SkillFormer, PATS, and ProfVLM deliver state-of-the-art multi-view proficiency estimation on Ego-Exo4D with up to 20x fewer parameters by combining selective fusion, dense sampling, and generative feedback.
F., Smethurst, G., Moraes, J
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
Stack Overflow code quality varies by US region, with readability violations most common overall and fewer issues in states with higher income, internet access, and equitable wealth distribution.
citing papers explorer
-
Parameter-Efficient Multi-View Proficiency Estimation: From Discriminative Classification to Generative Feedback
SkillFormer, PATS, and ProfVLM deliver state-of-the-art multi-view proficiency estimation on Ego-Exo4D with up to 20x fewer parameters by combining selective fusion, dense sampling, and generative feedback.
-
Geographic Variation in Stack Overflow Code Quality: Evidence from a Cross-Regional Study of Coding Practices
Stack Overflow code quality varies by US region, with readability violations most common overall and fewer issues in states with higher income, internet access, and equitable wealth distribution.