
5.7
平均评分
接收情况16/23
会议分布
ICLR
11
ICML
5
COLM
4
NeurIPS
3

发表论文 (23 篇)

202515 篇

6.5
4

Non-myopic Generation of Language Models for Reasoning and Planning

ICLR 2025Poster
6.6
4

CodeIO: Condensing Reasoning Patterns via Code Input-Output Prediction

ICML 2025Oral
6.1
4

Diving into Self-Evolving Training for Multimodal Reasoning

ICML 2025Poster
5.3
4

Diving into Self-Evolve Training for Multimodal Reasoning

ICLR 2025Rejected
6.0
3

B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners

ICLR 2025Poster
5.8
4

FacTool: Factuality Detection in Generative AI -- A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios

COLM 2025Poster
5.8
4

Breaking the Data Barrier -- Building GUI Agents Through Task Generalization

COLM 2025Poster
7.3
4

SimpleRL-Zoo: Investigating and Taming Zero Reinforcement Learning for Open Base Models in the Wild

COLM 2025Poster
4.5
4

From Scaling Law to Sub-Scaling Law: Understanding the Diminishing Returns of Larger Models

ICLR 2025withdrawn
4.0
4

AdaptVis: Spatial Understanding in Vision-Language Models Requires Adaptive Attention

ICLR 2025withdrawn
4.9
4

Predictive Data Selection: The Data That Predicts Is the Data That Teaches

ICML 2025Poster
6.1
4

Why Is Spatial Reasoning Hard for VLMs? An Attention Mechanism Perspective on Focus Areas

ICML 2025Poster
4.3
4

Math for AI: On the Generalization of Learning Mathematical Problem Solving

ICLR 2025Rejected
5.5
3

Bring Reason to Vision: Understanding Perception and Reasoning through Model Merging

ICML 2025Poster
6.8
4

SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond

NeurIPS 2025Poster

20248 篇

6.6
5

Compression Represents Intelligence Linearly

COLM 2024Poster
4.8
4

DART-Math: Difficulty-Aware Rejection Tuning for Mathematical Problem-Solving

NeurIPS 2024Poster
6.3
3

What Makes Good Data for Alignment? A Comprehensive Study of Automatic Data Selection in Instruction Tuning

ICLR 2024Poster
6.0
4

Can LLMs Express Their Uncertainty? An Empirical Evaluation of Confidence Elicitation in LLMs

ICLR 2024Poster
6.0
3

FacTool: Factuality Detection in Generative AI - A Tool Augmented Framework for Multi-Task and Multi-Domain Scenarios

ICLR 2024Rejected
4.7
3

SimTeG: A Frustratingly Simple Approach Improves Textual Graph Learning

ICLR 2024Rejected
7.2
5

Uncertainty of Thoughts: Uncertainty-Aware Planning Enhances Information Seeking in LLMs

NeurIPS 2024Poster
4.7
3

Prompt Optimization via Adversarial In-Context Learning

ICLR 2024Rejected
合作者 (20)