Chengbing Wang — accepted AI-conference papers

2026

Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form Generation

Chengbing Wang, Yang Zhang, Wenjie Wang, Xiaoyan Zhao, Fuli Feng, Xiangnan He +1

ICLR 2026poster

Preference alignment has enabled large language models (LLMs) to better reflect human expectations, but current methods mostly optimize for population-level preferences, overlooking individual users. Personalization is essential, yet early approaches—such as prompt customization or fine-tuning—strug…

Cited by 0 Source ↗Scholar ↗

2025

Decoding in Latent Spaces for Efficient Inference in LLM-based Recommendation

Chengbing Wang, Yang Zhang, Zhicheng Wang, Tianhao Shi, Keqin Bao, Fuli Feng +1

EMNLP 2025

Fine-tuning large language models (LLMs) for recommendation in a generative manner has delivered promising results, but encounters significant inference overhead due to autoregressive decoding in the language space. This work explores bypassing language-space decoding by directly matching candidate

Cited by 0 Source ↗PDF ↗Scholar ↗