Picture for Qinyuan Cheng

Qinyuan Cheng

Scaling of Search and Learning: A Roadmap to Reproduce o1 from Reinforcement Learning Perspective

Add code
Dec 18, 2024
Viaarxiv icon

Case2Code: Learning Inductive Reasoning with Synthetic Data

Add code
Jul 17, 2024
Figure 1 for Case2Code: Learning Inductive Reasoning with Synthetic Data
Figure 2 for Case2Code: Learning Inductive Reasoning with Synthetic Data
Figure 3 for Case2Code: Learning Inductive Reasoning with Synthetic Data
Figure 4 for Case2Code: Learning Inductive Reasoning with Synthetic Data
Viaarxiv icon

Scaling Laws for Fact Memorization of Large Language Models

Add code
Jun 22, 2024
Viaarxiv icon

Cross-Modality Safety Alignment

Add code
Jun 21, 2024
Viaarxiv icon

Unified Active Retrieval for Retrieval Augmented Generation

Add code
Jun 18, 2024
Viaarxiv icon

Aggregation of Reasoning: A Hierarchical Framework for Enhancing Answer Selection in Large Language Models

Add code
May 21, 2024
Viaarxiv icon

Dictionary Learning Improves Patch-Free Circuit Discovery in Mechanistic Interpretability: A Case Study on Othello-GPT

Add code
Feb 19, 2024
Viaarxiv icon

LLM can Achieve Self-Regulation via Hyperparameter Aware Generation

Add code
Feb 17, 2024
Viaarxiv icon

Can AI Assistants Know What They Don't Know?

Add code
Jan 28, 2024
Figure 1 for Can AI Assistants Know What They Don't Know?
Figure 2 for Can AI Assistants Know What They Don't Know?
Figure 3 for Can AI Assistants Know What They Don't Know?
Figure 4 for Can AI Assistants Know What They Don't Know?
Viaarxiv icon

Evaluating Hallucinations in Chinese Large Language Models

Add code
Oct 05, 2023
Viaarxiv icon