Skip to main content
Search

Michigan State University

6 related articles

Subscribe to updates
  1. arXiv

    Monocular 3D detection's depth formula carries a systematic bias: MonoPCA corrects it in closed form and lifts KITTI moderate AP to 20.55

    Monocular 3D detectors have long recovered depth by substituting the 2D box height into the projection relation, and MonoPCA shows this returns the distance to the visible front surface rather than the object center, with an error that grows with object size. It keeps the measurable 2D box height and restores center depth through an orientation- and size-aware closed-form correction, while a teacher-student distillation strengthens size and orientation prediction; on the KITTI test set it reaches 20.55 moderate AP, 1.44 above MonoCoP.

  2. arXiv

    Nine AI agents wrote 135 research follow-ups, and none cleared the domain scientists' bar on integrity, completeness and sufficiency

    Scientists at US Department of Energy national laboratories set the conditions an unpublished follow-up direction must meet, and nine frontier AI agents each wrote 15 follow-up papers, 135 in total. None passed all three checks of integrity, completeness and sufficiency, and 114 failed the integrity check, most often by claiming work that was never done or reporting numbers that contradict the recorded evidence. Agents readily produce papers that look like follow-ups, but none meets the standard the domain scientist set.

  3. arXiv

    Structured knowledge retrieval drops hand-written query-rule pairs: a routing agent and its retriever train in alternation

    Structured knowledge retrieval no longer needs predefined query-rule pairs: a routing agent picks a reasoning rule per query, its retriever ranks evidence under that rule's constraints, and the two train in alternation, each supervising the other.

  4. arXiv

    ASPIRE uses a behavior graph and dual explore-exploit experts to find agent prompt-injection vulnerabilities, reaching 54.1% attack success on AgentDojo

    ASPIRE is an open-ended prompt-injection red-teaming framework for LLM agents that maintains an evolving Agent Security Behavior Graph, uses complementary Explore and Exploit experts to propose consequence-centric test skeletons, has a separate realizer build concrete payloads and trigger queries, and updates the graph and cross-run strategy memory from trajectory evidence; on AgentDojo and AgentDyn it raises attack success to as high as 54.1% while covering more consequences, injection methods, environments, and behavior paths.

  5. Replacing full-Hessian supervision with random projected Hessian-vector products matches second-order accuracy while speeding each epoch by more than 24x

    The authors introduce Projected Hessian Learning (PHL), which supervises second-order curvature in machine-learning interatomic potentials (MLIPs) through stochastic Hutchinson-trace-based Hessian-vector product (HVP) projections instead of explicit Hessian construction; on a ωB97XD/6-31G(d) dataset of reactants, products, transition states, IRC and normal-mode-sampled geometries they compare four schemes (E-F, E-F-HVP with one-column or Hutchinson probes, and E-F-H), finding that with probe vectors resampled each minibatch both HVP methods are statistically indistinguishable from full-Hessian training in energy, force and Hessian accuracy while giving more than 24x speedup per epoch, and that under the more realistic fixed-vector regime with one HVP per molecule Hutchinson projections con

  6. bioRxiv

    An Open Field Phenomics Resource for Multimodal Maize Yield Prediction Across Divergent Environments

    This work releases curated 2020-2021 Genomes to Fields imagery from 356 drone flights across 19 environments covering 1,180 maize hybrids, and uses functional principal components of vegetation index and weather trajectories together with genomic information for yield prediction and QTL mapping, finding that combined genomic and phenomic kernels raised held-out hybrid prediction to r = 0.501 when environments were represented in training and 0.408 when environments were also withheld, that accumulated growing degree days offered no consistent advantage over days after planting, that weather contributed modest task-dependent gains, and that NGRDI functional principal components repeatedly mapped to quantitative trait loci on chromosomes 3 and 7.

You’re all caught up