16 papers
HiGenTrans: Hierarchical LLM Knowledge Transfer for Generative Recommendation
Zhuohang Jiang, Yuxin Chen, Haohao Qu +13
Generative recommendation promises to simplify conventional multi-stage recommender systems by generating item Semantic IDs (SIDs) autoregressively. However, two obstacles limit it…
ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents
Haohao Qu, Yongcheng Jing, Chun Hin Chan +3
Recent Recommendation Agents (RecAgents) offer a promising alternative by shifting recommendation to an active, user-side paradigm, where generative agents autonomously perceive ex…
MAGIC: Marginal-Guided Compression with Optimal Transport for Efficient Visual Document Retrieval
Xu Yuan, Hua Liu, Wenqi Fan +1
Recent visual document retrieval (VDR) systems such as ColPali use multi-vector page embeddings, in which patch-level vectors enable fine-grained evidence matching but incur substa…
AI Smart Glasses for Wearable Intelligence: From Egocentric Sensing to Agentic Personalization
Xu Yuan, Yi Wang, Zhuohang Jiang +8
Recent advances in artificial intelligence (AI) are reshaping smart glasses from egocentric capture and display devices into platforms for wearable intelligence. Smart glasses incr…
Unlocking Multimodal Protein Language Models at Inference Time
Yi Zhou, Qipeng Wang, Yunqing Liu +3
Multimodal protein language models (pLMs) learn joint protein sequence-structure distributions, and their generation performance should also depend critically on inference-time sam…
FashionKG-RAG: Knowledge Graph-Enhanced Retrieval-Augmented Generation for Fashion Question Answering
Yujuan Ding, Linyin Luo, Shijie Wang +5
Fashion is a knowledge-intensive domain in which effective decision-making depends on integrating multiple types of knowledge. Although Large Language Models (LLMs) have transforme…
A/B Agent: A Self-Evolving Agent for Strategy Iteration in Industrial A/B Testing
Zhuohang Jiang, Yuxin Chen, Yongsen Pan +9
Industrial recommendation strategy iteration heavily relies on large-scale A/B experimentation. Traditional tuning requires experts to repeatedly design strategies, configure exper…
Diffusion Language Model for Recommendation
Chengyi Liu, Yongqi Zhou, Junwei Pan +8
Large language model (LLM)-empowered recommender systems have emerged as a promising paradigm for generative recommendation, leveraging their strong semantic reasoning and generati…
Atomic Intent Reasoning: Bringing LLM Semantics to Industrial Cross-Domain Recommendations
Zhuohang Jiang, Yuxin Chen, Shijie Wang +6
Cross-domain recommendation is a core problem in content-to-e-commerce platforms. Its objective is to leverage user interactions with content to infer potential purchasing intent o…
Inference Cost Attacks for Retrieval-Augmented Large Language Models
Chengliang Liu, Liangbo Ning, Yujuan Ding +1
Retrieval-Augmented Generation (RAG)-enhanced LLM systems, while powerful, introduce substantial inference costs due to the inclusion of an extra multi-stage pipeline that dynamica…
Mixture-of-Experts Knowledge Graph Retrieval-Augmented Generation for Multi-Agent LLM-based Recommendation
Shijie Wang, Chengyi Liu, Yujuan Ding +4
Large language models (LLMs) have recently been adopted for recommendations due to their ability to understand user intent and item semantics. However, LLM-based recommender system…
PriHA: A RAG-Enhanced LLM Framework for Primary Healthcare Assistant in Hong Kong
Richard Wai Cheung Chan, Shanru Lin, Ya-nan Ma +3
To address the unsustainable rise in public health expenditures, the Hong Kong SAR Government is shifting its strategic focus to primary healthcare and encouraging citizens to use…
Beyond Description: A Multimodal Agent Framework for Insightful Chart Summarization
Yuhang Bai, Yujuan Ding, Shanru Lin +1
Chart summarization is crucial for enhancing data accessibility and the efficient consumption of information. However, existing methods, including those with Multimodal Large Langu…
SUPERGLASSES: Benchmarking Vision Language Models as Intelligent Agents for AI Smart Glasses
Zhuohang Jiang, Xu Yuan, Haohao Qu +4
The rapid advancement of AI-powered smart glasses-one of the hottest wearable devices-has unlocked new frontiers for multimodal interaction, with Visual Question Answering (VQA) ov…
HD-Prot: A Protein Language Model for Joint Sequence-Structure Modeling with Continuous Structure Tokens
Yi Zhou, Haohao Qu, Yunqing Liu +3
Proteins inherently possess a consistent sequence-structure duality. The abundance of protein sequence data, which can be readily represented as discrete tokens, has driven fruitfu…
Diffusion Generative Recommendation with Continuous Tokens
Haohao Qu, Shanru Lin, Yujuan Ding +2
Recent advances in generative artificial intelligence, particularly large language models (LLMs), have opened new opportunities for enhancing recommender systems (RecSys). Most exi…