8 citations · 32 across the 32 of their papers we have counts for
6 papers · 1 filter
Localized Symbolic Knowledge Distillation for Visual Commonsense Models
Jae Sung Park, Jack Hessel, Khyathi Raghavi Chandu +8
Instruction following vision-language (VL) models offer a flexible interface that supports a broad range of multimodal tasks in a zero-shot fashion. However, interfaces that operat…
Are "Hierarchical" Visual Representations Hierarchical?
Ethan Shen, Ali Farhadi, Aditya Kusupati
Learned visual representations often capture large amounts of semantic information for accurate downstream applications. Human understanding of the world is fundamentally grounded…
Selective Visual Representations Improve Convergence and Generalization for Embodied AI
Ainaz Eftekhar, Kuo-Hao Zeng, Jiafei Duan +3
Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic an…
CLIP meets Model Zoo Experts: Pseudo-Supervision for Visual Enhancement
Mohammadreza Salehi, Mehrdad Farajtabar, Maxwell Horton +7
Contrastive language image pretraining (CLIP) is a standard method for training vision-language models. While CLIP is scalable, promptable, and robust to distribution shifts on ima…
SHARCS: Efficient Transformers through Routing with Dynamic Width Sub-networks
Mohammadreza Salehi, Sachin Mehta, Aditya Kusupati +2
We introduce SHARCS for adaptive inference that takes into account the hardness of input samples. SHARCS can train a router on any transformer network, enabling the model to direct…
MatFormer: Nested Transformer for Elastic Inference
Devvrit, Sneha Kudugunta, Aditya Kusupati +8
Foundation models are applied in a broad spectrum of settings with different inference constraints, from massive multi-accelerator clusters to resource-constrained standalone mobil…