Three papers accepted to ACL 2026 conference (2 main + 1 findings). Congratulations!
News
Two papers (REA-RL, DeepCompress) accepted to ICLR 2026. Congratulations!
Gave an invited talk at Agentic AI Summit 2026 titled Scalable and Personalizable AI Agents.
DeepAgent accepted to WWW 2026. Congratulations!
One paper accepted to NeurIPS 2025 D&B. Congratulations!
One paper accepted to EMNLP 2025 main conference. Congratulations!
Three papers accepted to ACL 2025 conference (2 main + 1 findings). Congratulations to all the co-authors!
Great news! Congratulations to my PhD mentor, Prof. Irwin King, on being selected as a 2024 ACM Fellow.
Two papers accepted to ICLR 2025 conference. Congratulations to all the co-authors!
Three papers accepted to NeurIPS 2024 conference (2 main + 1 benchmark). Congratulations to all the co-authors!
Three papers accepted to EMNLP 2024 main conference. Congratulations to all the co-authors!
Four papers accepted to ACL 2024 (1 main conf, 3 findings). Congratulations to all the co-authors!
Two papers accepted to ICLR 2024. PsychoBench is selected as an Oral presentation (1.2%). Congratulations to all the co-authors!
Gave a tutorial at CCMT 2023 titled From Machine to Human-like Intelligence: Large-Language Models for Multilinguality, Multimodality, Multi-Agents and Emotion Interaction.
Two papers accepted to EMNLP 2023 Findings. Congratulations to all the co-authors!
Our preprint GPT-4 Is Too Smart To Be Safe: Stealthy Chat with LLMs via Cipher is out. Refer to the Github repo CipherChat and Demo page LLMCipherChat for more details.
Our preprint Emotionally Numb or Empathetic? Evaluating How LLMs Feel Using EmotionBench is out. Refer to the Github repo for EmotionBench.
Onsite talk titled Large Language Models for Machine Translation in the LLM Series Workshops hosted by CIPS.
Our preprint Encouraging Divergent Thinking in Large Language Models through Multi-Agent Debate is out.
Our github project about Multi-Agents Debate with LLMs is open now.
Our preprint Exploring Human-Like Translation Strategy with Large Language Models is out.
Online talk on Multilingual Information Processing in the ChatGPT Era hosted by Harbin Institute of Technology.
Our preprint PARROT: Translating During Chat Using Large Language Models is out.
Our reproduced Alpaca-style LLaMA-7b model is pushed to HuggingFace model hub (wxjiao/alpaca-7b). Evaluation on translation data can also be found at alpaca-mt.
Our preliminary report concerning ChatGPT for GEC is out: ChatGPT or Grammarly? Evaluating ChatGPT on Grammatical Error Correction Benchmark (v1).
One paper about sign language translation accepted to EACL 2023. Congratulations to all the authors!
Our technical report concerning ChatGPT for MT is out: Is ChatGPT A Good Translator? A Preliminary Study/Yes With GPT-4 As The Engine.
Won Best Paper Award at the MRL Workshop at EMNLP 2022 for our paper Adapters for Enhanced Modeling of Multilingual Knowledge and Text.
One paper accepted to WMT 2022 for the competition. Congratulations to all the authors!
One paper accepted to EMNLP 2022 (Findings). Congratulations to all the authors!
Won 1st place at WMT2022 Large-Scale Machine Translation Evaluation for African Languages (Constrained Track) in terms of both automatic and human evaluation.
Wenxiang gave an industrial talk at NLPCC 2022.
One paper accepted to ACL 2022. Congratulations to all the authors!
One paper accepted to IEEE Transactions on Audio, Speech and Language Processing. Congratulations to all the authors!
Joined Tencent AI Lab as a Senior Researcher.
Won the Technology Innovation Award (top 10%) of 2020 Tencent AI Lab Rhino Bird Project!
Just passed my PhD oral defense. Many thanks to my supervisors and committees!
Wenxiang gave a research talk at AI TIME.