Zhaoyi Yan

Orcid: 0000-0001-5155-5741

According to our database1, Zhaoyi Yan authored at least 22 papers between 2018 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
Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging.
CoRR, May, 2026

Not All Disagreement Is Learnable: Token Teachability in On-Policy Distillation.
CoRR, May, 2026

Geometry Conflict: Explaining and Controlling Forgetting in LLM Continual Post-Training.
CoRR, May, 2026

MergePipe: A Budget-Aware Parameter Management System for Scalable LLM Merging.
CoRR, February, 2026

Expandable Residual Approximation for Knowledge Distillation.
IEEE Trans. Neural Networks Learn. Syst., January, 2026

2025
Model Merging Scaling Laws in Large Language Models.
CoRR, September, 2025

InfiFPO: Implicit Model Fusion via Preference Optimization in Large Language Models.
CoRR, May, 2025

Delving Deep into Semantic Relation Distillation.
CoRR, March, 2025

Virtual Classification: Modulating Domain-Specific Knowledge for Multidomain Crowd Counting.
IEEE Trans. Neural Networks Learn. Syst., February, 2025

InfiFusion: A Unified Framework for Enhanced Cross-Model Reasoning via LLM Fusion.
CoRR, January, 2025

InfiGFusion: Graph-on-Logits Distillation via Efficient Gromov-Wasserstein for Model Fusion.
Proceedings of the Advances in Neural Information Processing Systems 38: Annual Conference on Neural Information Processing Systems 2025, 2025

2024
Multi-dataset learning with channel modulation loss for blind image quality assessment.
Multim. Tools Appl., December, 2024

Regressor-Segmenter Mutual Prompt Learning for Crowd Counting.
Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2024

2023
Towards Learning Multi-Domain Crowd Counting.
IEEE Trans. Circuits Syst. Video Technol., November, 2023

2022
Crowd Counting Via Perspective-Guided Fractional-Dilation Convolution.
IEEE Trans. Multim., 2022

An Improved Normed-Deformable Convolution for Crowd Counting.
IEEE Signal Process. Lett., 2022

2021
Variational Attention: Propagating Domain-Specific Knowledge for Multi-Domain Learning in Crowd Counting.
Proceedings of the 2021 IEEE/CVF International Conference on Computer Vision, 2021

Deep Metric Learning with Graph Consistency.
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence, 2021

2020
Prune it Yourself: Automated Pruning by Multiple Level Sensitivity.
Proceedings of the 3rd IEEE Conference on Multimedia Information Processing and Retrieval, 2020

Towards Accurate Low Bit-Width Quantization with Multiple Phase Adaptations.
Proceedings of the Thirty-Fourth AAAI Conference on Artificial Intelligence, 2020

2019
Perspective-Guided Convolution Networks for Crowd Counting.
Proceedings of the 2019 IEEE/CVF International Conference on Computer Vision, 2019

2018
Shift-Net: Image Inpainting via Deep Feature Rearrangement.
Proceedings of the Computer Vision - ECCV 2018, 2018


  Loading...