Picture for Chenghua Lin

Chenghua Lin

YuE: Scaling Open Foundation Models for Long-Form Music Generation

Add code
Mar 11, 2025
Viaarxiv icon

Silent Hazards of Token Reduction in Vision-Language Models: The Hidden Impact on Consistency

Add code
Mar 11, 2025
Viaarxiv icon

LongEval: A Comprehensive Analysis of Long-Text Generation Through a Plan-based Paradigm

Add code
Feb 26, 2025
Viaarxiv icon

Transforming Science with Large Language Models: A Survey on AI-assisted Scientific Discovery, Experimentation, Content Generation, and Evaluation

Add code
Feb 07, 2025
Viaarxiv icon

LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models

Add code
Jan 23, 2025
Figure 1 for LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
Figure 2 for LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
Figure 3 for LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
Figure 4 for LVPruning: An Effective yet Simple Language-Guided Vision Token Pruning Approach for Multi-modal Large Language Models
Viaarxiv icon

Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond

Add code
Jan 09, 2025
Figure 1 for Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
Figure 2 for Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
Figure 3 for Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
Figure 4 for Leveraging Large Language Models for Zero-shot Lay Summarisation in Biomedicine and Beyond
Viaarxiv icon

Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks

Add code
Jan 08, 2025
Figure 1 for Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
Figure 2 for Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
Figure 3 for Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
Figure 4 for Tougher Text, Smarter Models: Raising the Bar for Adversarial Defence Benchmarks
Viaarxiv icon

Disentangling Preference Representation and Text Generation for Efficient Individual Preference Alignment

Add code
Dec 30, 2024
Viaarxiv icon

Observing Micromotives and Macrobehavior of Large Language Models

Add code
Dec 10, 2024
Viaarxiv icon

Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence

Add code
Dec 01, 2024
Figure 1 for Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence
Figure 2 for Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence
Figure 3 for Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence
Figure 4 for Lightweight Contenders: Navigating Semi-Supervised Text Mining through Peer Collaboration and Self Transcendence
Viaarxiv icon