Haotian Lyu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Haotian Lyu has a total of 19 co-authors. Here are the top co-authors by number of shared publications:
Bingjie Huang
1 shared publicationChao Yao
1 shared publication- Chengrui Zhou
Fu Foundation School of Engineering and Applied Science, Columbia University, New York, USA
1 shared publication Dingzhou Wang
Pratt School of Engineer, Duke University
1 shared publication- Dingzhou Wang
Pratt School of Engineer, Duke University, Durham, USA
1 shared publication - Haowei Yang
Cullen College of Engineering, University of Houston, Houston, CA, USA
1 shared publication
Latest Publications
- Open Access
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Adapting to Changing User Preferences with Meta-Learned LLM Recommenders
Recommender systems must operate in dynamic environments where user preferences evolve rapidly across contexts, platforms, and temporal horizons. Conventional sequential recommenders struggle to adapt efficiently, often requiring extensive retraining or fine-tuning that incurs significant computational overhead. To overcome this issue, we suggest a meta-learned large language model recommender (Meta-LLMRec) that is aimed at quickly adapting to changing user behavior. Our model combines the concepts of meta-learning and token-level representations of language, allowing the recommender to learn transferable priors over heterogeneous tasks and dynamically learn more effectively with few gradient updates. In particular, we define the problem of preference prediction as a sequence-tosequence adaptation and optimize meta-initialized embeddings and Transformer encoders with a bilevel loss to reduce the generalization error on task distributions. Benchmark experiments of Meta-LLMRec against strong baselines, such as Amazon-Books and MovieLens-1M, show that it is more accurate and faster to adapt than baselines, by an average of 40% fewer gradient steps without compromising model stability. Ablation experiments also confirm that joint meta-learned priors, combined with tokenlevel semantics, perform significantly better in Cold-start scenarios, as well as in a change of temporal preference. These findings make Meta-LLMRec a scalable and effective paradigm in changing user preferences in realistic recommendation situations.
- 12 November 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessAdapting to Changing User Preferences with Meta-Learned LLM Recommenders
Recommender systems must operate in dynamic environments where user preferences evolve rapidly across contexts, platforms, and temporal horizons. Conventional sequential recommenders struggle to adapt efficiently, often requiring extensive retraining or fine-tuning that incurs significant computational overhead. To overcome this issue, we suggest a meta-learned large language model recommender (Meta-LLMRec) that is aimed at quickly adapting to changing user behavior. Our model combines the concepts of meta-learning and token-level representations of language, allowing the recommender to learn transferable priors over heterogeneous tasks and dynamically learn more effectively with few gradient updates. In particular, we define the problem of preference prediction as a sequence-tosequence adaptation and optimize meta-initialized embeddings and Transformer encoders with a bilevel loss to reduce the generalization error on task distributions. Benchmark experiments of Meta-LLMRec against strong baselines, such as Amazon-Books and MovieLens-1M, show that it is more accurate and faster to adapt than baselines, by an average of 40% fewer gradient steps without compromising model stability. Ablation experiments also confirm that joint meta-learned priors, combined with tokenlevel semantics, perform significantly better in Cold-start scenarios, as well as in a change of temporal preference. These findings make Meta-LLMRec a scalable and effective paradigm in changing user preferences in realistic recommendation situations.
- Open Access
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Self-Supervised User Embedding Alignment for Cross-Domain Recommendations via Multi-LLM Co-Training
Cross-domain recommendation is the central problem of personalized systems, especially in those cases where user prediction needs to be promoted across different kinds of content (e.g., music to books, or videos to articles). Typical collaborative filtering models cannot work well in this environment because user behavior representations are usually inconsistent in different domains and most existing neural models have a problem of overfitting on individual domains and lack generalization. This paper presents a new selfsupervised dual-LLM model of getting user embeddings to transfer across domains through multi-view representations. In particular, two domain-specificities LLMs are trained simultaneously, sharing layers of user embedding. Such embeddings are considered to be cross-modal semantic anchors, which are learned through a joint contrastive loss (where semantically similar user profiles in a domain are brought closer to each other) and a reconstruction loss (where intra-domain similarity should be maintained). This combined goal allows this model to map high-dimensional user embeddings in domain A and B into a common latent space so that in the target domains where user history may be sparse. It takes an advantage of both Masked Language Modelling (MLM), and next-item prediction tasks to retain modalityspecific learning in both LLMs, and also use contrastive learning enforcement of alignment using positive pairs sampled based on implicit behavioral cues. On cross-domain benchmarks, the experimental results indicate an improved top-k accuracy, embedding similarity (via CKA and t-SNE distance) and across transfer tasks compared to current image matching approaches CDAN, DGRec and CoNet.
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessSelf-Supervised User Embedding Alignment for Cross-Domain Recommendations via Multi-LLM Co-Training
Cross-domain recommendation is the central problem of personalized systems, especially in those cases where user prediction needs to be promoted across different kinds of content (e.g., music to books, or videos to articles). Typical collaborative filtering models cannot work well in this environment because user behavior representations are usually inconsistent in different domains and most existing neural models have a problem of overfitting on individual domains and lack generalization. This paper presents a new selfsupervised dual-LLM model of getting user embeddings to transfer across domains through multi-view representations. In particular, two domain-specificities LLMs are trained simultaneously, sharing layers of user embedding. Such embeddings are considered to be cross-modal semantic anchors, which are learned through a joint contrastive loss (where semantically similar user profiles in a domain are brought closer to each other) and a reconstruction loss (where intra-domain similarity should be maintained). This combined goal allows this model to map high-dimensional user embeddings in domain A and B into a common latent space so that in the target domains where user history may be sparse. It takes an advantage of both Masked Language Modelling (MLM), and next-item prediction tasks to retain modalityspecific learning in both LLMs, and also use contrastive learning enforcement of alignment using positive pairs sampled based on implicit behavioral cues. On cross-domain benchmarks, the experimental results indicate an improved top-k accuracy, embedding similarity (via CKA and t-SNE distance) and across transfer tasks compared to current image matching approaches CDAN, DGRec and CoNet.
- Open Access
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 997-1002
Research on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models
- 13 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 997-1002
Open AccessResearch on E-Commerce Long-Tail Product Recommendation Mechanism Based on Large-Scale Language Models
- Top Cited PapersOpen Access
- 6 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 610-615
LLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion
- 6 June 2025
- Published by Association for Computing Machinery (ACM)
- p. 610-615
Top Cited PapersOpen AccessLLM-Driven E-Commerce Marketing Content Optimization: Balancing Creativity and Conversion