news
Announcements and updates.
| Nov 8, 2026 | Same logic, different words: our NeurIPS 2026 paper on why LLMs contradict themselves |
|---|---|
| Nov 7, 2026 | Faster AI teams: our NeurIPS 2026 paper on latency-aware multi-agent workflows |
| Nov 6, 2026 | When generative AI is guessing: our AISTATS 2026 paper on epistemic uncertainty in diffusion models |
| Nov 5, 2026 | Seminar talk at Chicago Booth: "What Makes an RL Sample Transferable?" |
| Sep 30, 2026 | Seminar talks at Penn State, Stanford, and Berkeley: "What Makes an RL Sample Transferable?" |
| Jul 16, 2026 | Presenting on dual-channel tensor neural networks at JSM 2026 |
| Jul 16, 2026 | Organizing two sessions at JSM 2026 in Boston |
| Jul 15, 2026 | I will give a short course on Introduction to Reinforcement Learning at the Deep Learning for Science School (DL4Sci), July 20-24, at Lawrence Berkeley National Laboratory. The tutorial materials are available under courses. |