Author

Xue-Guang Ma

h-index 3 View on Semantic Scholar

We have 2 of 8 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.

Preprint Aug 2026

Tevatron-Elastic: A Unified Abstraction for Training Elastic Retrievers and Rerankers

This work presents a unified abstraction of Matryoshka embeddings, early exit, 2D~Matryoshka, and layerwise token compression that enables Matryoshka~LTC (MLTC), which jointly trains several token-compression ratios in one retriever checkpoint.

Yu Wang, Shengyao Zhuang, Xue-Guang Ma et al. · 1 citation

Preprint Aug 2026

Tevatron Meets Megatron: Expert-Parallel LLM Reranker Training on an Academic Budget

Tevatron 3.0 is presented, which integrates a Megatron-Core training backend into Tevatron while preserving its data pipeline, evaluation workflow, and Hugging Face-compatible checkpoints, and supports both LoRA and full-parameter fine-tuning.

Zhichao Xu, Xueguang Ma, Shengyao Zhuang et al. · 2 citations