67 citations · 373 across the 64 of their papers we have counts for
7 papers · 1 filter
Retrieval Meets Reasoning: Even High-school Textbook Knowledge Benefits Multimodal Reasoning
Cheng Tan, Jingxuan Wei, Linzhuang Sun +5
Large language models equipped with retrieval-augmented generation (RAG) represent a burgeoning field aimed at enhancing answering capabilities by leveraging external knowledge bas…
MLIP: Enhancing Medical Visual Representation with Divergence Encoder and Knowledge-guided Contrastive Learning
Zhe Li, Laurence T. Yang, Bocheng Ren +4
The scarcity of annotated data has sparked significant interest in unsupervised pre-training methods that leverage medical reports as auxiliary signals for medical visual represent…
Mitigating Prior Shape Bias in Point Clouds via Differentiable Center Learning
Zhe Li, Xiying Wang, Jinglin Zhao +3
Masked autoencoding and generative pretraining have achieved remarkable success in computer vision and natural language processing, and more recently, they have been extended to th…
USTEP: Spatio-Temporal Predictive Learning under A Unified View
Cheng Tan, Jue Wang, Zhangyang Gao +2
Spatio-temporal predictive learning plays a crucial role in self-supervised learning, with wide-ranging applications across a diverse range of fields. Previous approaches for tempo…
OpenSTL: A Comprehensive Benchmark of Spatio-Temporal Predictive Learning
Cheng Tan, Siyuan Li, Zhangyang Gao +5
Spatio-temporal predictive learning is a learning paradigm that enables models to learn spatial and temporal patterns by predicting future frames from given past frames in an unsup…
SimVP: Simpler yet Better Video Prediction
Zhangyang Gao, Cheng Tan, Lirong Wu +1
From CNN, RNN, to ViT, we have witnessed remarkable advancements in video prediction, incorporating auxiliary inputs, elaborate neural architectures, and sophisticated training str…
Temporal Attention Unit: Towards Efficient Spatiotemporal Predictive Learning
Cheng Tan, Zhangyang Gao, Lirong Wu +4
Spatiotemporal predictive learning aims to generate future frames by learning from historical frames. In this paper, we investigate existing methods and present a general framework…