佐藤なつ | Deep Learning JP - Part 2

SimPer: Simple self-supervised learning of periodic targets( ICLR 2023 )

Learning Fine-Grained Bimanual Manipulation with Low-Cost Hardware

マルチモーダル基盤モデル

TrOCR: Transformer-based Optical Character Recognition with Pre-trained Models

HyperDiffusion: Generating Implicit Neural Fields withWeight-Space Diffusion

Poisoning Language Models During Instruction Tuning Instruction Tuningを利⽤した⾔語モデルのポイズニング

Egocentric Video Task Translation (CVPR 2023 Highlight)

Hyena Hierarchy: Towards Larger Convolutional Language Models

AUTOGT: AUTOMATED GRAPH TRANSFORMER ARCHITECTURE SEARCH

Decoupling Human and Camera Motion from Videos in the Wild (CVPR2023)

2 / 7«123 4 5...»最後 »