minicheshire
PhD in Tsinghua University, obsessed with LLM ∩ Control (alignment, agent; and they're equivalent!). Two drifters with the world to see.
@THUNLP-MT @AgentForceTeamOfficialBeijing
Pinned Repositories
UA2-Agent
Official Implementation of UA^{2}-Agent and other baseline algorithms of "Towards Unified Alignment Between Agents, Humans, and Environment"
UA2-WebShop
Official Implementation of the retrofitted WebShop environment in "Towards Unified Alignment Between Agents, Humans, and Environment"
DEQ-Regulating-Neural-Dynamics
code for our ICML 2023 paper "mproving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics"
DEQ-White-Box-Robustness
This repo contains the source code for our NeurIPS 2022 paper: A closer Look at the Adversarial Robustness of Deep Equilibrium Models.
InResNet
Interpolation between Residual and Non-Residual Networks, ICML 2020. https://arxiv.org/abs/2006.05749
MT-Reading-List
A machine translation reading list maintained by Tsinghua Natural Language Processing Group
Robust-Prefix-Tuning
code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification
Unified-Debiasing-and-Detoxifying
Code for the ICLR 2023 paper: Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
MT-Reading-List
A machine translation reading list maintained by Tsinghua Natural Language Processing Group
THUMT
An open-source neural machine translation toolkit developed by Tsinghua Natural Language Processing Group
minicheshire's Repositories
minicheshire/Robust-Prefix-Tuning
code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification
minicheshire/InResNet
Interpolation between Residual and Non-Residual Networks, ICML 2020. https://arxiv.org/abs/2006.05749
minicheshire/Unified-Debiasing-and-Detoxifying
Code for the ICLR 2023 paper: Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization
minicheshire/DEQ-Regulating-Neural-Dynamics
code for our ICML 2023 paper "mproving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics"
minicheshire/DEQ-White-Box-Robustness
This repo contains the source code for our NeurIPS 2022 paper: A closer Look at the Adversarial Robustness of Deep Equilibrium Models.
minicheshire/MT-Reading-List
A machine translation reading list maintained by Tsinghua Natural Language Processing Group