← Search

Liming Dong

2 accepted papers

2025

Flow Matching Based Sequential Recommender Model

IJCAI 2025

Generative models, particularly diffusion model, have emerged as powerful tools for sequential recommendation. However, accurately modeling user preferences remains challenging due to the noise perturbations inherent in the forward and reverse processes of diffusion-based methods. Towards this end,

2025

Mitigating Language Confusion through Inference-time Intervention

COLING 2025main

Although large language models (LLMs) trained on extensive multilingual corpora exhibit impressive language transfer, they often fail to respond in the user’s desired language due to corpus imbalances, an embarrassingly simple problem known as the language confusion. However, existing solutions like…