Edith C. H. Ngai

The University of Hong Kong

Papers on Lattice

Total citations

Topics

h-index

Publication activitypapers/week, last 8 weeks

Research focus

Multimodal Models (2)Recommendation & Information Retrieval (2)Training Efficiency & Optimization (1)Eval Frameworks & Benchmarks (1)

Frequent co-authors

Jinfeng Xu (3)Zheyu Chen (2)Shuo Yang (2)Jinze Li (1)

Papers (3)

Apr 16, 2026

2w ago·also CMU ML, BIT, PKU

Well Begun is Half Done: Training-Free and Model-Agnostic Semantically Guaranteed User Representation Initialization for Multimodal Recommendation

Dramatically improve multimodal recommendation accuracy without any training by initializing user embeddings with item modality features and user cluster information.

Jinfeng Xu, Zheyu Chen, Shuo Yang +6

Multimodal Models Recommendation & Information Retrieval Training Efficiency & Optimization

Apr 9, 2026

Wenhao Yuan +83w ago·also HKU, The Central Hospital of Wuhan

Verify Before You Commit: Towards Faithful Reasoning in LLM Agents via Self-Auditing

LLM agents can be made more reliable by structurally verifying their internal reasoning, rather than relying on consensus which conflates agreement with faithfulness.

Wenhao Yuan, Chenchen Lin, Chenchen Lin +6

Eval Frameworks & Benchmarks Reasoning & Chain-of-Thought Tool Use & Agents

Mar 4, 2026

Mar 4, 2026·also BIT, HIT, PKU

CAMMSR: Category-Guided Attentive Mixture of Experts for Multimodal Sequential Recommendation

Forget static fusion: CAMMSR adaptively weights multimodal signals in sequential recommendations based on item category and user preferences, unlocking synergistic effects between modalities.