Zhenhao Li @ ACL25✈️
@ZhenhaoLi1
PhD student at @imperialcollege; Research Engineer at @EpicGames. Multi-agent, code generation, text moderation, NLP robustness
I’ll be at #acl2025 next week in Vienna🇦🇹 presenting our work. Looking forward to meeting old and new friends! If you like to discuss chatbot, code generation, multi-agents, robustness, hate speech detection, or just life😆, feel free to reach out and I’d love to chat!
🙌Happy to share our paper, “DiffuseDef: Improved Robustness to Adversarial Attacks via Iterative Denoising” is accepted to #ACL2025! Great thanks to my co-authors Huichi Zhou, @MarekRei, @lspecia! Arxiv: arxiv.org/abs/2407.00248 GitHub: github.com/Nickeilf/Diffu…
ACL is almost here 🎉 Our Imperial NLP community will be presenting several papers at the conference next week. We look forward to seeing everyone in Vienna!
We have a new paper up on arXiv! 🥳🪇 The paper tries to improve the robustness of closed-source LLMs fine-tuned on NLI, assuming a realistic training budget of 10k training examples. Here's a 60 second rundown of what we found!
Here's my insanely powerful Claude 3.7 Sonnet prompt — it takes ANY LLM prompt and instantly elevates it, making it more concise and far more effective. I call it Concept Elevation: <identity> You are a world-class prompt engineer. When given a prompt to improve, you have an…
My Anthropic account is banned for the violating usage policy, but I’ve never used it in recent 6 months. Submitted an appeal but received a rejection. I’ve been using ChatGPT since start but want to try Claude for coding. Unfortunately, Claude doesn’t like me. #Claude #ChatGPT
Today I tried to run some analysis for my thesis and opened a library that I used few years ago. It uses tensorflow 1 and now I have completely no idea how to fix bug with tf anymore. The community has developed so fast and it’s a great fortune to have huggingface🥹🥹
We are hiring 6 lecturers at @imperialcollege, to work on AI, ML, graphics, vision, quantum and software engineering. This includes researchers working on LLMs, #NLProc, generative models and text applications. Deadline 6 Jan. @ICComputing @imperial_nlp imperial.ac.uk/jobs/search-jo…
It is just so sad that the #NeurIPS2024 main conference ended with such a racist remark by a faculty when talking about ethics. How ironic! I also want to commend the Chinese student who spoke up right on spot. She was respectful, decent, and courageous. Her response was…
The video chat feature looks pretty cool, especially after the service outage and the apple intelligence integration yesterday. I can already think of some cool thoughts around it (like teaching me to cook or understanding what my dog is doing).
Just in time for the holidays, video and screensharing are now starting to roll out in Advanced Voice in the ChatGPT mobile app.
We have received many requests for slides and recordings for the language agent tutorial, and have been working hard on the release. The slides are now available! tinyurl.com/language-agent… We are still working on releasing the recording. The tutorial website will be the one-stop…
We have started the language agent tutorial!
Checkout our latest preprint on 🦎 → 🐍 NL-Augmenter, a large scale participative framework to compile task-sensitive natural language augmentations! arxiv.org/pdf/2112.02721… 1/n
Happy to share that our paper "Visual Cues and Error Correction for Translation Robustness" is accepted at #EMNLP2021 findings. Great thanks to @MarekRei and @lspecia. arXiv preprint coming soon.
CALL FOR Natural Language TRANSFORMATIONs🦎→🐍 At GEM💎 we are soliciting contributions of #NLProc transformations to a *collaborative* framework designed for data augmentation & evaluating robustness Submit a transformation for any #NLP task -> github.com/GEM-benchmark/… 🧵1/n