Picture for Xiangang Li

Xiangang Li

Leveraging Reasoning Model Answers to Enhance Non-Reasoning Model Capability

Add code
Apr 13, 2025
Viaarxiv icon

How Difficulty-Aware Staged Reinforcement Learning Enhances LLMs' Reasoning Capabilities: A Preliminary Experimental Study

Add code
Apr 01, 2025
Viaarxiv icon

Memorizing is Not Enough: Deep Knowledge Injection Through Reasoning

Add code
Apr 01, 2025
Viaarxiv icon

Think Twice: Enhancing LLM Reasoning by Scaling Multi-round Test-time Thinking

Add code
Mar 25, 2025
Viaarxiv icon

1.4 Million Open-Source Distilled Reasoning Dataset to Empower Large Language Model Training

Add code
Mar 25, 2025
Viaarxiv icon

Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data

Add code
Dec 03, 2024
Figure 1 for Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
Figure 2 for Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
Figure 3 for Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
Figure 4 for Advancing Speech Language Models by Scaling Supervised Fine-Tuning with Over 60,000 Hours of Synthetic Speech Dialogue Data
Viaarxiv icon

OpenChat: Advancing Open-source Language Models with Mixed-Quality Data

Add code
Sep 20, 2023
Figure 1 for OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Figure 2 for OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Figure 3 for OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Figure 4 for OpenChat: Advancing Open-source Language Models with Mixed-Quality Data
Viaarxiv icon

CornerFormer: Boosting Corner Representation for Fine-Grained Structured Reconstruction

Add code
Apr 22, 2023
Viaarxiv icon

A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model

Add code
Apr 18, 2023
Figure 1 for A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model
Figure 2 for A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model
Figure 3 for A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model
Figure 4 for A Comparative Study between Full-Parameter and LoRA-based Fine-Tuning on Chinese Instruction Data for Instruction Following Large Language Model
Viaarxiv icon

Towards Better Instruction Following Language Models for Chinese: Investigating the Impact of Training Data and Evaluation

Add code
Apr 16, 2023
Viaarxiv icon