Built with and by Teycir Ben Soltane•
How to Use•FAQ•GitHub•arXiv.org•
Share:
ArXivCSExplorer
☆☆Bookmarks🏆RSSHow to UseFAQ
Home/Authors/Jiayi Li

Jiayi Li

5 indexed papers

Recent (6 mo)
5
With code
0
Influential cites
0
Benchmarked
0

Publications per year

5
26

Top categories

ML×2NLP×2AI×2Architecture×1Info Retrieval×1

Frequent co-authors

Jiayi Liu3×
Hanqing Zeng2×
Yinglong Xia2×
Xiangjun Fan2×
Jiaqi Yang1×
Yihan Fu1×

Research Timeline

2026
Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback

The paper advocates for integrating explicit contextual feedback (like reviews and comments) into LLM-based recommender systems to achieve more personalized, transparent, and semantically aligned recommendations.

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step reasoning.

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification

OmniOPD introduces a logit-free, chunk-level distillation framework that improves on standard On-Policy Distillation by using semantic similarity and peak-entropy scheduling, achieving state-of-the-art performance even with black-box teachers.

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto large shared foundation models.

Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling

This paper presents DOPS, a hardware-aware framework for optimizing operator scheduling and weight layouts in Large Language Models, achieving significant speedups over prefill-decode disaggregation.

Highlighted terms show continued research focus across papers

Papers

cs.ARNEWEmpiricalJul 28, 2026

Beyond Prefill-Decode Disaggregation: Dissecting LLM Inference for Heterogeneous Platforms via Dynamic Operator Scheduling

Jiaqi Yang, Jiayi Li, Yihan Fu, Hongxiao Zhao +4 more

This paper presents DOPS, a hardware-aware framework for optimizing operator scheduling and weight layouts in Large Language Models, achieving significant speedups over prefill-decode disaggregation.

View →
cs.LGcs.CL
Recent
Jun 1, 2026

On the Scaling of PEFT: Towards Million Personal Models of Trillion Parameters

Mind Lab, :, Song Cao, Vic Cao +51 more

The paper reframes Parameter-Efficient Fine-Tuning (PEFT) from a mere cost-saving alternative to a robust architecture for creating persistent, personalized models that layer specific behaviors onto l…

View →
cs.AIRecentMay 31, 2026

DAG-MoE: From Simple Mixture to Structural Aggregation in Mixture-of-Experts

Jiarui Feng, Hanqing Zeng, Karish Grover, Ruizhong Qiu +10 more

The paper proposes DAG-MoE, a novel sparse Mixture-of-Experts framework that replaces standard weighted-sum aggregation with structural aggregation to enhance model performance and enable multi-step r…

View →
cs.LGcs.CLRecentMay 31, 2026

OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification

Yuhang Zhou, Lizhu Zhang, Yifan Wu, Mingyi Wang +4 more

OmniOPD introduces a logit-free, chunk-level distillation framework that improves on standard On-Policy Distillation by using semantic similarity and peak-entropy scheduling, achieving state-of-the-ar…

View →
cs.IRcs.AIRecentMay 27, 2026

Toward User Preference Alignment in LLM Recommendation via Explicit Context Feedback

Weizhi Zhang, Wooseong Yang, Yuxin Cui, Zhaohui Guo +8 more

The paper advocates for integrating explicit contextual feedback (like reviews and comments) into LLM-based recommender systems to achieve more personalized, transparent, and semantically aligned reco…

View →