Skip to main content
Search

Princeton University

21 related articles

Subscribe to updates
  1. arXiv

    Anomaly detection turns to diversity: VAS tops 148 embedding benchmarks without hyperparameter tuning

    The Vendi Anomaly Score (VAS) redefines an anomaly as how much dataset diversity drops when a sample is removed, scoring samples through changes in the eigenvalue spectrum of the Vendi score rather than through density estimation or space partitioning. Across 148 ADBENCH image and text embedding benchmarks, VAS holds a better average rank than compared methods including ADERH, DN2 and SLAD, with no validation-set tuning; in controlled ImageNet contamination experiments it remains strongest as contamination rate and dataset scale grow.

  2. bioRxiv

    Inside a protein language model, binary patterns form a jellyfish: hydrophobic content sets the main axis while heptad phase curls into a ring

    In ESM2 residue embeddings, polar/nonpolar binary patterns organize into a readable geometry. Generating 50 sequences for each of all 128 heptad binary patterns, 6400 in total, and running position-preserving PCA yields a jellyfish-shaped manifold: hydrophobic content spreads along PC1, while PC2 and PC3 encode heptad phase as near sine and cosine. A charge alphabet stays ordered, but scrambled amino-acid groupings or the non-protein model ByT5 lose the cyclic organization.

  3. Wrist pulse waveforms carry meal information: aligning them with food text wins 0.69 of meals and lifts calorie-intake AUC by 11%

    An Apple team aligned wrist photoplethysmography (PPG, a green-light measure of microvascular blood-volume change) with meal descriptions to train the Nutrition PPG Language Model (NPLM) and test whether passively collected pulse waveforms carry dietary information. On 1,122,834 meal descriptions from 19,340 participants, near-meal PPG raised the likelihood of the correct meal text to a win rate of 0.69, against 0.60 for a control that kept the same participant and time of day but broke the meal pairing, and 0.50 for across-subject shuffling. Without retraining, the signal raised postprandial satiety prediction AUC from 0.64 to 0.71 in an independent cohort, which the authors frame as augmenting text-based logging rather than replacing it.

  4. arXiv

    Worst cases stop being guesswork: Simple-PAT searches a procedural generator's parameters and cuts worst-case error on four vision tasks

    Vision models still fail on seemingly simple scenes, and a fixed dataset cannot reliably estimate worst-case error. Procedural adversarial learning treats an interpretable procedural generator as a controllable data source and uses zeroth-order optimization to search its low-dimensional control parameters for hard instances. On four tasks spanning surface normals, image segmentation and human pose estimation, Simple-PAT lowers worst-case error below uniform training and two robust reweighting baselines against a cross-model black-box adversary with 50M aggregate queries.

  5. arXiv

    Suppressed misbehavior in language models can come back: PEARL trains from half-failed trajectories and holds under retraining

    Undesired behaviors in language models can re-emerge during later fine-tuning, and standard post-hoc suppression had not been compared on immediacy, durability and capability together. PEARL adds adversarial prefixes, continuations from intermediate states of cached misaligned trajectories, to GRPO's on-policy rollouts so the policy practices recovering from partly wrong states. Across Qwen3-4B and GPT-OSS-20B and two organism types, PEARL suppresses strongly while preserving task accuracy, with the clearest gains on the broad-trigger organism and GPT-OSS-20B; on Qwen3-4B with the narrow-trigger organism, SFT is more durable under heavy targeted retraining.

  6. arXiv

    Discharge decisions can retrain the model: capacity-aware discharge cuts readmission-risk learning error by 24%–25%

    Hospitals use readmission-risk predictions to decide who leaves first, but outcomes are recorded only for discharged patients, so retraining a predictor on that data can lock in censoring bias. Coupling a queueing-based Markov decision process with a periodically retrained risk predictor, the work finds that a discharge-up-to policy, which sets a target census and discharges by priority only when occupancy exceeds it, spreads observed lengths of stay through natural arrival variability. In synthetic experiments and calibrated simulations built on patient-level data from a partner hospital, the policy reduced learning error by 24%–25% relative to thresholding on risk and shrank baseline-adjusted readmission cost disparities by 38%–63%.

  7. arXiv

    SSM decoding stops writing state every step: caching recent inputs halves state traffic and matches vLLM speculation

    State-space model decoding previously read and wrote the full recurrent state at every step, making state traffic the memory-bandwidth bottleneck and leaving speculative decoding without cheap rollback. ReplaySSM represents the state as a checkpoint plus a buffer of recent inputs, writes the checkpoint only when the buffer fills, and computes outputs directly on most steps. Implemented in vLLM for Mamba-2 and Gated DeltaNet, it speeds up standard decoding over a tuned baseline at serving batch size 256, reaches about the throughput of vLLM's speculative decoding on two 120B-class models, and separate state precisions reduce output KL divergence and downstream accuracy losses.

  8. arXiv

    Automatic differentiation drops the coordinate basis: one JAX transformation now yields curvature, divergence and rotor-group updates

    Automatic differentiation can now run without fixing a coordinate basis: writing the geometric-algebra multivector derivative as a JAX transformation lets the same operator compute curvature, divergence and rotor-group updates.

  9. arXiv

    SafeActBench traces the evidence-to-action chain across 656 cases, finding strong static judgment but weaker interactive execution in tool-using agents

    The authors introduce SafeActBench, 656 cases across six operational domains and five protocols, using a provenance-bound Evidence Ledger and a deterministic trajectory evaluator to check whether tool-using agents establish required evidence before acting; across ten model–harness configurations, strong static action assessment coexists with much weaker interactive execution, failures often begin with incomplete investigation or premature action, single-action execution is usually reliable once evidence is established, and multi-action workflows additionally expose unresolved prerequisites and incomplete execution.

  10. arXiv

    MiniCorp lets an agent firm run an e-commerce company: price elasticities of 2.9–3.2, 23–32% ad-attributed lift, and delayed organic gains

    MiniCorp is a closed-loop office simulator that couples a persistent agent firm with an evolving e-commerce external market: the external world explicitly models search demand, matching and ranking, click and conversion, sponsored-search auctions, and dynamic competitors, while the internal world is a firm of standing roles that read exported business data, communicate, and propose decisions. Experiments show the integrated market reproduces empirical response patterns in price elasticity, the persistent effects of temporary discounts and stockouts, and the delayed organic gains of advertising, and that agents coordinate across roles while generating replayable counterfactual enterprise data.