Chengkai Huang

Factorized Latent Reasoning for LLM-based Recommendation

Tianqi Gao, Chengkai Huang, Zihan Wang, Cao Liu et autres

Large language models (LLMs) have recently been adopted for recommendation by framing user preference modeling as a language generation problem. However, existing latent reasoning approaches typically represent user intent with a single latent vector, which struggles to capture the inherently multi-faceted nature …

au, cn (code pays fourni par la source)

Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG

Xihang Wang, Zihan Wang, Chengkai Huang, Cao Liu et autres

cn, au (code pays fourni par la source)

Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG

Xihang Wang, Zihan Wang, Chengkai Huang, Cao Liu et autres

Multimodal Retrieval-Augmented Generation (MRAG) is widely adopted for Multimodal Large Language Models (MLLMs) with external evidence to reduce hallucinations. Despite its success, most existing MRAG frameworks treat retrieved evidence as indivisible documents, implicitly assuming that all content within a document is equally …

cn, au (code pays fourni par la source)

Gaussian Mixture Flow Matching with Domain Alignment for Multi-Domain Sequential Recommendation

Xiaoxin Ye, Chengkai Huang, Hongtao Huang, Lina Yao

Users increasingly interact with content across multiple domains, resulting in sequential behaviors marked by frequent and complex transitions. While Cross-Domain Sequential Recommendation (CDSR) models two-domain interactions, Multi-Domain Sequential Recommendation (MDSR) introduces significantly more domain transitions, compounded by challenges such as domain heterogeneity …

au (code pays fourni par la source)

PruneRAG: Confidence-Guided Query Decomposition Trees for Efficient Retrieval-Augmented Generation

Shuguang Jiao, Xinyu Xiao, Yunfan Wei, Shuhan Qi et autres

Retrieval-augmented generation (RAG) has become a powerful framework for enhancing large language models in knowledge-intensive and reasoning tasks. However, as reasoning chains deepen or search trees expand, RAG systems often face two persistent failures: evidence forgetting, where retrieved knowledge is not effectively …

cn, au (code pays fourni par la source)

Learning to Retrieve Navigable Candidates for Efficient Vision-and-Language Navigation

Shutian Gu, Chengkai Huang, Ruoyu Wang, Lina Yao

Vision-and-Language Navigation (VLN) requires an agent to follow natural-language instructions and navigate through previously unseen environments. Recent approaches increasingly employ large language models (LLMs) as high-level navigators due to their flexibility and reasoning capability. However, prompt-based LLM navigation often suffers from inefficient …

Dual Conditional Diffusion for Sequential Recommendation

Hongtao Huang, Chengkai Huang, Tong Yu, Xiaojun Chang et autres

Recent advancements in diffusion models have shown promising results in sequential recommendation (SR). Existing approaches predominantly rely on implicit conditional diffusion models, which compress user behaviors into a single representation during the forward diffusion process. While effective to some extent, this oversimplification …

au, us, cn (code pays fourni par la source)

Fdioa/PruneRAG: PruneRAG Initial Release

Fdioa, Chengkai Huang

PruneRAG Initial Release

au (code pays fourni par la source)

Fdioa/PruneRAG: Add LICENSE

Fdioa, Chengkai Huang

No description provided.

au (code pays fourni par la source)

Fdioa/PruneRAG: Add LICENSE

Fdioa, Chengkai Huang

No description provided.

au (code pays fourni par la source)

Federated Large Language Models: Current Progress and Future Directions

Yuhang Yao, Jianyi Zhang, Junda Wu, Chengkai Huang et autres

SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual Scenes

Chuhan Wang, Xintong Li, J Zhang, Junda Wu et autres

Chuhan Wang, Xintong Li, Jennifer Yuntong Zhang, Junda Wu, Chengkai Huang, Lina Yao, Julian McAuley, Jingbo Shang. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2026.

us, ca, au (code pays fourni par la source)