Alert button
Picture for Tianwei Ni

Tianwei Ni

Alert button

Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers

Add code
Bookmark button
Alert button
Mar 29, 2024
Pingcheng Dong, Yonghao Tan, Dong Zhang, Tianwei Ni, Xuejiao Liu, Yu Liu, Peng Luo, Luhong Liang, Shih-Yang Liu, Xijie Huang, Huaiyu Zhu, Yun Pan, Fengwei An, Kwang-Ting Cheng

Figure 1 for Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
Figure 2 for Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
Figure 3 for Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
Figure 4 for Genetic Quantization-Aware Approximation for Non-Linear Operations in Transformers
Viaarxiv icon

Do Transformer World Models Give Better Policy Gradients?

Add code
Bookmark button
Alert button
Feb 11, 2024
Michel Ma, Tianwei Ni, Clement Gehring, Pierluca D'Oro, Pierre-Luc Bacon

Figure 1 for Do Transformer World Models Give Better Policy Gradients?
Figure 2 for Do Transformer World Models Give Better Policy Gradients?
Figure 3 for Do Transformer World Models Give Better Policy Gradients?
Figure 4 for Do Transformer World Models Give Better Policy Gradients?
Viaarxiv icon

Bridging State and History Representations: Understanding Self-Predictive RL

Add code
Bookmark button
Alert button
Jan 17, 2024
Tianwei Ni, Benjamin Eysenbach, Erfan Seyedsalehi, Michel Ma, Clement Gehring, Aditya Mahajan, Pierre-Luc Bacon

Figure 1 for Bridging State and History Representations: Understanding Self-Predictive RL
Figure 2 for Bridging State and History Representations: Understanding Self-Predictive RL
Figure 3 for Bridging State and History Representations: Understanding Self-Predictive RL
Figure 4 for Bridging State and History Representations: Understanding Self-Predictive RL
Viaarxiv icon

When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment

Add code
Bookmark button
Alert button
Jul 31, 2023
Tianwei Ni, Michel Ma, Benjamin Eysenbach, Pierre-Luc Bacon

Figure 1 for When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Figure 2 for When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Figure 3 for When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Figure 4 for When Do Transformers Shine in RL? Decoupling Memory from Credit Assignment
Viaarxiv icon

Towards Disturbance-Free Visual Mobile Manipulation

Add code
Bookmark button
Alert button
Dec 17, 2021
Tianwei Ni, Kiana Ehsani, Luca Weihs, Jordi Salvador

Figure 1 for Towards Disturbance-Free Visual Mobile Manipulation
Figure 2 for Towards Disturbance-Free Visual Mobile Manipulation
Figure 3 for Towards Disturbance-Free Visual Mobile Manipulation
Figure 4 for Towards Disturbance-Free Visual Mobile Manipulation
Viaarxiv icon

Recurrent Model-Free RL is a Strong Baseline for Many POMDPs

Add code
Bookmark button
Alert button
Oct 11, 2021
Tianwei Ni, Benjamin Eysenbach, Ruslan Salakhutdinov

Figure 1 for Recurrent Model-Free RL is a Strong Baseline for Many POMDPs
Figure 2 for Recurrent Model-Free RL is a Strong Baseline for Many POMDPs
Figure 3 for Recurrent Model-Free RL is a Strong Baseline for Many POMDPs
Figure 4 for Recurrent Model-Free RL is a Strong Baseline for Many POMDPs
Viaarxiv icon

Adaptive Agent Architecture for Real-time Human-Agent Teaming

Add code
Bookmark button
Alert button
Mar 07, 2021
Tianwei Ni, Huao Li, Siddharth Agrawal, Suhas Raja, Fan Jia, Yikang Gui, Dana Hughes, Michael Lewis, Katia Sycara

Figure 1 for Adaptive Agent Architecture for Real-time Human-Agent Teaming
Figure 2 for Adaptive Agent Architecture for Real-time Human-Agent Teaming
Figure 3 for Adaptive Agent Architecture for Real-time Human-Agent Teaming
Figure 4 for Adaptive Agent Architecture for Real-time Human-Agent Teaming
Viaarxiv icon

f-IRL: Inverse Reinforcement Learning via State Marginal Matching

Add code
Bookmark button
Alert button
Nov 09, 2020
Tianwei Ni, Harshit Sikchi, Yufei Wang, Tejus Gupta, Lisa Lee, Benjamin Eysenbach

Figure 1 for f-IRL: Inverse Reinforcement Learning via State Marginal Matching
Figure 2 for f-IRL: Inverse Reinforcement Learning via State Marginal Matching
Figure 3 for f-IRL: Inverse Reinforcement Learning via State Marginal Matching
Figure 4 for f-IRL: Inverse Reinforcement Learning via State Marginal Matching
Viaarxiv icon

Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient

Add code
Bookmark button
Alert button
Jul 03, 2020
Yufei Wang, Tianwei Ni

Figure 1 for Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
Figure 2 for Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
Figure 3 for Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
Figure 4 for Meta-SAC: Auto-tune the Entropy Temperature of Soft Actor-Critic via Metagradient
Viaarxiv icon

Phase Collaborative Network for Multi-Phase Medical Imaging Segmentation

Add code
Bookmark button
Alert button
Dec 06, 2018
Huangjie Zheng, Lingxi Xie, Tianwei Ni, Ya Zhang, Yan-Feng Wang, Qi Tian, Elliot K. Fishman, Alan L. Yuille

Figure 1 for Phase Collaborative Network for Multi-Phase Medical Imaging Segmentation
Figure 2 for Phase Collaborative Network for Multi-Phase Medical Imaging Segmentation
Figure 3 for Phase Collaborative Network for Multi-Phase Medical Imaging Segmentation
Figure 4 for Phase Collaborative Network for Multi-Phase Medical Imaging Segmentation
Viaarxiv icon