@riaddajani.bsky.social
Reposted
🚨New preprint w/ @lisik.bsky.social!
Aligning Video Models with Human Social Judgments via Behavior-Guided Fine-Tuning
We introduce a ~49k triplet social video dataset, uncover a modality gap (language > video), and close via novel behavior-guided fine-tuning.
🔗 arxiv.org/abs/2510.01502
Aligning Video Models with Human Social Judgments via Behavior-Guided Fine-Tuning
We introduce a ~49k triplet social video dataset, uncover a modality gap (language > video), and close via novel behavior-guided fine-tuning.
🔗 arxiv.org/abs/2510.01502
October 3, 2025 at 1:48 PM
🚨New preprint w/ @lisik.bsky.social!
Aligning Video Models with Human Social Judgments via Behavior-Guided Fine-Tuning
We introduce a ~49k triplet social video dataset, uncover a modality gap (language > video), and close via novel behavior-guided fine-tuning.
🔗 arxiv.org/abs/2510.01502
Aligning Video Models with Human Social Judgments via Behavior-Guided Fine-Tuning
We introduce a ~49k triplet social video dataset, uncover a modality gap (language > video), and close via novel behavior-guided fine-tuning.
🔗 arxiv.org/abs/2510.01502