Yuxiang Huang

Orcid: 0009-0007-6448-4576

Affiliations:
  • Tsinghua University, BNRist, Beijing, China


According to our database1, Yuxiang Huang authored at least 17 papers between 2022 and 2026.

Collaborative distances:
  • Dijkstra number2 of four.
  • Erdős number3 of four.

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
Spava: Accelerating Long-Video Understanding via Sequence-Parallelism-aware Approximate Attention.
CoRR, January, 2026

2025
NOSA: Native and Offloadable Sparse Attention.
CoRR, October, 2025

InfLLM-V2: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation.
CoRR, September, 2025

MiniCPM-V 4.5: Cooking Efficient MLLMs via Architecture, Data, and Training Recipe.
CoRR, September, 2025

MiniCPM4: Ultra-Efficient LLMs on End Devices.
CoRR, June, 2025

Tool Learning with Foundation Models.
ACM Comput. Surv., April, 2025

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling.
CoRR, February, 2025

Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads on Consumer-Grade Devices.
Trans. Mach. Learn. Res., 2025

CITR: Efficient Long Video Understanding Needs Causal Importance.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

FR-Spec: Accelerating Large-Vocabulary Language Models via Frequency-Ranked Speculative Sampling.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

APB: Accelerating Distributed Long-Context Inference by Passing Compressed Context Blocks across GPUs.
Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2025

2024
Time series data encoding in Apache IoTDB: comparative analysis and recommendation.
VLDB J., May, 2024

Locret: Enhancing Eviction in Long-Context LLM Inference with Trained Retaining Heads.
CoRR, 2024

MiniCPM: Unveiling the Potential of Small Language Models with Scalable Training Strategies.
CoRR, 2024

Ouroboros: Generating Longer Drafts Phrase by Phrase for Faster Speculative Decoding.
Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, 2024

2023
Tool Learning with Foundation Models.
CoRR, 2023

2022
Time Series Data Encoding for Efficient Storage: A Comparative Analysis in Apache IoTDB.
Proc. VLDB Endow., 2022


  Loading...