Author

Xinrui He

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#machine learning Preprint Sep 2026

Harnessing Image Question Dependence for Better VLM Test-time Reinforcement Learning

The proposed TTIQ, a test-time reinforcement learning framework that harnesses image-question dependence for better vlm adaptation, combines image and question dependence with calibrated confidence to construct a response-level reward that favors jointly grounded responses.

Xinrui He, Ting-Wei Li, Jun-Ting Wang et al. · 0 citations

Jul 2026

Understanding Semantic IDs: From Item Representation to Item Selection in Generative Recommendation

The results show that SIDs provide useful coarse item organization, but their fine boundaries should not alone determine which items remain available during generation, and propose Item-Supported Decoding (ISD), a lightweight inference-time method that allows a user-specific item ranking to support corresponding SID pr...

Jun-Ting Wang, Xinrui He, Yunzhe Li et al. · arXiv.org · 2 citations