40 citations · 79 across the 14 of their papers we have counts for
14 papers
Decision Transformer under Random Frame Dropping
Kaizhe Hu, Ray Chen Zheng, Yang Gao +1
Controlling agents remotely with deep reinforcement learning~(DRL) in the real world is yet to come. One crucial stepping stone is to devise RL algorithms that are robust in the fa…
Seer: Language Instructed Video Prediction with Latent Diffusion Models
Xianfan Gu, Chuan Wen, Weirui Ye +2
Imagining the future trajectory is the key for robots to make sound planning and successfully reach their goals. Therefore, text-conditioned video prediction (TVP) is an essential…
Predictive Inference with Feature Conformal Prediction
Jiaye Teng, Chuan Wen, Dinghuai Zhang +3
Conformal prediction is a distribution-free technique for establishing valid prediction intervals. Although conventionally people conduct conformal prediction in the output space,…
USEEK: Unsupervised SE(3)-Equivariant 3D Keypoints for Generalizable Manipulation
Zhengrong Xue, Zhecheng Yuan, Jiashun Wang +3
Can a robot manipulate intra-category unseen objects in arbitrary poses with the help of a mere demonstration of grasping pose on a single object instance? In this paper, we try to…
EleGANt: Exquisite and Locally Editable GAN for Makeup Transfer
Chenyu Yang, Wanrong He, Yingqing Xu +1
Most existing methods view makeup transfer as transferring color distributions of different facial regions and ignore details such as eye shadows and blushes. Besides, they only ac…
Fighting Fire with Fire: Avoiding DNN Shortcuts through Priming
Chuan Wen, Jianing Qian, Jierui Lin +3
Across applications spanning supervised classification and sequential control, deep learning has been reported to find "shortcut" solutions that fail catastrophically under minor c…
Mastering Atari Games with Limited Data
Weirui Ye, Shaohuai Liu, Thanard Kurutach +2
Reinforcement learning has achieved great success in many applications. However, sample efficiency remains a key challenge, with prominent methods requiring millions (or even billi…
Maximum Entropy Population-Based Training for Zero-Shot Human-AI Coordination
Rui Zhao, Jinming Song, Yufeng Yuan +5
We study the problem of training a Reinforcement Learning (RL) agent that is collaborative with humans without using any human data. Although such agents can be obtained through se…
Differentiable Architecture Pruning for Transfer Learning
Nicolo Colombo, Yang Gao
We propose a new gradient-based approach for extracting sub-architectures from a given large model. Contrarily to existing pruning methods, which are unable to disentangle the netw…
Do You Listen with One or Two Microphones? A Unified ASR Model for Single and Multi-Channel Audio
Gokce Keskin, Minhua Wu, Brian King +5
Automatic speech recognition (ASR) models are typically designed to operate on a single input data type, e.g. a single or multi-channel audio streamed from a device. This design de…
Attention-based Neural Beamforming Layers for Multi-channel Speech Recognition
Bhargav Pulugundla, Yang Gao, Brian King +5
Attention-based beamformers have recently been shown to be effective for multi-channel speech recognition. However, they are less capable at capturing local information. In this wo…
Adapting by Pruning: A Case Study on BERT
Yang Gao, Nicolo Colombo, Wei Wang
Adapting pre-trained neural models to downstream tasks has become the standard practice for obtaining high-quality models. In this work, we propose a novel model adaptation paradig…
Mutual Information State Intrinsic Control
Rui Zhao, Yang Gao, Pieter Abbeel +2
Reinforcement learning has been shown to be highly successful at many challenging tasks. However, success heavily relies on well-shaped rewards. Intrinsically motivated RL attempts…
Disentangling Neural Architectures and Weights: A Case Study in Supervised Classification
Nicolo Colombo, Yang Gao
The history of deep learning has shown that human-designed problem-specific networks can greatly improve the classification performance of general neural models. In most practical…