2.2k citations · 10.8k across the 93 of their papers we have counts for
8 papers · 1 filter
Guide Your Agent with Adaptive Multimodal Rewards
Changyeon Kim, Younggyo Seo, Hao Liu +4
Developing an agent capable of adapting to unseen environments remains a difficult challenge in imitation learning. This work presents Adaptive Return-conditioned Policy (ARP), an…
NICE: CVPR 2023 Challenge on Zero-shot Image Captioning
Taehoon Kim, Pyunghwan Ahn, Sangyun Kim +39
In this report, we introduce NICE (New frontiers for zero-shot Image Captioning Evaluation) project and share the results and outcomes of 2023 challenge. This project is designed t…
3D Denoisers are Good 2D Teachers: Molecular Pretraining via Denoising and Cross-Modal Distillation
Sungjun Cho, Dae-Woong Jeong, Sung Moon Ko +5
Pretraining molecular representations from large unlabeled data is essential for molecular property prediction due to the high cost of obtaining ground-truth labels. While there ex…
Lightweight feature encoder for wake-up word detection based on self-supervised speech representation
Hyungjun Lim, Younggwan Kim, Kiho Yeom +4
Self-supervised learning method that provides generalized speech representations has recently received increasing attention. Wav2vec 2.0 is the most famous example, showing remarka…
Hierarchical discriminative learning improves visual representations of biomedical microscopy
Cheng Jiang, Xinhai Hou, Akhil Kondepudi +5
Learning high-quality, self-supervised, visual representations is essential to advance the role of computer vision in biomedical microscopy and clinical medicine. Previous work has…
Multimodal Deep Learning
Cem Akkus, Luyang Chu, Vladana Djakovic +14
This book is the result of a seminar in which we reviewed multimodal approaches and attempted to create a solid overview of the field, starting with the current state-of-the-art ap…
Transferring Pre-trained Multimodal Representations with Cross-modal Similarity Matching
Byoungjip Kim, Sungik Choi, Dasol Hwang +2
Despite surprising performance on zero-shot transfer, pre-training a large-scale multimodal model is often prohibitive as it requires a huge amount of data and computing resources.…
Learning to Unlearn: Instance-wise Unlearning for Pre-trained Classifiers
Sungmin Cha, Sungjun Cho, Dasol Hwang +3
Since the recent advent of regulations for data protection (e.g., the General Data Protection Regulation), there has been increasing demand in deleting information learned from sen…