◍wovepaper
SearchResearchersInstitutions
Sign in
researcher

Leiyi Hu

3 papers hereh-index 6246 citations9 works total

Matching runs newest-first, so older work may not be attached to this profile yet.

author position
  • middle author3

Across the 3 of 3 papers where every author was matched, so the position is known.

fields
  • cs.CV2
  • cs.CL1

identity via Semantic Scholar / OpenAlex

activity
20232025
most cited5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks

3 citations · 3 across the 2 of their papers we have counts for

collaborators

3 papers

cs.CL2025

Rectify Evaluation Preference: Improving LLMs' Critique on Math Reasoning via Perplexity-aware Reinforcement Learning

Changyuan Tian, Zhicong Lu, Shuang Qian +8

To improve Multi-step Mathematical Reasoning (MsMR) of Large Language Models (LLMs), it is crucial to obtain scalable supervision from the corpus by automatically critiquing mistak…

cs.CV2024★ 3 cited

5%>100%: Breaking Performance Shackles of Full Fine-Tuning on Visual Recognition Tasks

Dongshuo Yin, Leiyi Hu, Bin Li +2

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks…

cs.CV2023

Adapter is All You Need for Tuning Visual Tasks

Dongshuo Yin, Leiyi Hu, Bin Li +1

Pre-training & fine-tuning can enhance the transferring efficiency and performance in visual tasks. Recent delta-tuning methods provide more options for visual classification tasks…

◍wovepaper

Papers, researchers and institutions, woven together.

Explore
  • Search
  • Researchers
  • Institutions
Account
  • Library
  • Chat
Data
  • arXiv.org
  • Semantic Scholar
  • OpenAlex
  • Latest RSS
AboutContactPrivacyDevelopersllms.txtopenapi.json
Not affiliated with arXiv. Researcher data from Semantic Scholar (ODC-BY) and OpenAlex.