UWaterloo's Yuntian Deng Open-Sources Implicit CoT, NeuralOS and More
yuntiandeng · x · 2026-09-16
UWaterloo assistant professor Yuntian Deng shares his lab's open-source work: Implicit Chain-of-Thought (internalizing reasoning into hidden computation — a 12-layer GPT-2 hits 99.5% accuracy multiplying two 20-digit numbers without emitting steps), NeuralOS for end-to-end neural simulation of computing environments, the ProgramAsWeights paradigm, plus his course and homepage.
His research focuses on internalizing explicit reasoning into implicit computation and studying real-world LLM usage at scale; WildChat was used by OpenAI's o1 and Anthropic's Claude 3 for safety evaluation, and his OpenNMT toolkit is widely adopted.
Related event: Yuntian Deng Open-Sources Program-as-Weights and NeuralOS Research(2 posts)→
More from Research
- Adobe & UCLA's Tev: verifiable progress rewards lift long-horizon agent Pass@5 from 0.17 to 0.28 — jiqizhixin · 2026-11-02
- Old trick still works: portal sampling cuts path-tracing noise dramatically at 64spp — ssh4net · 2026-11-02
- Marcel Böhme's paper asks why cybersecurity can never be solved, proposes vulnerability-guided hardening — mboehme_ · 2026-11-02
- Perplexity open-sources WANDR: 500 research tasks, 170,495 evidence points, URL-rechecking grader — thisguyknowsai · 2026-11-02
- AI researcher: we have no reliable way to tell whether an AI system is conscious — dioscuri · 2026-11-02
- Ant Group's Venus-DefakerOne2 hits 96% accuracy detecting AI-generated videos — inclusionAI · 2026-11-02