arXiv:2607. 10810v1 Announce Type: cross Abstract: Deep generative models are increasingly used as simulators for downstream decision-making under data scarcity, but in risk-sensitive applications their usefulness depends on rare adverse scenarios rather than typical samples.
arXiv:2608. 11544v1 Announce Type: cross Abstract: We propose CVaR-penalized Generative Particle Algorithm (CVaR-GPA), a robust, tail-agnostic algorithm for fine-tuning generative models to learn heavy-tailed distributions and capture extreme events, requiring no prior knowledge or estimation of the target's tail characteristics.
arXiv:2605. 13175v2 Announce Type: replace Abstract: Recent works have proposed incorporating heavy-tailed (HT) noise into diffusion- and flow-based generative models, with the goals of better recovering the tails of target distributions and improving generative diversity.
arXiv:2609.37169v1 Announce Type: cross Abstract: Mid-training equips pretrained large language models with specialized and reasoning capabilities, but the returns of this stage are bounded since add...
arXiv:2607. 24507v1 Announce Type: cross Abstract: Existing methods mainly adapt pretrained autoregressive (AR) language models to masked diffusion, whereas we directly adapt them to uniform-noise diffusion, where every token remains editable during sampling.
arXiv:2606. 00320v1 Announce Type: new Abstract: We present an online, distribution-free framework for controlling the Conditional Value-at-Risk (CVaR), extending conformal tail risk control to non-stationary and adversarial environments.
arXiv:2502. 04646v2 Announce Type: replace-cross Abstract: Weighted sampling -- sampling from a probability density function (PDF) proportional to the product of a base PDF and a weight function -- is a fundamental technique with wide-ranging applications in variance reduction, biased sampling, data augmentation, and more.
The paper introduces block‑triangular joint drifting, a method that applies a projected drift field to the joint distribution of consecutive states, enabling one‑step generative surrogate models for stochastic transition dynamics. This architecture preserves the current‑state marginal while directly sampling the conditional distribution of next states, allowing stochastic trajectories to be generated with a single model evaluation per time step. Experiments show that the approach achieves accurate marginal and trajectory‑dependent statistics with favorable accuracy‑cost tradeoffs compared to deterministic, diffusion, flow, and distillation‑based generative surrogates.
arXiv:2606. 03184v1 Announce Type: cross Abstract: Financial forecasting is difficult due to low signal-to-noise ratios, latent factors, heavy tails, regime shifts, and jumps.
arXiv:2608. 19394v1 Announce Type: cross Abstract: We introduce Deep-MKV-TS, a path-dependent McKean-Vlasov framework for financial scenario generation.
The paper introduces Speculative Evaluation, a method to reduce variance in evaluating stochastic large language models (LLMs) under a fixed rollout budget. It employs a Hierarchical Bayesian Neyman (HBN) policy that first runs a short uniform pilot, then pools task-level success counts via a hierarchical Bayesian model to compute posterior expectations of task-level sampling variances. Using these expectations, the method applies exact positive-integer Neyman allocation to allocate rollouts, and an asynchronous variant (HBN-async) speculatively executes continuations from partial pilot feedback to mitigate synchronization overhead. Across six checkpoints and 18 benchmark groups, Speculative Evaluation achieves 12.8%-33.6% lower variance compared to uniform allocation, outperforming empirical and independent Bayesian baselines, and demonstrates practical benefits in real-generation experiments.
CRNDiff is a new count‑native diffusion framework that uses stochastic chemical reaction networks to model nonnegative integer data such as single‑cell RNA sequencing. It provides a closed‑form forward‑noising kernel, enabling efficient reverse sampling via forward‑filtering backward‑sampling and data‑driven selection of the terminal noising time. The method also introduces tilted Feynman–Kac steering to sample rare subpopulations without retraining, and demonstrates superior conditional fidelity and marker‑level preservation on human heart scRNA‑seq data.
arXiv:2606. 18367v1 Announce Type: new Abstract: Standard benchmarks evaluate time series foundation models (TSFMs) using aggregate metrics, but these can mask severe failures in critical operating regimes.