Chengkai Huang

Macquarie University

Papers on Lattice

Total citations

Topics

Publication activitypapers/week, last 8 weeks

Research focus

Natural Language Processing (3)Recommendation & Information Retrieval (3)Multimodal Models (2)Reasoning & Chain-of-Thought (1)

Frequent co-authors

Zihan Wang (3)Lina Yao (3)Xihang Wang (2)Cao Liu (2)

Papers (3)

Apr 30, 2026

1d ago·also Macquarie, Meituan, UNSW

Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG

Stop drowning your MLLMs in irrelevant context: FES-RAG shows that carefully selecting multimodal fragments boosts factual accuracy by up to 27% and slashes context length.

Xihang Wang, Zihan Wang, Chengkai Huang +4

Multimodal Models Natural Language Processing Recommendation & Information Retrieval

Apr 29, 2026

Independent Researcher2d ago·also Macquarie, Meituan, UNSW

Factorized Latent Reasoning for LLM-based Recommendation

LLMs can model user preferences more effectively by disentangling intent into multiple latent factors, leading to improved recommendation accuracy and interpretability.

Tianqi Gao, Chengkai Huang, Zihan Wang +3

Natural Language Processing Reasoning & Chain-of-Thought Recommendation & Information Retrieval

Apr 27, 2026

4d ago·also Macquarie, Meituan, PKU, UNSW

MEG-RAG: Quantifying Multi-modal Evidence Grounding for Evidence Selection in RAG

Semantic grounding, not token probability, is the key to better multimodal RAG.

Xihang Wang, Zihan Wang, Chengkai Huang +5