Yingyu Lin

Excited to share that our recent work DivSkill-SQL is now ranked #1 on the official Spider2-Lite leaderboard🎉 Text-to-SQL agent ensembling, which generates multiple SQL candidates, then selects the best one, has been shown to be effective.

How does **Property Inference attacks** look on an LLM? 🤔 Our new work **PropInfer** reveals a previously unrecognized training data confidentiality risk in LLMs! 🚨 We show how attackers can successfully infer confidential, *dataset-level* properties (like patient demographics) of fine-tuning dataset. We do this by: —Introducing the first benchmark task for Property inference in LLM —Proposing two tailored attacks targeting LLM Come check out our spotlight paper "Can We Infer Confidential Properties of Training Data from LLMs?" at #NeurIPS2025 during Thur, 4 Dec 4:30 p.m. PST — 7:30 p.m. PST Exhibit Hall C,D,E #1313 📍 @chhaviyadav_ @kamalikac @ruihan_w

🚀 We just set a new SOTA for LLM inference acceleration with speculative decoding. By corralling a band of specialist drafters, we got 4.99× on Llama-3.1-8B-Instruct, 4.93× on Qwen-32B — beating EAGLE3 by nearly 2x. No gimmicks. Just careful math + solid engineering. 🧵1/

🔥Introducing Pandora 🌏 🪐 a World Model that generates videos of world states with real-time language control 🎥🕹️ Simulate the world across domains in an _interactive_ way! check out more world-model.ai