Hengli Li
@Hengli_Li_pku
AI PhD @PKU1898
Sorry, I deleted the previous post by accident, and this is a newly post one. BTW, what I want to say is: WE HAVE RELEASE THE CODE! check github.com/bigai-nlco/Lat…
🧐 Seek in the Dark 🤯No training🤯No data🤯No Reward Model LATENTSEEK: A novel framework that enhances LLM reasoning through Test-Time Instance-level Policy Gradient within the model’s latent space.
How will frontier AI systems reform the political collective decision-making process? 🚀 Excited to share our work EuroCon, a groundbreaking benchmark evaluating LLMs' ability to find political consensus in parliamentary settings. 1/N
🤩
Thrilled to share our new work, EORM- Energy Outcome Reward Model!💡 Tired of complex process supervision or RLHF? 👋 We introduce EORM, a lightweight verifier that works post-hoc— a simple add-on model that ranks generated Chain-of-Thought solutions. No LLM retraining required!