Kaiyan Chang

Orcid: 0009-0007-3106-679X

Affiliations:
  • Northeastern University, School of Computer Science and Engineering, Shenyang, China


According to our database1, Kaiyan Chang authored at least 12 papers between 2023 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

Online presence:

On csauthors.net:

Bibliography

2026
RouteLMT: Learned Sample Routing for Hybrid LLM Translation Deployment.
CoRR, April, 2026

When Scaling Fails: Mitigating Audio Perception Decay of LALMs via Multi-Step Perception-Aware Reasoning.
CoRR, March, 2026

APR: Penalizing Structural Redundancy in Large Reasoning Models via Anchor-based Process Rewards.
CoRR, February, 2026

NiuTrans.LMT: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

2025
Beyond English: Toward Inclusive and Scalable Multilingual Machine Translation with LLMs.
CoRR, November, 2025

SUBQRAG: Sub-Question Driven Dynamic Graph RAG.
CoRR, October, 2025

One Size Does Not Fit All: A Distribution-Aware Sparsification for More Precise Model Merging.
CoRR, August, 2025

StoryBench: A Dataset for Diverse, Explainable, Multi-hop Narrative Text-to-Image Generation.
Proceedings of the Natural Language Processing and Chinese Computing, 2025

Step-level Verifier-guided Hybrid Test-Time Scaling for Large Language Models.
Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, 2025

2024
Efficient Prompting Methods for Large Language Models: A Survey.
CoRR, 2024

Hybrid Alignment Training for Large Language Models.
Proceedings of the Findings of the Association for Computational Linguistics, 2024

2023
Learning Evaluation Models from Large Language Models for Sequence Generation.
CoRR, 2023


  Loading...