Junchen Fu

A large-scale reproducibility study to systematically investigate the impact of semantic ID design on generative recommendation under a unified experimental framework provides a controlled and reproducible understanding of semantic ID design and offers practical insights for future generative recommender systems.

Adaptive inference can dramatically enhance recommendation accuracy for diverse user profiles, outperforming traditional one-pass models.

Reranking tools based on risk exposure can drastically improve safety in LLM agent interactions without sacrificing utility.

Assistant personality significantly influences user trust and interaction quality, with preferences varying dramatically across different information-seeking tasks.

Steering personality in LLMs is not just about traits; it's a complex interplay of cognitive processes that reveals surprising geometric relationships in activation space.

RecRec reveals that decoupling reasoning from prediction can significantly enhance sequential recommendation performance, breaking free from the constraints of fixed-dimensional states.

Smaller multimodal emotion models can outperform their larger counterparts, achieving state-of-the-art results with significantly improved efficiency.

Stream-aware adaptation can significantly enhance the performance of large multimodal models in sequential recommendation, overcoming traditional limitations of layer degradation.

Massive multimodal models like Qwen and CLIP excel at information retrieval, but their sheer size makes them impractical – this workshop tackles the efficiency gap.