3 sources
A good person to know for the longer Microsoft line that runs from machine-comprehension systems into more recent adaptation work like LoRA and MTL-LoRA.
Researcher Profile
Editor reviewedYelong Shen
Parameter-efficient finetuning
Microsoft researcher across reading systems and low-rank model adaptation
Useful because his work spans the older machine-comprehension era at Microsoft and the later LoRA-style adaptation line that became core infrastructure for modern finetuning.
Organizations
Microsoft
Topics
About This Page
This profile is meant to help you get oriented quickly: why this researcher matters, what to read first, and where to explore next.
Known For
The ideas, systems, and research directions that make this person worth knowing.
01
LoRA and low-rank adaptation
02
Machine-comprehension systems at Microsoft
03
Multi-task adaptation methods for large models
04
Parameter-efficient finetuning
05
LoRA: Low-Rank Adaptation of Large Language Models
06
LoRA
Start Here
Canonical papers, project pages, or repositories that anchor this profile.
Related Researchers
People worth exploring next because they share topics, labs, or source material with this profile.
3 sources
A high-signal person to study if you care about the practical mechanics of adapting large models, especially where scaling theory turns into techniques that actually spread across the industry.
Start HereAbout | Edward Hu
3 sources
A useful profile for the path from parameter-efficient finetuning into newer agent-safety work, especially if you want people whose contributions span both model customization and tool-using systems security.
3 sources
One of the clearer people to follow if you want the bridge between deep-learning theory, practical adaptation methods like LoRA, and broader attempts to explain how large language models actually work.
Start HereZeyuan Allen-Zhu's Home Page
3 sources
A useful profile for the seam between deep-learning theory and practical large-model methods, especially if you want someone whose work spans convergence theory, small-language-model data design, and LoRA.
Start HereWelcoming our New Faculty Members
1 source
Co-authored LoRA: one of the core techniques behind modern fine-tuning pipelines.