Model soups: averaging weights of multiple fine-tuned models improves accuracy without increasing inference time

Mitchell Wortsman, Gabriel Ilharco, Samir Yitzhak Gadre, +8

arXiv (Cornell University)

Few-shot LearningLlm Fine-tuningEngineeringMachine LearningModel Tuning +24

CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation

Samir Yitzhak Gadre, Mitchell Wortsman, Gabriel Ilharco, +2

EngineeringMachine LearningArbitrary ObjectsField RoboticsUncommon Objects +18

End-User Robot Programming Using Mixed Reality

Samir Yitzhak Gadre, Eric Rosen, Gary W. Chien, +3

Human-robot Collaborative AssemblyRobot ProgrammingEngineeringMixed RealityIntelligent Robotics +14

DataComp: In search of the next generation of multimodal datasets

Samir Yitzhak Gadre, Gabriel Ilharco, Alex Chengyu Fang, +31

arXiv (Cornell University)

EngineeringMachine LearningMultimodal LearningMultimedia AnalysisMultimodal Llm +15

OpenFlamingo: An Open-Source Framework for Training Large Autoregressive Vision-Language Models

Anas Awadalla, Irena Gao, Josh Gardner, +13

arXiv (Cornell University)

Natural Language ProcessingLarge Ai ModelMultimodal LlmOpen-source FrameworkEngineering +13

Continuous Scene Representations for Embodied AI

Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song, +1

2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Artificial IntelligenceScene AnalysisEngineeringMachine LearningEmbodied Ai +16

Objaverse-XL: A Universe of 10M+ 3D Objects

Matt Deitke, Ruoshi Liu, Matthew Wallingford, +14

arXiv (Cornell University)

EngineeringMachine Learning3D ModelingComputer-aided DesignVision Models +16

Act the Part: Learning Interaction Strategies for Articulated Object Part Discovery

Samir Yitzhak Gadre, Kiana Ehsani, Shuran Song

2021 IEEE/CVF International Conference on Computer Vision (ICCV)

Artificial IntelligenceEngineeringMachine LearningPhysical IntuitionHuman Pose Estimation +20

Patching open-vocabulary models by interpolating weights

Gabriel Ilharco, Mitchell Wortsman, Samir Yitzhak Gadre, +5

arXiv (Cornell University)

Llm Fine-tuningEngineeringMachine LearningOpen-vocabulary ModelsMultilingual Pretraining +15

Improving Multimodal Datasets with Image Captioning

Thao D. Nguyen, Samir Yitzhak Gadre, Gabriel Ilharco, +2

arXiv (Cornell University)

EngineeringMachine LearningMultimodal LearningCorpus LinguisticsNatural Language Processing +17