Author

Qi Qi

h-index 1 View on Semantic Scholar

We have 2 of 5 papers

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.

#artificial intelligence Jun 2026

Geometry-Aware Online Scheduling for LLM Serving: From Theoretical Bound to System Practice

This work establishes a theoretically sound and empirically proven approach for resolving memory-constrained scheduling in modern LLM deployments by introducing the Smallest Volume First (SVF) algorithm and its highly efficient variant, 1-bit SVF.

Lingjing Kong, Qi Qi, Yin-Yu Ye et al. · arXiv.org · 3 citations

Preprint Aug 2026

TransRetrieval: Scaling Up Transformer-Based Retrieval for Industrial Recommendation

TransRetrieval is presented, a Transformer-based retrieval framework that scales with both computational budget and cross-domain data and introduces weighted average aggregation, which restores the homogeneous-token assumption Transformers rely on, and target token compression that cuts per-candidate FLOPs while preser...

Zhi-Fei Zheng, Yun-Fei Liu, Bin Liu et al. · 0 citations