Skip to main content
Search

Stanford University

77 related articles

Subscribe to updates
  1. bioRxiv

    Cryo-FIB-SEM volumes stop drowning in charging artifacts: a two-stage restoration lets a standard FIB-SEM membrane predictor read them directly

    Cryo focused-ion-beam scanning electron microscopy images cells in a near-native hydrated state in 3D, but charging artifacts, noise and weak membrane contrast have long hampered interpretation. A post-acquisition two-stage deep-learning pipeline translates cryo images toward the conventional room-temperature FIB-SEM domain: stage one suppresses large-scale artifacts slice by slice, and stage two uses five consecutive slices to enhance membrane contrast. On 164 held-out synthetic images, stage one raised mean paired PSNR by 16.74 dB over degraded inputs; across four experimental datasets, visible artifacts decreased and membranes became clearer, and the pretrained CebraNET membrane predictor could be applied directly to the processed volumes without retraining.

  2. eLife

    Visual cortex neurons do more than fire harder: in macaque V1 and V4, a second feature pushes activity below baseline

    Many neurons in macaque V1 and V4 do not merely raise firing for a preferred stimulus; they are excited by one visual feature and suppressed by a distinct one around an elevated baseline. Using functional digital twins, deep networks trained on recorded responses that predict how a neuron will answer new images, researchers identified each neuron's most and least activating images across more than a million natural images, and confirmed that these images sit at the extremes of recorded responses and hold up under independent models. The same bidirectional selectivity appears in mouse V1 and lateral visual areas.

  3. arXiv

    Where semantic priors should enter causal discovery: orientation gains hold, but query placement and admission certificates do not yet

    Observational data often leave causal directions unresolved or unstable, and large language models can propose directions from variable names and descriptions. This study splits the use of semantic information into query allocation, proposal admission and graph retention, and tests each on the Asia, Sachs, Child, Insurance and Alarm benchmark networks. Semantic orientation beats coin-flip orientation, but targeting unstable edges shows no established advantage over matched-random allocation; the tested admission certificate can only abstain given the available calibration tasks, and learned references contain the true DAG in only three of 80 planned tasks.

  4. Spectral bias lives in the training kernel, not the wavenumber basis: dense operator learners spread error almost evenly across modes

    Training five operator models on the one-dimensional discrete Poisson problem shows that error is not learned wavenumber by wavenumber but is retained along small-eigenvalue directions of the kernel that governs the training update. Sine-aligned spectral and linear Fourier neural operators give each wavenumber its own rate, so error collects at high wavenumbers; dense networks have eigendirections close to random in the sine basis, so error is nearly equal at every wavenumber and relative error grows only because the true solution spectrum decays. Removing the minibatch cross terms leaves the GELU dense network with under 0.1% of squared error below ηλ≈8×10⁻⁵ under either forcing.

  5. arXiv

    Structural surrogates learn modal quantities instead of curves: tower displacement error 0.73–0.76%, beam 0.029–0.116%

    Neural surrogates for structural dynamic response no longer fit the whole frequency-response curve directly; they first predict frequency-independent modal quantities and then reconstruct the response by analytical modal superposition. Across 20,000 designs each for a steel truss tower and a tapered beam, with supplied modal frequencies, 5% reference damping and a declared band, the modal configurations give mean displacement-history errors of 0.73–0.76% and 0.029–0.116% respectively. These figures cover fixed topology and conditional inference, and do not yet establish design-only deployment or an earthquake-engineering assessment.

  6. arXiv

    Two-view covariances no longer learned as one blob: CANE separates in-view and cross-view structure and cuts brain-age error to 4.97 years

    In two-view data, each view has its own covariance and a cross-view covariance links them, yet covariance neural networks handled only single-view data and could not distinguish these structures once the views were concatenated. CANE splits the model into an in-view covariance filtering stage and a cross-view covariance filtering stage, replacing the whitening and singular-vector selection of canonical correlation analysis with learnable polynomial responses on the covariance spectrum, and trains directly on the downstream task. Across seven brain-imaging and motion-sensing datasets, CANE is best or tied for best on six, reaching a mean absolute error of 4.97 years for age prediction on ADNI1, often with fewer parameters than a two-view VNN.

  7. arXiv

    Agnostic learning and multiaccuracy proved equivalent: one multiaccuracy oracle, queried adaptively, reaches the best discriminator

    For a fixed feature distribution and an arbitrary model class, agnostic learning (training a discriminator that matches the best member of the class) and multiaccuracy (training a generator whose labels no observer in the class can distinguish from real ones) are proved equivalent in statistical and computational complexity. Only the direction from agnostic learning to multiaccuracy was known; the converse was blocked because a single multiaccurate predictor can fail to beat random guessing even after calibration. The new reduction repeatedly queries a multiaccuracy oracle, splits by prediction level sets and averages the iterates, yielding a predictor that is both multiaccurate and calibrated and thus performs agnostic learning.

  8. arXiv

    Subsurface flow data assimilation gets adaptive-tempered sequential Monte Carlo: posteriors match reference MCMC on four synthetic truths, with 2.5–7.0× single-GPU speedups

    Geological uncertainty in subsurface flow systems is often hierarchical: a set of geological metaparameters controls overall statistics while cell-by-cell property fields vary, and both must be estimated from observations. An adaptive-tempered sequential Monte Carlo method estimates metaparameters and Gaussian latent variables jointly within one likelihood framework, with surrogate models supplying all forward evaluations. Across four synthetic true models, its posterior metaparameter distributions and flow predictions agree closely with reference MCMC results, while single-GPU data assimilation is 2.5–7.0 times faster and needs fewer function evaluations.

  9. 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.

  10. arXiv

    Agents learn to think in latent space: HybridAgent gains 10.4% on average across 11 benchmarks while cutting tokens by up to 54.7%

    HybridAgent lets a single agent move back and forth between continuous latent reasoning and text interaction within one generation, so part of its thinking leaves token-by-token decoding while tool use stays intact. Text agents previously had to write every step as tokens, while latent-reasoning models lacked native tool access and were hard to inspect. Across 11 benchmarks in mathematics, science, medicine, search and agentic reasoning at 4B to 14B scale, it reports a 10.4% average gain over frontier text and latent agents, with 35.5%–54.7% fewer tokens and 1.8–2.6 times faster inference.