Fine-tuning Gemini 2.5 Pro with LoRA on 400 home videos improves per-feature agreement with clinicians by 40% and zero-shot ASD diagnosis F1 by 53% on held-out data, with classifier pipelines reaching 77% accuracy.
Advancing hu- man action recognition with foundation models trained on unlabeled public videos, 2024
3 Pith papers cite this work. Polarity classification is still indexing.
3
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
years
2026 3roles
background 1polarities
background 1representative citing papers
TwistedHumor dataset shows dark humor in YouTube Shorts clusters around critique, coping, awkwardness and identity with more mixed and toxic audience reactions than regular humor.
The survey organizes foundation models for sensor-based HAR into a lifecycle taxonomy and identifies three trajectories: HAR-specific models from scratch, adaptation of general time-series models, and integration with large language models.
citing papers explorer
-
Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos
Fine-tuning Gemini 2.5 Pro with LoRA on 400 home videos improves per-feature agreement with clinicians by 40% and zero-shot ASD diagnosis F1 by 53% on held-out data, with classifier pipelines reaching 77% accuracy.
-
When Jokes Cross the Line: Analyzing Regular Humor and Dark Humor in YouTube Shorts
TwistedHumor dataset shows dark humor in YouTube Shorts clusters around critique, coping, awkwardness and identity with more mixed and toxic audience reactions than regular humor.
-
Foundation Models Defining A New Era In Sensor-based Human Activity Recognition: A Survey And Outlook
The survey organizes foundation models for sensor-based HAR into a lifecycle taxonomy and identifies three trajectories: HAR-specific models from scratch, adaptation of general time-series models, and integration with large language models.