| Can Medical Vision-Language Pre-training Succeed with Purely Synthetic Data? | Oct 17, 2024 | zero-shot-classificationZero-Shot Learning | —Unverified | 0 |
| LLM Chain Ensembles for Scalable and Accurate Data Annotation | Oct 16, 2024 | zero-shot-classificationZero-Shot Learning | CodeCode Available | 0 |
| CtrlSynth: Controllable Image Text Synthesis for Data-Efficient Multimodal Learning | Oct 15, 2024 | Image-text RetrievalText Retrieval | —Unverified | 0 |
| A Unified Debiasing Approach for Vision-Language Models across Modalities and Tasks | Oct 10, 2024 | FairnessImage Captioning | CodeCode Available | 0 |
| GLOV: Guided Large Language Models as Implicit Optimizers for Vision Language Models | Oct 8, 2024 | zero-shot-classificationZero-Shot Learning | CodeCode Available | 0 |
| Improving Predictor Reliability with Selective Recalibration | Oct 7, 2024 | zero-shot-classificationZero-Shot Learning | —Unverified | 0 |
| An Evaluation of Large Pre-Trained Models for Gesture Recognition using Synthetic Videos | Oct 3, 2024 | ClassificationGesture Recognition | —Unverified | 0 |
| Toward a Holistic Evaluation of Robustness in CLIP Models | Oct 2, 2024 | ClassificationOut-of-Distribution Detection | —Unverified | 0 |
| NECOMIMI: Neural-Cognitive Multimodal EEG-informed Image Generation with Diffusion Models | Oct 1, 2024 | Contrastive LearningEEG | CodeCode Available | 0 |
| Zero-Shot Classification of Crisis Tweets Using Instruction-Finetuned Large Language Models | Sep 30, 2024 | ClassificationDisaster Response | —Unverified | 0 |
