Showing 1–14 of 14 results
/ Date/ Name
Mar 20, 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object NavigationMar 13, 2024Language models scale reliably with over-training and on downstream tasksMay 3, 2021Act the Part: Learning Interaction Strategies for Articulated Object Part DiscoveryApr 27, 2023DataComp: In search of the next generation of multimodal datasetsJun 17, 2024DataComp-LM: In search of the next generation of training sets for language modelsAug 2, 2023OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language ModelsMar 10, 2025Should VLMs be Pre-trained with Image Data?Jul 11, 2023Objaverse-XL: A Universe of 10M+ 3D ObjectsMar 10, 2022Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference timeApr 14, 2023Multimodal C4: An Open, Billion-scale Corpus of Images Interleaved with TextJul 19, 2023Improving Multimodal Datasets with Image CaptioningJul 19, 2022Structure from Action: Learning Interactions for Articulated Object 3D Structure DiscoveryMar 31, 2022Continuous Scene Representations for Embodied AIAug 10, 2022Patching open-vocabulary models by interpolating weights