Name: Zonghan Yang
Type: User
Company: @THUNLP-MT @AgentForceTeamOfficial
Bio: PhD in Tsinghua University, obsessed with LLM ∩ Control (alignment, agent; and they're equivalent!). Two drifters with the world to see.
Location: Beijing
Blog: minicheshire.github.io
Zonghan Yang's Projects
code for our ICML 2023 paper "mproving Adversarial Robustness of Deep Equilibrium Models with Explicit Regulations Along the Neural Dynamics"
This repo contains the source code for our NeurIPS 2022 paper: A closer Look at the Adversarial Robustness of Deep Equilibrium Models.
Interpolation between Residual and Non-Residual Networks, ICML 2020. https://arxiv.org/abs/2006.05749
A machine translation reading list maintained by Tsinghua Natural Language Processing Group
code for the ICLR'22 paper: On Robust Prefix-Tuning for Text Classification
Code for the ICLR 2023 paper: Unified Detoxifying and Debiasing in Language Generation via Inference-time Adaptive Optimization