2023Q2 | 🍎 Paper Today I Read 🦔

[169] Direct Preference Optimization: Your Language Model is Secretly a Reward Model

[163] What You See is What You Read? Improving Text-Image Alignment Evaluation

google NeurIPS 2023Q2 evaluation

[135] Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with Text

multimodal dataset NeurIPS 2023Q2

[133] DataComp: In search of the next generation of multimodal datasets

dataset CLIP 2023Q2

[132] Hyperbolic Image-Text Representations

ICML CLIP 2023Q2 meta

[130] Segment Anything

segmentation 2023Q2 meta

[119] Visual Instruction Tuning

multimodal NeurIPS 2023Q2

[118] PaLI-X: On Scaling up a Multilingual Vision and Language Model

multimodal google 2023Q2

[115] ImageBind: One Embedding Space To Bind Them All

multimodal 25min 2023Q2 meta