University of Maryland

Headlines · 4

1. Nov 2
   Epi2Diff predicts human item difficulty from LLM reasoning traces

   Researchers from Virginia Tech, the University of Maryland, MBZUAI and the University of Pittsburgh proposed Epi2Diff, a framework that splits LLM reasoning traces into cognitive episodes and combines them with item content to predict human difficulty. The research team reported first-place results across the main metrics for SAT Mathematics, SAT Reading and Writing, Cambridge and USMLE, with SAT Mathematics accuracy reaching 73.0%. Its paper was accepted by Transactions on Machine Learning Research.

   36氪 人工智能 · 🔥 0
2. Oct 20
   Gemini 4 Argon agents extend fusion magnetic-confinement math

   Google's Gemini 4 Argon, run through the Antigravity environment, helped researchers extend mathematical solutions tied to the magnetic fields inside experimental fusion reactors. The study by Opal Issan, Jonathan Citrin, Matt Landreman and Brendan Tracey builds on exact solutions Landreman published in September 2026 with help from OpenAI's GPT-6 Astra Pro, adding a parameter that breaks their shared geometric symmetry to give researchers more exact reference cases for checking magnetic-equilibrium software. Promising candidates reportedly emerged within hours, but the authors still had to verify the derivations; the article states this is not a fusion-energy or commercial-viability breakthrough, and its headline framing that a 59-year-old conjecture was "shattered" overstates the result.

   TechRadar · 🔥 0
3. Oct 15
   DeepMind and partners unveil IdeaLens, a detector for AI-generated research ideas

   Researchers from the University of Maryland, Google DeepMind and Simon Fraser University have posted an arXiv preprint, IdeaLens: Detecting AI Ideas in Long-form Writing, describing a detector that converts an article into an outline and judges idea provenance rather than prose style. The team trained on about one million English long-form texts using Pangram 3.3.2 labels, fine-tuned Nvidia's Nemotron-3.5-Lightning-30B-A3B with LoRA, and built a prose-reading control model called ProseLens. In the authors' reported tests, IdeaLens flagged 6.8% of articles as AI when AI wrote from a complete human outline, down from 94.9% with only a topic prompt; when humans rewrote stories from AI-generated outlines, it judged 68% as AI versus 8% for Pangram 4. The authors caution that training labels came from an existing detector, the TwiceTold set had only 50 human rewrites, and the system cannot yet apportion credit in multi-turn human-AI co-creation.

   MIT科技评论中文 · 🔥 0
4. Oct 8
   GPT-6 Astra finds exact plasma equilibria, overturning 59-year-old Grad conjecture

   University of Maryland plasma physicist Matt Landreman prompted GPT-6 Astra Pro to design an asymmetric three-dimensional plasma equilibrium; the model returned a family of exact analytic solutions in 20 minutes 34 seconds and, the next day, after a failed first attempt plus a proof that the first construction could not yield a non-integer rotational transform, produced a second family with magnetic shear in 33 minutes 37 seconds. Two arXiv papers published a day apart in late September overturn Harold Grad's 1967 conjecture: Landreman's paper credits GPT-6 Astra Pro in its acknowledgements, says parts were drafted by it, and publishes the prompts and verification scripts. A separate 147-page paper, "Counterexamples to the Grad conjecture," from Brown, Oxford and Bar-Ilan researchers used GPT-5.6 Sol, Claude Fable 5 and Claude Opus 5 for technical detail and computation, and ships a Lean 4 formalisation.

   36氪 人工智能 · 🔥 0

Experience and discussion from the community

Share my University of Maryland experienceAsk about University of Maryland