Skip to main content
Search

# Digital Twin

21 related articles

Subscribe to updates
  1. bioRxiv

    A digital twin of freely moving mouse V1 reproduces classic orientation and cell-type tuning when frozen and replayed with gratings

    Activity in mouse primary visual cortex (V1) during free movement can now be predicted by a multimodal digital twin from retinocentric video plus eye and head movements, locomotion speed and pupil diameter. Across 223 neurons from three mice the model reached a mean prediction correlation of 0.31; frozen and replayed with drifting gratings, it recovered canonical orientation, spatial-frequency and contrast tuning and the systematic differences between broad- and narrow-waveform cells, and without retraining it matched the population representational geometry of an independent head-fixed natural-movie dataset as closely as two recorded mice match each other.

  2. arXiv

    Vision-language models rewrite robot cost programs: 97.5% success on four tasks after five feedback rounds in simulation

    Contact-rich robot manipulation has relied either on end-to-end learned policies or on hand-engineered rewards and constraints for known scenes. Objectives as Policies has a pretrained vision-language model write an editable multi-stage cost program, which one shared sampling-based model-predictive controller executes in a digital twin and revises from execution statistics. Across four tabletop tasks, simulation cumulative success reached 90% with at most two feedback rounds and 97.5% with up to five; programs that succeeded in simulation then reached 80% success in the real world with perturbed object locations.

  3. arXiv

    Sewer digital twins stop retraining per pipe: the FLOOD operator predicts across unseen pipes and networks, about 5,500-fold faster on one pipe

    Sewer hydraulic digital twins have been limited by the cost of solving the Saint-Venant equations, while existing machine-learning surrogates need retraining for each new pipe or flow regime. FLOOD learns the solution operator of the Saint-Venant equations with a multi-branch neural operator, taking pipe geometry, hydraulic parameters and water levels at both manholes as inputs and returning depth and flow rate. On pipes excluded from training it reaches coefficients of determination of 1.000 for depth and 0.999 for flow rate, speeds up single-pipe online prediction by about 5,500-fold, and also serves roughness calibration and leakage localization.

  4. 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.

  5. NVIDIA's FOX blueprint puts a factory manager agent in charge of inspection, rework and root-cause agents

    NVIDIA released the Factory Operations Blueprint (FOX), a reference architecture that adds a factory manager agent to existing factory systems and has it coordinate specialist agents for inspection, root-cause analysis and fleet management. Previously, factory teams had to gather evidence across systems, consult specialists and coordinate the next step, which took substantial time and manual querying. FOX's SMT reference example follows an AOI alert through secondary inspection, rework transport in a digital twin and analysis of reflow oven readings, then returns a PDF report with source records and recommended actions.

  6. bioRxiv

    A fixed fly connectome learns to remember: the cue hides in neuronal adaptation and is read only in the brain state of learning

    A spiking model built from the complete central nervous system connectome of a male fly learns to plan moves and to remember a visual cue while its wiring stays fixed. The cue is not held by persistent firing but written into neuronal spike-frequency adaptation, kept silent through a blank delay and read out by the next input. Recall works only in the brain state of learning: the same trace is nearly reversed at an untrained delay, and a lesion mimicking the Kv4 loss caused by Aβ42 rewrites the trace and its reading, while learning under the lesion is spared.

  7. medRxiv

    Sepsis glucose digital twins stop waiting for error thresholds: a frozen PatchTST plus reinforcement-learning residual fix improved one-step forecasts in all 10 ICU patients

    Glucose digital twins in septic intensive care previously refit the model only after forecast error crossed a threshold, a reactive correction. This work reports a proactive workflow: a frozen PatchTST foundation model produces a one-step forecast, and an Actor–Critic reinforcement-learning agent uses the last 30-minute glucose window and recent residual history to apply a correction bounded at ±0.05 to that first step, which is then rolled out recursively over 15 steps. On minute-by-minute continuous glucose monitoring from 10 septic ICU patients, the pretrained agent lowered one-step forecast error in all 10 without patient-specific retraining, and mean absolute percentage error on the source patient's test set fell from 0.49% to 0.34%.

  8. medRxiv

    Compressing health records for causal analysis can drop a rare code, cutting mediation interval coverage to 2%

    Multimodal health records are often compressed into low-dimensional representations and used as adjustment sets, yet variational autoencoders are trained to reconstruct data rather than to preserve what causal identification needs. In simulations, a representation that discarded a rare code affecting both treatment and mediator gave 95% intervals for the interventional indirect effect with 2% coverage at n = 3,000 under moderate confounding, while reconstruction loss did not reveal the problem; a diagnostic comparing nuisance-function predictive loss flagged it in every replicate.

  9. Printed PLA gets a causal chain from clay exfoliation to layer bonding and voids, reaching 62.5 MPa at 2 wt.% clay

    Strength in fused-filament PLA parts modified with organo-modified montmorillonite depends jointly on clay exfoliation, melt rheology, interlayer thermal bonding and pore morphology, while earlier optimization mapped filler fraction and print parameters directly to mechanical properties. C³M-OMMT Twin chains clay exfoliation and rheology state, layer-by-layer thermal history, defect-interface graphs, causal mechanical response, Bayesian Pareto optimization and experimental validation. Across 0 to 5 wt.% clay and nozzle temperatures from 195 to 225 °C, its optimum is about 2 wt.% clay, 215 °C, 0.15 mm layer height and 35 mm/s, giving 62.5 MPa tensile strength, 94.1 MPa flexural strength and 2.18% void fraction.

  10. A generative ICU twin trained without task labels forecasts 13 endpoints at AUROC 0.83–0.98 and ranks first among 20 predictors

    A 123.5-million-parameter generative model, Didymos, was trained once without task labels on 409,297 intensive care stays from seven databases in five countries and answers prediction questions by sampling a patient's futures. On held-out stays it read 13 primary endpoints from those futures at AUROC 0.83–0.98 and ranked first on average among 20 predictors, including label-trained LightGBM and TabPFN-3.5. Its simulated treatment responses agreed with eight of nine observational contrasts, yet at two hospitals in Russia and China that contributed no training data it needed minutes of continued training on unlabelled local stays to match locally supervised models.