efficient-exploration-of-high-tc-superconductors-using-gradient-based-composition-design

aldm-grasping-zero-shot-sim-to-real-transfer-for-robot-grasping

extremality-of-stabilizer-states-in-quantum-information-theory

vihe-virtual-in-hand-eye-transformer-for-3d-robotic-manipulation

vibration-sensitivity-comparison-of-one-port-and-two-port-mems-microphones

弱教師付きビデオ段落グラウンディングのためのシャム学習と共同アライメントおよび回帰

fedspu-personalized-federated-learning-for-resource-constrained-devices-with-stochastic-parameter-update

evolution-of-interpretable-learning-rules-in-foraging-agents


Anchor-based Robust Finetuning (ARF) regularizes the finetuning process of vision-language models like CLIP to preserve their out-of-distribution generalization capabilities in both domain shift and zero-shot learning scenarios.


coremsg

preserving-out-of-distribution-generalization-in-vision-language-model-finetuning


Preserving Out-of-Distribution Generalization in Vision-Language Model Finetuning


title_rewrite

Vision-language model finetuning