Skip to main content
Search

King Abdullah University of Science and Technology

16 related articles

Subscribe to updates
  1. arXiv

    Latent-charge potentials get exact periodic electrostatics: projection recovers the 1.8 charge an unconstrained NaCl model loses

    Latent-charge machine-learning potentials learn atomic charges as hidden variables from energies and forces, but their long-range electrostatic term had no exact periodic form, leaving net charge mixed with self-energy. Writing that term as a smeared Epstein–Hurwitz lattice sum separates the net-charge artefact from the local self-energy and yields a sphere-average theorem for cells of any shape, plus forces and virial. Projecting the latent charges onto fixed total charge gives projected latent Ewald summation (pLES); on charged NaCl clusters it recovers the total charge an unconstrained model misses by up to 1.8 and cuts a short-range model's test errors from 1.44 to 0.42 meV/atom and from 37 to 13 meV/Å.

  2. arXiv

    Deep eutectic solvent screening moves beyond quantum chemistry: TiNN splits the hydrogen-bond network into two steps and cuts measured solubility error from 23-fold to about 1.5-fold

    A deep eutectic solvent is a multicomponent hydrogen-bond network of acceptors, donors and solutes, so its solubility cannot be read off the properties of individual constituents. TiNN represents the process in two stages, first forming the acceptor-donor environment and then accommodating the solute, and constrains the temperature and pressure response through a learned free-energy pathway, reaching a test-set R2R^2 of 0.917 on 938 records. In new measurements of glucose, xylan and Kraft lignin in acidic, basic and neutral deep eutectic solvents, TiNN reduces the geometric mean fold error of solubility from more than 23 for COSMO-RS to about 1.5.

  3. arXiv

    Segmentation prompts stop being one vector: [SEG] attention maps lift Sa2VA on object parts and multiple objects

    Language-guided segmentation usually compresses the referent's location into a single [SEG] hidden-state vector handed to the decoder, a vector with no spatial index while the decoder never sees the expression. AttnSeg instead passes the [SEG] token's attention over image patches as the decoder's dense prompt and supervises that map directly with an attention-guidance objective in two training stages. On Sa2VA, the 4B model raises ReasonSeg gIoU from 57.70 to 64.11 and GS-Eval from 61.91 to 72.11, with gains concentrated on object parts, multiple objects and single objects, and negligible change on stuff regions.

  4. 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.

  5. Vehicles Leave After One-Shot Training: Exact Federated Editing Cuts Cumulative Time 36%–44% in Mobility Simulation

    One-shot federated learning finishes training in a single communication round, but the resulting model is frozen once devices join or leave, leaving full retraining as the fallback. F-SOSA draws a fixed-size uniform random client subset so outputs under neighboring device sets stay bounded in total variation, then rewrites curvature-aware fusion as a projection over client-additive sufficient statistics, enabling F-SOSA-U for withdrawing a contribution and F-SOSA-I for adding one. In a SUMO urban mobility simulation, both match retraining accuracy while cutting cumulative time and communication by 36%–44% and 22%–33%.

  6. Nature Methods

    Cell segmentation in spatial transcriptomics gets a cross-platform test: SAM tops the raw score, SCS leads once coverage counts

    Cell segmentation in spatial transcriptomics has lacked a cross-platform comparison with biologically meaningful metrics. A benchmark evaluates 11 image-based, transcriptomics-based and multimodal methods across 15 datasets from 5 technologies and about 2.3 million cells, scoring segmentation quality, transcript recovery, morphology, expression purity and spatial organization. On the average of 15 metrics, SAM scores highest (0.58), ahead of SAM2 (0.53), BIDCell (0.52) and SCS (0.48); after adjusting by the ratio of segmented to reference cells, SCS leads (0.34), with BIDCell and Baysor both at 0.33.

  7. Joint multi-sample network inference steadies omics reconstructions, but a prior cut to 20% leaves zero active reactions

    Multi-sample regulatory network inference has long solved each sample separately and stitched shared structure from overlaps, which is unstable under noise. CORNETO instead solves several samples inside one mixed-integer constrained optimization with structured sparsity penalties. On haematopoietic and adult cortical single-cell data, joint inference generally improved robustness and reproducibility, while predictive gains depended on biological context and prior-network completeness.

  8. arXiv

    Most of the no-think RL gain in hybrid reasoning models is thinking leakage: erasing an 8-D think subspace at 8B removes 75% of it

    Training Qwen3-1.7B, 4B and 8B with GRPO in no-think mode raises accuracy while responses grow longer, carry more reflection words, and internal activations shift toward the original model's think mode. Weight scaling, activation patching and attention-head interventions indicate that much of this gain comes from reactivating reasoning the original model already had rather than learning new reasoning behavior; at 8B, replacing an 8-dimensional think subspace removes 75% of the gain, and the reverse exchange transfers 50% of it to the original model.

  9. arXiv

    Agent safety in shared professional workspaces gets a comparison: a correct deliverable can still come with a secret written to a shared folder

    APEX-Harm evaluates prompt and script injection against long-horizon agents on investment banking, law, and consulting tasks; across 12 frontier models Opus 5 and Sonnet 5 have the lowest overall attack success rates (8% and 20%), while task-specific script replacement and attacker-provided generic scripts still average 81–84% and 73%.

  10. arXiv

    Cloud writes the program, a small on-device model answers the questions: AppWorld success rises up to 14.9 points with user data kept local

    Letting a cloud model write the program while a small on-device model answers bounded questions about user data that appear only at run time improved a code-only agent's success rate on AppWorld in all six backbone-model and test-partition combinations, by up to 14.9 percentage points, with user data staying on the device.