Weighted Point Set Embedding for Multimodal Contrastive Learning Toward Optimal Similarity Metricby Toshimitsu Uesaka, Taiji…
Overcoming Knowledge Barriers: Online Imitation Learning from Observation with Pretrained World Modelsby Xingyuan Zhang, Philip…
Efficient Remote Sensing with Harmonized Transfer Learning and Modality Alignmentby Tengjun HuangFirst submitted to arxiv…
LayerSkip: Enabling Early Exit Inference and Self-Speculative Decodingby Mostafa Elhoushi, Akshat Shrivastava, Diana Liskovich, Basil…
MoDE: CLIP Data Experts via Clusteringby Jiawei Ma, Po-Yao Huang, Saining Xie, Shang-Wen Li, Luke…
Feature Distribution Shift Mitigation with Contrastive Pretraining for Intrusion Detectionby Weixing Wang, Haojin Yang, Christoph…
OccFeat: Self-supervised Occupancy Feature Prediction for Pretraining BEV Segmentation Networksby Sophia Sirko-Galouchenko, Alexandre Boulch, Spyros…
How to Benchmark Vision Foundation Models for Semantic Segmentation?by Tommie Kerssies, Daan de Geus, Gijs…
Many-Shot In-Context Learningby Rishabh Agarwal, Avi Singh, Lei M. Zhang, Bernd Bohnet, Luis Rosias, Stephanie…
ScaleFold: Reducing AlphaFold Initial Training Time to 10 Hoursby Feiwen Zhu, Arkadiusz Nowaczynski, Rundong Li,…