← Search

Lixuan Guo

2 accepted papers

2026

CSRv2: Unlocking Ultra-Sparse Embeddings

ICLR 2026poster

In the era of large foundation models, the quality of embeddings has become a central determinant of downstream task performance and overall system capability. Yet widely used dense embeddings are often extremely high-dimensional (e.g., 4096), incurring substantial costs in storage, memory, and inf…

Cited by 0SourcecodeScholar
2026

No More K-means: Single-Stage Sparse Coding for Efficient Multi-Vector Retrieval

ICML 2026poster

Multi-vector retrieval (MVR) models, exemplified by ColBERT, have established new benchmarks in retrieval accuracy by preserving fine-grained token-level interactions. However, this granularity imposes prohibitive storage and retrieval efficiency bottlenecks: to manage the immense memory footprint a…

Cited by 0SourceScholar