Author

Ou Wu

Observed name: Wu, Ou

Institution: University of Chinese Academy of Sciences

Observed institution: University of Chinese Academy of Sciences

OpenAlex ID: A5137626952

One Algorithm, Two Goals: Dual Scoring for Parameter and Data Selection in LLM Fine-Tuning

2026 · Chen, Xinrui, Yang, Liu, et al. · arXiv (Cornell University) · 2

AlphaToken: Decoupling Adaptation and Stability for Path-Aware Response Token Valuation in LLM Post-Training

2026 · Qing Liu, Ou Wu, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP) · 2

One Distribution, Two Channels: Coverage-Calibrated KV Retention and Compensation

2026 · Liu, Shuxin, Liu, Qing, et al. · arXiv (Cornell University)

Token Utility Is Selection-Conditioned: Coupled Selection of Prompt Context and Response Supervision for Instruction Tuning

2026 · Wu, Can, Chen, Xinrui, et al. · arXiv (Cornell University)

Revisiting Ripple Effects in Knowledge Editing through Pressure-Aware Joint Neighborhood Optimization

2026 · Huang, Haoben, Liu, Shuxin, et al. · arXiv (Cornell University)

Towards a Data-Parameter Correspondence for LLMs: A Preliminary Discussion

2026 · Wu, Ou · arXiv (Cornell University)

MetaKE: Meta-Learning for Knowledge Editing Toward a Better Accuracy-Editability Trade-off

2026 · Liu, Shuxin, Gao, Di, et al. · arXiv (Cornell University)

Two to Tango: Coupled Task-Reference Selection for Safe LLM Fine-tuning

2026 · Xinrui Chen, Jianhao Zhang, et al. · Conference on Empirical Methods in Natural Language Processing (EMNLP)

Works count: 8

Citation count: 4

H-index: 2

I10-index: