Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization Paper • 2610.37058 • Published 23 days ago
Exploring the Limits of the Delta Learning Hypothesis: Single-Pair Generator Biases in Direct Preference Optimization Paper • 2610.37058 • Published 23 days ago
Multi-SFT: Permissively-Licensed Multilingual Instruction-Following Paper • 2610.22086 • Published Oct 15
Multilingual Training and Evaluation Resources for Vision-Language Models Paper • 2604.18347 • Published Jun 5
Contrastive Language-Image Pretrained Models are Zero-Shot Human Scanpath Predictors Paper • 2305.12380 • Published May 21, 2023