Etha Tianze Hua

🤔Ever wonder why LLMs give inconsistent answers in different languages? In our paper, we identify two failure points in the multilingual factual recall process and propose fixes that guide LLMs to the "right path." This can boost performance by 35% in the weakest language! 📈

Wondering how long it takes to train a 1B-param LM from scratch on your GPUs? 🧵 See our paper to learn about the current state of academic compute and how to efficiently train models! Use our code to test your own models/GPUs! arxiv.org/abs/2410.23261 github.com/apoorvkh/acade…

🧙‍♂️ Does all of a transformer's magic come from training? In our NeurIPS 2024 paper, we discovered that for many tasks, merely training the embedding and unembedding layers of transformers yields surprisingly strong performance! A thread 🧵

We will be presenting our pister tomorrow at NAACL poster session 7 at 11am! If you are interested, feel free to come by and chat!

Excited to share our work mOthello: When Do Cross-Lingual Representation Alignment and Cross-Lingual Transfer Emerge in Multilingual Models? accepted at #NAACL2024 with @EthaHua @Brown_NLP Paper: arxiv.org/abs/2404.12444 Code: github.com/ethahtz/multil… Webpage:…

Research Associate @tsgouros and @BrownCSDept students are using sound and AI to make @NASA imagery accessible to people with vision impairments. Learn more at Brown CS Blog: go.brown.edu/SgourosNASAAcc…

8 yrs ago I discovered synthetic biology and immediately knew my life as an architect would never be the same again—obsession w/ creating self-constructing architectures by design culminated in my PhD work #anthrobots advised by visionary @drmichaellevin gizemgumuskaya.com/selected_works…