Poly-View Contrastive Learning: Maximizing Information for Improved Representation Learning
Poly-view contrastive learning maximizes information by increasing view multiplicity, leading to improved representation learning.
MIM4D: Masked Modeling for Autonomous Driving Representation Learning
MIM4D proposes a novel pre-training paradigm based on dual masked image modeling (MIM) for autonomous driving representation learning, achieving state-of-the-art performance on the nuScenes dataset.
Self-supervised Representation Learning From Random Data Projectors
Learning high-quality data representations from randomness is a feasible and plausible alternative when transformation invariance is challenging.
DecisionNCE: Embodied Multimodal Representations via Implicit Preference Learning
DecisionNCE는 결정을 위한 다중 모달 표현을 내재적 선호 학습을 통해 효과적으로 추출하는 통합된 표현 학습 프레임워크를 제안합니다.
K-Link: Enhancing Representation Learning in Multivariate Time-Series Data with Knowledge-Link Graph from LLMs
Knowledge-Link Graph from LLMs improves representation learning in MTS data.
Guarantees for Learning Nonlinear Representations from Multiple Tasks with Non-Identical Covariates and Dependent Data
This paper provides theoretical guarantees for learning nonlinear representations from multiple tasks, even when the data distributions across tasks are different and the data within each task is statistically dependent.
© 2024 by Linnk AI