Skip to main content
Search

University of Toronto

26 related articles

Subscribe to updates
  1. arXiv

    SPARC lets experimental evidence rewrite model weights: 8 of 11 recommended conditions fall below 300 mV overpotential

    Closed-loop experiments usually fix the model family and representation first, then let new data update only predictions. SPARC builds an evidence matrix from the out-of-sample predictions of competing regression models, assigns each model's influence through a sparse posterior, and combines candidate-dependent predictive dispersion with a residual scale into a trust score that modulates exploration. In an automated alkaline oxygen-evolution campaign, 8 of 11 recommendations fixed in advance reached overpotentials below 300 mV, versus 18 of 125 initial experiments, with a best value of 242 mV.

  2. arXiv

    CyberArena puts AI agents in live attack-and-defense combat, and two frontier models pull ahead of the field

    CyberArena turns cybersecurity evaluation from static targets into multi-round combat: two agents in isolated sandboxes attack each other's services while patching their own, with objectives rotating every round. Across 40 challenges and 466 games, GPT-5.6 Sol and Claude Opus 5 led 12 frontier agents, and on 30 challenges all three compared models solved solo, round-three capture rates fell to 52%, 37% and 35%.

  3. arXiv

    A language-model agent writes its own physics-residual detector: BATADAL test-attack F1 rises from 0.504 to 0.878

    For runtime attack detection in cyber-physical systems, PIA has a large language model agent write physical residuals such as pump characteristics, tank mass balances and controller logic from a plant description and normal operating data, then test each candidate on an evaluation workbench before deployment. On the BATADAL water-distribution attack benchmark's test attacks, PIA with Claude Opus 5.5 reaches an F1 of 0.878 against 0.504 for the strongest of six statistical and deep baselines; ablations show that denying the agent data testing costs up to 0.28 F1.

  4. arXiv

    Chemical reaction networks stop refitting per dataset: one training run, then model choice and rate constants in seconds

    A single amortized neural architecture now handles reaction-pathway discrimination and rate-constant estimation together, so new experimental data needs only a forward pass to yield posterior model probabilities and parameter posteriors.

  5. arXiv

    Autonomous-driving tests stop following a fixed script: a scenario orchestrator rewrites other vehicles in real time and fully realizes the intended interaction in all six scenario families

    Autonomous-driving policies react in closed loop, so a scenario scripted with fixed routes often drifts away from the interaction it was meant to stage, a problem called closed-loop drift. A scenario orchestrator continuously monitors the joint traffic state and adapts non-ego actors through re-timing, re-routing and role reassignment, solving a constrained optimization at each step so the test intent survives while interventions stay limited and traffic stays feasible. In the CARLA simulator across six scenario families and six ego policies, the method fully realizes the intended interaction in every scenario family, while baselines such as ProSim, LASER and OSC2Runner mostly satisfy only the two easiest scenes.

  6. Disordered proteins get all-atom ensembles in one diffusion pass, matching NMR and SAXS without reweighting

    IDPForge repurposes ESMFold's attention and structure modules as a diffusion generator that produces all-atom ensembles of intrinsically disordered proteins and regions directly from sequence, without per-sequence training, coarse-grained back-mapping or ensemble reweighting. On 32 test sequences with NMR and/or SAXS data it reaches a normalized total X-EISD score of 0.89, against 0.57 for IDPConformerGenerator, 0.58 for IDPFold and 0.58 for CALVADOS, and it can denoise only the disordered region around a folded template.

  7. Calibrated uncertainty often fails to beat random sampling: active learning on out-of-distribution materials data

    Active learning for materials and molecular property prediction treats high-uncertainty samples as the information a model is missing. Across formation energy, bandgap and solubility tasks, uncertainty came from loss-landscape sampling and from ensembles retrained with different seeds, then was calibrated with linear calibration factors and a neural network. Calibrated uncertainty generally did not reduce the data a model needed to improve on out-of-distribution data, showing no advantage over random sampling or uncalibrated estimates, and error bars overlapped.

  8. medRxiv

    Cancer side effects can be forecast from routine labs: SPARC holds up across 11 hospitals

    Predicting cancer treatment side effects has long relied on static nomograms built from a handful of variables. SPARC instead models longitudinal sequences of blood counts, metabolic panels and vital signs, pretraining on 101,920,379 measurements from 224,047 patients and then fine-tuning for mortality, anemia, neutropenia, febrile neutropenia, acute kidney injury and liver toxicity. It matched or led comparison models on held-out, prospective and multi-hospital cohorts, and its predicted risk strata identified patients most likely to benefit from G-CSF prophylaxis.

  9. arXiv

    A chat before labelling: micro-narratives made the same posts read more divergently, not more alike

    A pre-annotation stage that anchors a short axis-guided conversation in a scenario vignette and returns a first-person micro-narrative raised identity resonance and harm sensitivity among 104 annotators labelling 30 ambiguous hate speech items, while label entropy rose and inter-annotator agreement fell.

  10. arXiv

    FOCUS uses KL-guided modality switching to transfer privileged-state training to an RGB-D policy, raising average test success from 0.71 to 0.93 across five IsaacLab manipulation tasks

    FOCUS is a single-stage PPO framework that keeps the critic on privileged state while an actor switches its rollout source between privileged-state and RGB-D latents according to the KL divergence between the two modalities' action distributions, combined with representation alignment; across five IsaacLab manipulation tasks it raises average test success from 0.71 to 0.93 and end-to-end budget-normalized training-success AUC from 0.47 to 0.65 relative to the strongest RGB-D-at-test baseline on each task.