Yu Yang
@YuYang_i
reasoning research @OpenAI 🍓 | UCLA CS PhD (‘21-‘24) | Ex. Microsoft Research (AI Frontiers), Meta (FAIR), NVIDIA Research (LPR)
Finally out! 🎉 Are AI coding assistants like @cursor_ai, @GitHubCopilot, @codeiumdev, and @QodoAI helping you write secure code—or adding risks? With SecCodePLT, a platform for #codegen security from our recent research, we assessed insecure coding risks. Check out our blog! 😊
AI coding assistants (e.g. @cursor_ai, @codeiumdev , @github Copilot) are transforming software development—but how secure are they? Our new blog post reveals which tools stand up to security best practices, which introduce hidden vulnerabilities, and what you can do to…
1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).
we trained a new model that is good at creative writing (not sure yet how/when it will get released). this is the first time i have been really struck by something written by AI; it got the vibe of metafiction so right. PROMPT: Please write a metafictional literary short story…
We released *DuoGuard*, a 0.5B multilingual guardrail model! Its two-player RL framework adversarially co-evolves a generator and classifier to generate safety data. DuoGuard offers fine-grained probabilities across 12 subcategories with customizable thresholds. Check it out! 🥳
New paper & model release! Excited to introduce DuoGuard: A Two-Player RL-Driven Framework for Multilingual LLM Guardrails, showcasing our new DuoGuard-0.5B model. - Model: huggingface.co/DuoGuard/DuoGu… - Paper: arxiv.org/abs/2502.05163 - GitHub: github.com/yihedeng9/DuoG… Grounded in a…
Mitigating racial bias from LLMs is a lot easier than removing it from humans! Can’t believe this happened at the best AI conference @NeurIPSConf We have ethical reviews for authors, but missed it for invited speakers? 😡
I’ll help presenting our #NeurIPS2024 posters tomorrow (Friday):🌱 1- Changing the training data distribution to improve in-distribution performance (11@west #7106) w. @dangnth97 2- Data selection for fine-tuning LLMs with superior performance (16:30@west #5401) w. @YUYANG_UCLA
Smaller high-quality subsets of language data not only improve LLMs’ training efficiency, but also yield considerably better performance! 🙌🎉🌱 @YUYANG_UCLA has a theoretically-rigorous method for this in her #NeurIPS2024 paper! Check it out on Fri, Dec 13, 16:30, #PS 6
1/ I'll be at #NeurIPS2024 presenting our work SmallToLarge (S2L): Data-efficient Fine-tuning of LLMs! 🚀 What’s S2L? It’s a scalable data selection method that trains a small proxy model to guide fine-tuning for larger models, reducing costs while preserving performance. 👇
We'll be at @NeurIPSConf next week in Vancouver! Stop by Booth #44 to: - Play our Jailbreak Game – test your skills for exciting prizes! - Hear talks from our AI researchers Dawn Song (@dawnsongtweets), Bo Li (@uiuc_aisecure), Sanmi Koyejo (@sanmikoyejo), Yu Yang (@YUYANG_UCLA)…