Qiyuan Zhu

Orcid: 0009-0008-9251-2711

According to our database1, Qiyuan Zhu authored at least 20 papers between 2017 and 2026.

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

Timeline

Legend:

Book  In proceedings  Article  PhD thesis  Dataset  Other 

Links

On csauthors.net:

Bibliography

2026
IndexMem: Learned KV-Cache Eviction with Latent Memory for Long-Context LLM Inference.
CoRR, May, 2026

NanoResearch: Co-Evolving Skills, Memory, and Policy for Personalized Research Automation.
CoRR, May, 2026

Intern-Atlas: A Methodological Evolution Graph as Research Infrastructure for AI Scientists.
CoRR, April, 2026

QaRL: Rollout-Aligned Quantization-Aware RL for Fast and Stable Training under Training-Inference Mismatch.
CoRR, April, 2026

Bit-by-Bit: Progressive QAT Strategy with Outlier Channel Splitting for Stable Low-Bit LLMs.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Adaptive Spatial and Temporal Redundancy Optimization for Efficient Reasoning in Large Language Models.
Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), 2026

Outlier Matters: Efficient Long-to-Short Reasoning via Outlier-Guided Model Merging.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging.
Proceedings of the Fortieth AAAI Conference on Artificial Intelligence, 2026

2025
Sub-MoE: Efficient Mixture-of-Expert LLMs Compression via Subspace Expert Merging.
CoRR, June, 2025

BTC-LLM: Efficient Sub-1-Bit LLM Quantization via Learnable Transformation and Binary Codebook.
CoRR, June, 2025

Follow-Your-Motion: Video Motion Transfer via Efficient Spatial-Temporal Decoupled Finetuning.
CoRR, June, 2025

Gait recognition via weighted global-local feature fusion and attention-based multiscale temporal aggregation.
J. Electronic Imaging, 2025

Outlier-Aware Model Merging for Efficient Multitask Inference.
Proceedings of the 33rd ACM International Conference on Multimedia, 2025

Delta Decompression for MoE-based LLMs Compression.
Proceedings of the Forty-second International Conference on Machine Learning, 2025

2024
Decentralised Traffic Incident Detection via Network Lasso.
CoRR, 2024

An Experimental Study on Decomposition-Based Deep Ensemble Learning for Traffic Flow Forecasting.
Proceedings of the AI 2024: Advances in Artificial Intelligence, 2024

2023
M<sup>6</sup>Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023

2022
Look Closer to Supervise Better: One-Shot Font Generation via Component-Based Discriminator.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2022

2017
Decentralized navigation of multiple agents based on ORCA and model predictive control.
Proceedings of the 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2017


  Loading...