Get started
Author

Xing Sun

Institution: Tencent (China)
Observed institution: Tencent (China)
ORCID: 0000-0001-8132-9083
Observed ORCID: 0000-0001-8132-9083
OpenAlex ID: A5144907272
Sinkhorn Distance Minimization for Knowledge Distillation
2024 · Xiao Cui, Yulei Qin, et al. · Language Resources and Evaluation Conference (LREC) · 4
PDF
Human Cognition Inspired RAG with Knowledge Graph for Complex Problem Solving
2026 · Yao Cheng, Yibo Zhao, et al. · Proceedings of the AAAI Conference on Artificial Intelligence · 2
VITA-Audio: Fast Interleaved Audio-Text Token Generation for Efficient Large Speech-Language Model
2025 · Zuwei Long, Yunhang Shen, et al. · neural information processing systems · 2
Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
2025 · Yulei Qin, Gang Li, et al. · neural information processing systems · 1
TPLA: Tensor Parallel Latent Attention for Efficient Disaggregated Prefill & Decode Inference
2026 · Xiaojuan Tang, Fanxu Meng, et al. · International Conference on Architectural Support for Programming Languages and Operating Systems (ASPLOS)
Breaking the Evaluation Paradox: Evaluating High-Entropy Search with Computationally Irreducible Constraints
2026 · Juntao Wu, Wei Wen, et al. · Findings of the Association for Computational Linguistics: ACL (Findings of ACL)
PDF
Collision to Cognition: Hash-Driven Graph Construction for Efficient RAG
2026 · Chuang Zhou, Zheng Yuan, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
Query-Aware Knowledge Retrieval via Hyperbolic Structuring
2026 · Chuang Zhou, Junnan Dong, et al. · Proceedings of the conference - Association for Computational Linguistics. Meeting
PDF
TransMLA: Migrating GQA Models to MLA with Full DeepSeek Compatibility and Speedup
2025 · Fanxu Meng, Pingzhi Tang, et al. · neural information processing systems
LTD-Bench: Evaluating Large Language Models by Letting Them Draw
2025 · Liuhao Lin, Ke Li, et al. · neural information processing systems
Works count: 10
Citation count: 9
H-index: 2
I10-index:
Year
Topic
Type