Many clinical decisions are rapid multiple-choice tasks that require uncertainty estimates for safe deployment. This paper evaluates four System 1 models, zero-shot non-generative classifiers that return answer probabilities in a single forward pass, on 86 clinical tasks across six capability tiers spanning text and imaging. The authors find that these models excel at medical knowledge questions and report extraction, operating in under half a second and for a few joules per decision, but they fall sharply on clinical judgement and volumetric imaging tasks. The results map a clear capability gradient and make a pragmatic case for where fast, cheap decision models can fit into clinical workflows.

Global AUC can hide regions where a classifier discriminates poorly, which is dangerous in high-stakes clinical risk stratification. This paper introduces LOCATOR, a method that computes a localized AUC ($\mathrm{LAUC}$) for each participant by weighting all event–non-event pairs by Gower-distance similarity, then trains an XGBoost regressor on $\logit(\mathrm{LAUC})$ from baseline covariates to flag high- and low-competence regions without subsetting the data. The authors derive asymptotic properties of the $\mathrm{LAUC}$ estimator and apply the framework to the guideline-endorsed PREVENT model in NHANES, with external validation in UK Biobank.

Classical analyses of the Unadjusted Langevin Algorithm (ULA) in Wasserstein-2 distance predict a dimension-dependent mixing time and bias, yet empirically ULA often estimates low-dimensional statistical functionals accurately without scaling the step size with dimension. This paper proposes using the subspace robust Wasserstein (SRW) distance to analyze ULA on ridge-separable Bayesian posteriors, proving that iteration complexity can be dimension-free in both the overparameterized regime ($N \lesssim d$) and the large-sample regime ($N \gtrsim d^2$), while showing such guarantees are impossible near the proportional regime $N \asymp d$. The results explain a bell-shaped bias profile and provide a rotationally invariant alternative to prior $\ell^\infty$-based dimension-free analyses that fail under isotropy.

This paper attacks a foundational weakness in RL evaluation: standard benchmarks rank algorithms by relative return without knowing the optimal policy, so they cannot measure true distance to optimality. The authors propose converse optimality, a construction that generates control tasks together with certified optimal value functions and policies, enabling absolute metrics like optimality gap and regret. The framework separates continuous-time sensitivity studies from native discrete-time oracle-referenced comparisons, and extends the certificate logic to non-smooth values, non-affine action interfaces, and partially observed settings. By turning benchmarks into known-answer instruments, the work promises to expose failure modes and regime dependencies that relative rankings completely hide.

Gandalf tackles SSD wear-out in LLM serving systems that offload ever-growing KV caches beyond GPU and host memory. The core idea is that hybrid attention architectures (full plus linear/sparse) generate KV states with predictably different reuse lifetimes, so preferring SSD placement for long-lived full-attention KV while keeping short-lived linear states in DRAM can slash write volume without sacrificing cache hits. The paper claims average 7.3x lifetime extensions on trace-driven simulation, which matters because production agentic workloads can exhaust enterprise SSDs in months.

Machine learning for atomistic materials discovery is often bottlenecked by the cost of generating density functional theory (DFT) training data for new chemical systems. PYTHIA attacks this by freezing a pretrained MACE foundation model, adapting its atomic features through a lightweight Transformer, and feeding the result into a Gaussian Process that both predicts adsorption energies and quantifies uncertainty for Bayesian Optimization. The framework is designed to make complex architectures usable on small DFT datasets, enabling simultaneous optimization of adsorbate placement and substrate defects in understudied materials.

DLoss tackles objective misalignment in radiology report generation: standard cross-entropy treats diagnostic and narrative tokens identically, so models can sound fluent while omitting critical findings or inserting false ones. The core idea is to pool decoder probabilities across sequence positions with different operators—noisy-OR for supported diagnoses and tempered log-sum-exp for unsupported ones—and add this as an auxiliary loss without changing architecture or inference. Evaluated across six 3D MedVLMs on ~50,000 abdominal CT scans, DLoss improves clinical metrics on most benchmarks, though gains vary widely by backbone.

Continuous-time linear SDEs provide a natural model for interacting dynamical systems, but recovering causal drift coefficients from equilibrium data is difficult when reciprocal interactions (directed 2-cycles) or latent variables are present. This paper establishes new graphical sufficient conditions for generic identifiability of the drift matrix from stationary covariance in non-simple graphs, and develops an instrumental-variable framework to identify target direct effects under latent confounding. Both contributions extend the rank-based algebraic approach of Dettling et al. (2023) to settings previously unexplored for stationary linear SDEs.

Next-event prediction in sequential data is usually handled by opaque neural networks, while existing symbolic rule methods lack a principled way to form a unified predictive model. This paper introduces Rules, a neuro-symbolic network that learns Temporal Conjunctive Prediction Rules via differentiable temperature annealing, and Runes, which adds a residual transformer to correct rule-based logit predictions. It matters because it offers an explicit accuracy-interpretability trade-off, producing compact, inspectable symbolic rules for safety-sensitive domains while remaining competitive with black-box transformers.

Random projections (RP) offer a powerful way to reduce the $O(n^3)$ cost of kernel spectral algorithms, but existing theory has largely been confined to well-specified settings or narrow mis-specified regimes under restrictive boundedness assumptions. This paper establishes high-probability minimax optimal learning rates in Sobolev norms for RP-based spectral algorithms under general source conditions and a Bernstein noise condition, without assuming uniform boundedness of the regression function $f_\rho$. By exploiting the RKHS embedding property and a refined operator similarity analysis, the authors enlarge the optimal source range from $s \geq 1 - 1/\beta$ to $s > \alpha_0 - 1/\beta$, showing that projection dimensions proportional to the effective dimension preserve statistical efficiency while yielding substantial computational savings.

Federated clustering under non-IID data must minimize communication rounds while preventing leakage of local data properties. This paper proposes Evolving Federated Density Peak Clustering (eFDPC), where each client incrementally learns diagonal-covariance Gaussian micro-clusters from private mini-batches, selects local density peaks, and transmits masked peaks through a shuffler-based anonymization layer. A server-side second density-peak step reconstructs unlinkable global centers from additive shares, aiming for accurate one-shot clustering without centralizing raw samples.

Training-free generalist graph anomaly detection must identify heterogeneous anomalies on unseen graphs without target-domain labels. Jev-GAD addresses this by extracting structural, attribute, and neighborhood evidence, converting it into graph-relative percentiles $e_j(v)=\mathcal{R}_G(\delta_j(v))$, and packaging selected evidence into semantically labeled decision states for a frozen pretrained language model. The model returns anomaly scores via non-generative option-logit readout $s_{\mathrm{dec}}(v)=\sigma(\ell_v^a-\ell_v^n)$, which are then fused with four complementary statistical scorers through equal-weight rank normalization. While the multi-view evidence design is principled, the paper hinges on a costly, manually engineered LLM interface and reports gains that sit atop an unstable baseline landscape.

PAIR tackles a fundamental mismatch in professional network retrieval: relevance is complementary rather than symmetric. LinkedIn proposes a triple-tower retrieval framework that learns from exposure-conditioned preference signals via a multi-negative contrastive objective, combines static profile embeddings with lightweight dynamic history updates in embedding space, and supports multiple serving budgets through Matryoshka training. The work matters because demonstrated retrieval gains translated into real business impact at billion-user scale.

This paper introduces a continuous-time linear-quadratic model of open-loop target pursuit to study how agents learn interception strategies. It derives exact closed-form solutions for optimal control trajectories, REINFORCE policy learning dynamics, and temporal-difference value learning dynamics. The central finding is that the eigenvalue spectrum of the learning dynamics matrix generically displays a gap, meaning agents learn to reach the target before optimizing their movement path. The results offer a rigorous theoretical benchmark for pursuit behavior and its learning dynamics.

Inside-JEPA tackles the opacity of latent world models by embedding relational channels for ordered entity pairs directly into the JEPA latent state. The core idea is that an inverse-dynamics loss—recovering actions from changes in these channels—can ground them to geometric relations without any relation labels during training. This matters because it could let world-model states be read and given goals in relational terms, the natural vocabulary for planning and manipulation.

Language models are increasingly used for discrete decisions like tool selection or intent classification, yet prompting LLMs for these closed-set choices is slow and sensitive to option order. This paper introduces Crivo, a family of compact encoders scaling from 17 million to 1 billion parameters, and runs a controlled study to determine whether scoring each option in a separate encoder pass outperforms reading all options jointly in a single sequence. The work matters because it tests the limits of parameter efficiency and architectural choices for high-speed decision nodes that must generalize across changing label sets.

This paper proposes an adaptive framework for cryptographic primality testing that integrates arbitrary-precision arithmetic, hardware-aware sieving, and a machine-learning-guided Miller-Rabin witness selector anchored on quantum entropy. The core idea is to reduce expensive modular exponentiations by using lightweight structural features of a candidate integer to prioritize bases likely to expose compositeness early. It targets the key-generation bottleneck for RSA and ECC, yet the contribution is more architectural than empirically demonstrated, resting heavily on a withdrawn survey and a toy Python benchmark.

This paper initiates the statistical theory of reverse-KL policy distillation under misspecification, asking whether the teacher's full action distribution improves efficiency over action-level feedback and whether online student trajectories are necessary versus offline teacher data. The authors establish minimax-optimal rates for full-feedback settings, develop clipped importance-weighting and trajectory-truncation algorithms, and prove a striking separation: offline action feedback can match full-feedback rates, while online action feedback requires exponentially more data. The results give a first theoretical footing for empirical design choices in modern LLM distillation.

As Mathlib grows past 400,000 theorems, effective semantic search is critical for both human formalization and automated proving, yet real-world queries are short and ambiguous while existing engines train on lengthy, context-rich informalizations. Lean Finder V2 closes this gap with an adversarial generator-retriever loop that synthesizes over 600,000 faithful, challenging short queries, then uses them for both retriever fine-tuning and GEPA-optimized input rewriting. The result is a new state of the art on human-curated and real-world benchmarks, plus measurable gains in downstream theorem-proving tasks.

Meta-RL agents struggle to adapt quickly to unseen tasks when task evidence is sparse or spread across long interaction histories, because recurrent models compress history too aggressively and transformers scale quadratically. METTA proposes a two-scale neural memory architecture that uses Test-Time Training (TTT) layers for fine-grained within-episode adaptation and compact episode summaries for cross-episode reasoning, preserving linear sequence complexity. The core claim is that this design enables stronger task-family-level generalization and more structured exploration on long-horizon sparse-reward tasks than both recurrence and full-attention baselines, while keeping wall-clock training cost low.