Skip to main content
Search

Vanderbilt University

10 related articles

Subscribe to updates
  1. arXiv

    Neural reachability now errs on the safe side: ConDR pushes the learned value below the true one and gives the lowest closed-loop collision rates

    DeepReach replaces the grid in Hamilton–Jacobi reachability with a neural value function but penalizes both sides of the residual equally, so the learned value can sit above the true one and unsafe states get labeled safe. ConDR instead trains toward a subsolution of the HJI variational inequality: the obstacle branch and terminal condition hold by construction, a one-sided loss pushes the differential residual below a safety margin, and a complementarity term blocks the degenerate all-unsafe solution. On Air3D, Air6D, a 9D multi-vehicle system and a 13D quadrotor, ConDR reports the lowest false-negative rate and the lowest closed-loop collision rates, with at most a small rise in intervention.

  2. arXiv

    Researchers introduce mathematical primitives and a four-dimension benchmark, identify Discovery as the dominant bottleneck in LLM mathematical reasoning, and improve reasoning with a primitive-privileged self-distillation framework

    The work introduces the notion of Mathematical Primitive and a benchmark that evaluates mathematical reasoning along four dimensions—Discovery, Generation, Digestion, and Execution—and a systematic diagnosis shows that solution accuracy masks distinct capability profiles, that primitives unlock substantial latent execution capacity, and that Discovery is the dominant bottleneck; building on the finding that discovery-limited failures are particularly amenable to repair, it proposes a primitive-privileged self-distillation framework that selectively transfers primitive-guided reasoning into the student model and consistently improves mathematical reasoning over baselines across model scales and challenging benchmarks.

  3. arXiv

    CogAdapt uses human EEG and gaze to pick which code-model blocks to adapt, gaining 10.86 points on LiveCodeBench over all-block fine-tuning while cutting about 87% of gradient-eligible adaptation parameters

    CogAdapt derives program-level and token-level priors from human EEG and eye-tracking data recorded during code reading, combines them with a frozen MoE model's response to each coding task to dynamically select a small set of transformer blocks for sparse fine-tuning, and reports consistent correspondence between human reading behavior and MoE computation across Qwen and GLM, best pass@1 on LiveCodeBench and BigCodeBench, gains of 10.86 and 6.29 percentage points over matched regular all-block fine-tuning on LiveCodeBench, and an 86.21–87.21% reduction in gradient-eligible adaptation parameters.

  4. arXiv

    PAC-Private Diffusion Adaptation Perturbs the Learned Component Once, Beating DP-SGD on Subject Identity and Generation Quality at Equal Reconstruction Privacy

    The work proposes a PAC-private diffusion model adaptation that first learns a compact data-dependent component via LoRA or Textual Inversion and then calibrates anisotropic Gaussian noise from the covariance of repeated mechanism outputs, perturbing the learned component only once after optimization to avoid privacy composition across gradient updates; on few-shot concept personalization and full-dataset image synthesis it better preserves subject identity, generation quality, and downstream classification accuracy than DP while achieving the same reconstruction privacy.

  5. arXiv

    Prompt2Skill builds skills automatically from a single natural-language task description, averaging a 36.1% relative gain across four benchmarks and five models

    Prompt2Skill is a multi-agent framework that, from a natural-language task description alone, has a Data Agent derive a task specification and build a proxy data pool through retrieval, adaptation, and synthesis, and a Skill Agent refine the skill in a closed loop of execution feedback, reflective editing, and paired statistical screening, improving over direct prompting by 36.1% and over off-the-shelf skills by 83.0% on average across question answering, reading comprehension, spreadsheet manipulation, and mathematical reasoning with five open-source and commercial target models, without significant regressions.

  6. arXiv

    A survey unifies joint, cross-modal and joint-editing video-audio generation on one distribution and gives the first systematic taxonomy of joint audio-visual editing: nine categories, 28 edit types

    Observing that video and audio are perceived together yet most generative models treat them in isolation, this survey casts joint generation, cross-modal generation (one modality from the other) and joint editing as three problems defined on a single distribution over audio-visual pairs, organizes the field around one question—how the output is kept coherent across modalities in time and semantics—proposes a taxonomy along five design axes (generation strategy, audio representation, video representation, alignment enforcement, pretraining reuse), and, to the authors' knowledge, provides the first systematic taxonomy of joint audio-visual editing, mapped as nine edit categories spanning 28 edit types, together with methods, datasets and metrics for each setting and a closing list of open pr

  7. arXiv

    IntraStyler uses a contrastively trained style encoder to synthesize T2 MRI styles without predefined sub-domains, raising Extra-VS Dice from 0.61 to 0.81 with zero failures on CrossMoDA

    The work proposes IntraStyler, a 3D unpaired image translation method that requires no predefined sub-domains, using a contrastively trained style encoder to extract anatomy-disentangled style embeddings from each target-domain image and conditioning a QS-Attn synthesis network via dynamic instance normalization; on the CrossMoDA benchmark (226 labeled ceT1, 295 unlabeled T2, 96-image T2 test set) it automatically discovers 7 style references instead of the 3 used by sub-domain methods, and downstream nnU-Net segmentation achieves the best Dice and ASSD on Intra-VS, Extra-VS, and Cochlea, with Extra-VS Dice of 0.81 and zero failures.

  8. Harnessing Generative Artificial Intelligence and a Persona Prompt to Develop Competence in Addressing Social Determinants of Health

    A family nurse practitioner (FNP) program had 98 students use a generative AI persona prompt in Claude Sonnet to create a virtual patient on a video-conferencing platform, and after a 30-minute prebriefing, about 75 minutes of scenario work, and a 45-minute PEARLS-based debriefing, the most common one-word reaction was “helpful” (n = 83), 95% said the activity facilitated their learning about SDOH (n = 82), 78% chose the two highest comfort levels for screening for and addressing SDOH (average 4.1/5), the SDOH quiz average was 94% (n = 98), and 54% answered the question on specific strategies to address SDOH correctly.

  9. FEBS Letters

    Prospecting the Protein Design Landscape: From High-Affinity Binders to Functionally Switchable Proteins

    This review surveys the landscape of deep learning-driven protein design pipelines, discusses tailored applications in peptide, small molecule, binder, vaccine, and antibody design, argues that current confidence metrics for filtering and evaluating designs remain optimized for static protein interfaces and can fail on underrepresented or conformationally complex targets, proposes ensemble-based methods as a promising avenue for improving design success rates, and highlights emerging strategies such as fold-switching scaffolds and molecular glues realized through engineered cyclic peptides that expand the functional scope of designed proteins.

  10. Infectious risks of transfusion: a 10-year look back and perspectives

    This review reflects on how infectious diseases shaped transfusion services from 2016 to 2026, covering innovations in donor selection, testing and pathogen reduction, notable pathogens including Zika virus, Plasmodium, Babesia and SARS-CoV-2, and favorable developments such as individualized risk assessment, relaxation of donor deferral policies, and AI and machine learning tools for surveillance and horizon scanning, while noting that many of these gains do not extend to low and low-middle income countries.

You’re all caught up