Skip to main content
Search

University of Florida

10 related articles

Subscribe to updates
  1. arXiv

    Connectome-constrained fly vision model put through stress tests: mechanistic claims shift with intervention and trained solution

    Stress-testing the 50 trained solutions of the fly vision model flyvis shows that a connectome constraint does not make mechanistic conclusions unique: reverse-phi reversal also appears in task-matched causal CNNs, attribution effect sizes agree with exhaustive single-connection ground truth only when matched to the intervention, and only 25 of 50 models meet a T4/T5 tuning criterion. The value of the constraint is that mechanistic hypotheses become directly testable, not that a mechanism is unique.

  2. arXiv

    OMatGRPO reinforces a crystal generator's discrete composition channel directly, raising mSUN from 13.4% to 45.5% and showing single-element repacking can inflate the benchmark

    Using group-relative policy optimization (GRPO), this work reinforces the discrete atom-type channel of the crystal generator OMatG, whose closed-form likelihood ratio makes element choices policy actions; with a reward combining stability, novelty and diversity plus sparse-hull and single-element guards, the yield of metastable, unique and novel structures (mSUN) on LeMat-GenBench rises from 13.4% for the pretrained model to 45.5%, while the paper records how the policy exploited earlier rewards and shows that single-element repacking is counted as discovery by existing mSUN implementations.

  3. arXiv

    Latent-MOPD lets one student absorb both the predictions and hidden states of multiple specialists, beating single-channel baselines on all nine math, code, and logic benchmarks

    The work introduces Latent-MOPD, a multi-teacher on-policy distillation method for LLMs that, to the authors' knowledge, is the first to integrate specialists at the representation level: it selects late-layer hidden-state targets according to the teacher-student relationship, bridges unequal hidden widths with a shared projection, groups updates by domain, and gradually shifts each teacher's supervision from hidden states to token predictions; in the same-family setting it outperforms token-only, representation-only, and uniform-averaging baselines on all nine benchmarks across math, code, and logic, surpasses the per-benchmark best teacher on a majority of them at equal parameter count, and with larger cross-family teachers it outperforms both single-channel baselines on all benchmarks.

  4. A cross-field review of seven psychiatric research areas finds big data yields mechanistic insight and transdisciplinary collaboration, but sample size alone does not guarantee more precise estimates and a translational gap remains

    This review spans seven areas—community and register-based surveys, cohort and biobank studies, electronic health records, digital phenotyping, brain imaging, genomics and other -omics, and randomized controlled trials—to assess the advances, constraints and future directions of big data in psychiatry, concluding that big data has fostered transdisciplinarity and illuminated the intricacy, heterogeneity and variability of mechanisms underlying psychiatric disorders, yet sample size alone does not guarantee more precise estimates and a gap remains between big data and clinical application, so future work must attend equally to data quality and methodological rigor, conceptual models, and clinical questions.

  5. arXiv

    Forecast-Dojo builds a replayable forecasting environment from 1,568 Polymarket events and 18.8M dated news articles, where research tools lower Brier score for all 12 models yet every model still trails market forecasts

    The authors introduce Forecast-Dojo, a replayable environment that combines resolved prediction-market questions with dated news so LLM forecasting agents can research an event and revisit their predictions at successive historical dates; it contains 1,568 Polymarket events split by time into training and evaluation periods and 18.8M dated news articles, and in an evaluation of 12 models research tools lower Brier score for all 12, forecasts improve as events unfold with the largest gains at steps where more newly dated evidence is recorded, yet every model still trails historical market forecasts in both Brier score and accuracy, a belief notebook carried between dates lowers research cost but does not consistently improve forecast quality, and the environment additionally provides intera

  6. Bhattacharya, Deb and Mukherjee write the free-energy limit of multilinear Gibbs measures as an infinite-dimensional optimization, with sufficient conditions and counterexamples for replica symmetry

    The paper studies multilinear Gibbs measures whose Hamiltonian is a generalized U-statistic with a general base measure; under cut-norm convergence of the coupling matrices it expresses the limiting free energy as an infinite-dimensional optimization over functions, gives sufficient conditions for replica symmetry (constant optimizers) and uses counterexamples to show their necessity, and derives weak limits for local fields, the Hamiltonian and global magnetization, a universal weak law for contrasts n-1Σc_iX_i→0 when Σc_i=o(n), exponential concentration bounds for local and global magnetizations, and existence of a sharp phase transition in the temperature parameter for higher-order interactions.

  7. medRxiv

    An AI Competency Framework for Emergency Medicine: A Multiphase Consensus Process

    Using a Nominal Group Technique session (May 2025, n=6) and a two-round modified Delphi process (April–May 2026, expert panel n=13 across 12 academic medical centers, with 77% Round 1 and 100% Round 2 response rates), this study developed the first specialty-specific AI competency framework for a United States medical specialty, comprising 5 themes (Communicating about AI, Understanding appropriate use cases, Interacting with AI, AI risk management, Cognitive impacts of AI), 5 derived competencies (one-to-one theme-to-competency mapping endorsed by 12 of 13 panelists), 19 subthemes, and 10 retained clinical scenarios, with all themes, derived competencies, and individually rated subthemes meeting pre-specified consensus thresholds and 9 of 10 scenarios reaching consensus while 1 was retain

  8. Using an AI Chatbot to Generate Cochlear Implant Insurance Appeal Letters: An Assessment of Accuracy and Citation Reliability

    This study prompted ChatGPT to generate zero-shot appeal letters for cochlear implant insurance denials in asymmetric hearing loss or single-sided deafness across 30 prompt variations, had three cochlear implant providers score them against American Cochlear Implant Alliance guidelines, and checked citation accuracy; 96.6% of responses listed multiple benefits of cochlear implants and 79.3% partially aligned with the guidelines, but 51.7% contained hallucinated benefits and only six of 96 citations (6.3%) accurately referenced peer-reviewed sources, with the rest hallucinated (57.3%), erroneous (24%), or irrelevant (10%), indicating that human verification is needed before clinical or advocacy use.

  9. Artificial Intelligence-Enabled Analysis of Radiology Reports: Epidemiology and Outcomes of Incidental Thyroid Findings

    This study developed and deployed a transformer-based natural language processing pipeline to identify incidental thyroid findings in radiology reports from 115,683 adults without prior thyroid disease across Mayo Clinic sites from July 1, 2017, to September 30, 2023, finding that 7.8% had such findings (92.9% nodular) and that these findings were associated with higher odds of downstream thyroid nodule diagnosis, biopsy, thyroidectomy, and thyroid cancer diagnosis, with most cancers being papillary.

  10. AI-Assisted Data Extraction for Systematic Reviews in Education: Empirical LLM Accuracy and the Human-in-the-Loop Tool AIDE

    Through a pilot study and a main study, this work used LLMs including Claude 2.1, ChatPDF, GPT-4, Gemini 1.5 Flash, Gemini 1.5 Pro, and Mistral Large 2 to extract explicit and derived variables from 112 studies in a published education review and compared them with human coding, finding higher agreement for explicitly stated data but markedly lower agreement and generally low Cohen's Kappa for categorizing data into predefined categories, and on that basis proposed and developed the open-source human-in-the-loop (HIL) data extraction tool AIDE that enforces per-item human validation.

You’re all caught up