People › Fengji Zhang
About
Fengji Zhang is a PhD Student in the Department of Computer Science, City University of Hong Kong.
Research Interests
Publications (13)
- To Answer or to Abstain: Mitigating Search-Agent Hallucinations via Abstention-Aware Reinforcement Learning.
- R2ComSync: improving code-comment synchronization with in-context learning and reranking.
- LaViT: Aligning Latent Visual Thoughts for Multi-modal Reasoning.
- HumanEval-V: Systematic Evaluation of Visual Reasoning in Large Multimodal Models for Code Generation
- Towards Engineering Multi-Agent LLMs: A Protocol-Driven Approach.
- NegCPARBP: Enhancing Privacy Protection for Cross-Project Aging-Related Bug Prediction Based on Negative Database.
- Exploring continual learning in code intelligence with domain-wise distilled prompts.
- A2Search: Ambiguity-Aware Question Answering with Reinforcement Learning.
- HumanEval-V: Evaluating Visual Understanding and Reasoning Abilities of Large Multimodal Models Through Coding Tasks.
- Data preparation for Deep Learning based Code Smell Detection: A systematic literature review.
- RepoCoder: Repository-Level Code Completion Through Iterative Retrieval and Generation.
- Diverse title generation for Stack Overflow posts with multiple-sampling-enhanced transformer.
- Improving Stack Overflow question title generation with copying enhanced CodeBERT model and bi-modal information.