Counterfactual contrastive learning: robust representations via causal image synthesisby Melanie Roschewitz, Fabio De Sousa Ribeiro,…
A Knowledge-Injected Curriculum Pretraining Framework for Question Answeringby Xin Lin, Tianhuang Su, Zhenya Huang, Shangzi…
Semiparametric Token-Sequence Co-Supervisionby Hyunji Lee, Doyoung Kim, Jihoon Jun, Sejune Joo, Joel Jang, Kyoung-Woon On,…
LAFS: Landmark-based Facial Self-supervised Learning for Face Recognitionby Zhonglin Sun, Chen Feng, Ioannis Patras, Georgios…
Cross-domain and Cross-dimension Learning for Image-to-Graph Transformersby Alexander H. Berger, Laurin Lux, Suprosanna Shit, Ivan…
Pix2Gif: Motion-Guided Diffusion for GIF Generationby Hitesh Kandala, Jianfeng Gao, Jianwei YangFirst submitted to arxiv…
Yi: Open Foundation Models by 01.AIby 01.AI, Alex Young, Bei Chen, Chao Li, Chengen Huang,…
NeuSpeech: Decode Neural signal as Speechby Yiqian Yang, Yiqun Duan, Qiang Zhang, Hyejeong Jo, Jinni…
Word Order and World Knowledgeby Qinghua Zhao, Vinit Ravishankar, Nicolas Garneau, Anders SøgaardFirst submitted to…
Is It a Free Lunch for Removing Outliers during Pretraining?by Baohao Liao, Christof MonzFirst submitted…