162 citations · 445 across the 12 of their papers we have counts for
12 papers
Towards Accurate Model Selection in Deep Unsupervised Domain Adaptation
Kaichao You, Ximei Wang, Mingsheng Long +1
Deep unsupervised domain adaptation (Deep UDA) methods successfully leverage rich labeled data in a source domain to boost the performance on related but unlabeled data in a target…
Jenga: Effective Memory Management for Serving LLM with Heterogeneity
Chen Zhang, Kuntai Du, Shu Liu +10
Large language models (LLMs) are widely used but expensive to run, especially as inference workloads grow. To lower costs, maximizing the request batch size by managing GPU memory…
depyf: Open the Opaque Box of PyTorch Compiler for Machine Learning Researchers
Kaichao You, Runsheng Bai, Meng Cao +3
PyTorch \texttt{2.x} introduces a compiler designed to accelerate deep learning programs. However, for machine learning researchers, adapting to the PyTorch compiler to full potent…
Efficient ConvBN Blocks for Transfer Learning and Beyond
Kaichao You, Guo Qin, Anchang Bao +4
Convolution-BatchNorm (ConvBN) blocks are integral components in various computer vision tasks and other domains. A ConvBN block can operate in three modes: Train, Eval, and Deploy…
Video Interpolation by Event-driven Anisotropic Adjustment of Optical Flow
Song Wu, Kaichao You, Weihua He +5
Video frame interpolation is a challenging task due to the ever-changing real-world scene. Previous methods often calculate the bi-directional optical flows and then predict the in…
TimeReplayer: Unlocking the Potential of Event Cameras for Video Interpolation
Weihua He, Kaichao You, Zhendong Qiao +6
Recording fast motion in a high FPS (frame-per-second) requires expensive high-speed cameras. As an alternative, interpolating low-FPS videos from commodity cameras has attracted s…
From Big to Small: Adaptive Learning to Partial-Set Domains
Zhangjie Cao, Kaichao You, Ziyang Zhang +2
Domain adaptation targets at knowledge acquisition and dissemination from a labeled source domain to an unlabeled target domain under distribution shift. Still, the common requirem…
Ranking and Tuning Pre-trained Models: A New Paradigm for Exploiting Model Hubs
Kaichao You, Yong Liu, Ziyang Zhang +3
Model hubs with many pre-trained models (PTMs) have become a cornerstone of deep learning. Although built at a high cost, they remain \emph{under-exploited} -- practitioners usuall…
Tianshou: a Highly Modularized Deep Reinforcement Learning Library
Jiayi Weng, Huayu Chen, Dong Yan +6
In this paper, we present Tianshou, a highly modularized Python library for deep reinforcement learning (DRL) that uses PyTorch as its backend. Tianshou intends to be research-frie…
LogME: Practical Assessment of Pre-trained Models for Transfer Learning
Kaichao You, Yong Liu, Jianmin Wang +1
This paper studies task adaptive pre-trained model selection, an underexplored problem of assessing pre-trained models for the target task and select best ones from the model zoo \…
How Does Learning Rate Decay Help Modern Neural Networks?
Kaichao You, Mingsheng Long, Jianmin Wang +1
Learning rate decay (lrDecay) is a \emph{de facto} technique for training modern neural networks. It starts with a large learning rate and then decays it multiple times. It is empi…
Learning to Transfer Examples for Partial Domain Adaptation
Zhangjie Cao, Kaichao You, Mingsheng Long +2
Domain adaptation is critical for learning in new and unseen environments. With domain adversarial training, deep networks can learn disentangled and transferable features that eff…