Skip to main content
Search

Centre National de la Recherche Scientifique

28 related articles

Subscribe to updates
  1. arXiv

    Recurrent state estimation gets a convergence guarantee: one gain drives the error exponentially into any small neighborhood

    Recurrent models for state estimation previously had empirical success but no formal convergence or robustness guarantees. This work treats a recurrent network as a discretization of continuous latent dynamics and requires the latent flow to contract, proving that a smooth injective map embeds the true physical state into latent space; raising a single scalar gain κ drives the estimation error exponentially fast into an arbitrarily small neighborhood of zero, at the cost of decoder capacity growing polynomially in κ. On a real mobile-robot pose-estimation task, the provably contracting model outperforms a vanilla GRU and trains more stably.

  2. arXiv

    Discrete diffusion need not pay for vocabulary size: masked and uniform noising both hit minimax rates on sparse data

    Discrete diffusion models have lacked the statistical theory that continuous diffusion enjoys, and it was unclear whether they can exploit sparse structure in the data distribution. This analysis casts masked-diffusion score estimation as a per-context label-smoothed classifier and shows the smoothing is equivalent to regularizing with the score loss of the uniform distribution. On sparse distributions where at most k sequences have positive probability, the terminal laws of both masked and uniform noising attain the sparse minimax rate, and the smoothing level can be chosen adaptively from the number of distinct training sequences without knowing the sparsity parameter.

  3. bioRxiv

    Fox skips tree building for host-symbiont coevolution: reading paired alignments directly, it runs over three orders of magnitude faster than an ABC baseline

    Estimating the frequencies of host-symbiont coevolution events used to require reconstructing a host tree and then reconciling the symbiont tree against it, so tree-inference error propagated into the result. Fox instead uses a transformer to output the relative frequencies of cospeciation, host switching, loss and duplication directly from the host and symbiont multiple sequence alignments and their mapping, paying the simulation cost once at training time and processing each new system in a single forward pass. On the independent simulator treeducken, Fox reached a mean absolute error of 0.060 on the 92 datasets AmoCoala completed, against 0.131 for AmoCoala, while running more than three orders of magnitude faster.

  4. arXiv

    Multifidelity optimization stops letting cheap runs eat the budget: on DTMB 5415 the hull resistance falls further than the single-fidelity baseline

    Multifidelity active learning now folds the choice of fidelity into the choice of where to sample, instead of fixing the location first. MF-CAS scores each candidate by the high-fidelity improvement opportunity per unit cost using decomposed uncertainty intervals; on the constrained 14-dimensional DTMB 5415 hull hydrodynamic optimization with a 100 equivalent-high-fidelity budget, its resistance reduction exceeds that of the single-fidelity LCB baseline, while the multifidelity LCB baseline barely improves on the initial design.

  5. Intrusion alerts stop trusting one model: notary agents and on-chain votes certify a 99.65%-accurate subset

    Intrusion alerts no longer trigger remediation on a single model's word: independent notary agents re-check each verdict and co-sign it on a Hyperledger Fabric ledger only after a 2-of-3 quorum. On the class-balanced CICIDS2017 test set the calibrated ensemble reaches 96.60% accuracy over all decisions, and the certified subset reaches 99.65% accuracy at a 0.04% false-positive rate with 87.3% coverage; on the independently generated GeNIS 2025 corpus the same stack certifies 99.86% of flows at 99.98% accuracy.

  6. Clinical history-taking stops following a fixed questionnaire: an explicit state picks each question, lifting BERTScore F1 from 0.68 to 0.84

    Automated history-taking in telemedicine must collect a structured record over many turns while adapting to what the patient answers. MedAgent-RAG keeps an explicit clinical state of filled slots, a ranked differential diagnosis, questions already asked and red flags detected, selects every question from that state, and grounds its final assessment in clinical guidelines retrieved by a parent–child retrieval-augmented pipeline. Evaluated on the MediTOD corpus with a language-model patient simulator, it raises BERTScore F1 from 0.68 for a single-shot baseline built on the same language model to 0.84, at a cost of 15.8 turns on average.

  7. arXiv

    Synapses That Remember Two Moments: Equilibrium Propagation Moves Its Contrastive Update Inside the Device, Matching Standard MNIST Error

    Equilibrium Propagation (EqProp) updates each synapse by comparing a local quantity at the free and nudged equilibria, which normally requires extra memory or a duplicated network to hold the earlier value. Here that temporal comparison is carried by the synapse's own two-timescale dynamics: a volatile state relaxes toward the product of pre- and postsynaptic activities while a non-volatile state stores the learned parameter, and the volatile state's change is transferred to the non-volatile one through a global gate. On MNIST with a single-hidden-layer network, the phase-based and continual forms reach test errors of 2.01% and 2.24%, against 2.00% and 2.28% for standard EqProp, within one standard deviation.

  8. medRxiv

    Is a new gene link actually new? PESTO sorts 940 associations into four evidence tiers and calls 7% novel

    Rare-variant studies now yield more significant gene-phenotype associations than teams can place against prior evidence, and that placement has become the tighter bottleneck. PESTO combines large language model literature curation with structured Open Targets genetic evidence in one agentic pipeline that assigns Novel, Hypothesized, Existing or Established with supporting citations. Across 940 unique associations from two rare-variant studies, 7% were called Novel and 21% Hypothesized; 86% of 50 randomly paired negative controls fell into those two tiers.

  9. arXiv

    A CT foundation model built for cancer patients' chest-abdomen-pelvis scans lifts AUC to 0.767 from 0.695

    CAPTOR, a vision-language foundation model pretrained on 25,512 chest-abdomen-pelvis CT-report pairs from cancer-focused exams, outperformed existing CT foundation models in its target setting. Disease classification reached an AUC of 0.767 versus 0.695 for the next-best model on the full chest-abdomen-pelvis subset, and 0.784 versus 0.734 on the oncologic subset. It encodes organ-centered crops of whole exams but makes study-level, not lesion-level, judgments.

  10. arXiv

    Foreshock counts may be underestimated: reversing declustering finds 30-40% more small foreshocks in Southern California

    Reversing the declustering metric so that the later mainshock's magnitude, not the earlier event's, sets the correlation range recovers more small foreshocks in both synthetic catalogs and the Southern California catalog, showing that foreshock counts depend not only on earthquake physics but on the temporal symmetry built into the declustering method.