7 papers
EGRA:Toward Enhanced Behavior Graphs and Representation Alignment for Multimodal Recommendation
Xiaoxiong Zhang, Xin Zhou, Zhiwei Zeng +2
MultiModal Recommendation (MMR) systems have emerged as a promising solution for improving recommendation quality by leveraging rich item-side modality information, prompting a sur…
Search-Time Contamination in Deep Research Agents: Measuring Performance Inflation in Public Benchmark Evaluation
Yongjie Wang, Xinyue Zhang, Kunhong Yao +4
Public benchmarks enable fair and reproducible evaluation of LLM reasoning, but they become fragile for deep research agents that actively search the web during inference. Such age…
From Entity-Centric to Goal-Oriented Graphs: Enhancing LLM Knowledge Retrieval in Minecraft
Jonathan Leung, Yongjie Wang, Zhiqi Shen
Large Language Models (LLMs) demonstrate impressive general capabilities but often struggle with step-by-step procedural reasoning, a critical challenge in complex interactive envi…
CM: Calibrating Multimodal Recommendation
Xin Zhou, Yongjie Wang, Zhiqi Shen
Alignment and uniformity are fundamental principles within the domain of contrastive learning. In recommender systems, prior work has established that optimizing the Bayesian Perso…
Response Uncertainty and Probe Modeling: Two Sides of the Same Coin in LLM Interpretability?
Yongjie Wang, Yibo Wang, Xin Zhou +1
Probing techniques have shown promise in revealing how LLMs encode human-interpretable concepts, particularly when applied to curated datasets. However, the factors governing a dat…
RoleRAG: Enhancing LLM Role-Playing via Graph Guided Retrieval
Yongjie Wang, Jonathan Leung, Zhiqi Shen
Large Language Models (LLMs) have shown promise in character imitation, enabling immersive and engaging conversations. However, they often generate content that is irrelevant or in…