Picture for Jinman Zhao

Jinman Zhao

University of Toronto

Multi-Preference Lambda-weighted Listwise DPO for Dynamic Preference Alignment

Add code
Jun 24, 2025
Viaarxiv icon

PreP-OCR: A Complete Pipeline for Document Image Restoration and Enhanced OCR Accuracy

Add code
May 28, 2025
Viaarxiv icon

UORA: Uniform Orthogonal Reinitialization Adaptation in Parameter-Efficient Fine-Tuning of Large Models

Add code
May 26, 2025
Viaarxiv icon

Sequence-level Large Language Model Training with Contrastive Preference Optimization

Add code
Feb 23, 2025
Figure 1 for Sequence-level Large Language Model Training with Contrastive Preference Optimization
Figure 2 for Sequence-level Large Language Model Training with Contrastive Preference Optimization
Figure 3 for Sequence-level Large Language Model Training with Contrastive Preference Optimization
Figure 4 for Sequence-level Large Language Model Training with Contrastive Preference Optimization
Viaarxiv icon

False Discovery Rate Control via Frequentist-assisted Horseshoe

Add code
Feb 08, 2025
Viaarxiv icon

Bias and Toxicity in Role-Play Reasoning

Add code
Sep 21, 2024
Figure 1 for Bias and Toxicity in Role-Play Reasoning
Figure 2 for Bias and Toxicity in Role-Play Reasoning
Figure 3 for Bias and Toxicity in Role-Play Reasoning
Figure 4 for Bias and Toxicity in Role-Play Reasoning
Viaarxiv icon

Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch

Add code
Sep 21, 2024
Figure 1 for Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
Figure 2 for Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
Figure 3 for Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
Figure 4 for Can Language Model Understand Word Semantics as A Chatbot? An Empirical Study of Language Model Internal External Mismatch
Viaarxiv icon

LongRecipe: Recipe for Efficient Long Context Generalization in Large Language Models

Add code
Sep 04, 2024
Viaarxiv icon

MMREC: LLM Based Multi-Modal Recommender System

Add code
Aug 08, 2024
Viaarxiv icon

Semantic Understanding and Data Imputation using Large Language Model to Accelerate Recommendation System

Add code
Jul 14, 2024
Viaarxiv icon