scale-aware conditioning

This study addresses the numerical ill-conditioning commonly encountered in dictionary learning for dynamical equation discovery in systems biology, where highly correlated candidate functions degrade model identification accuracy. The work systematically investigates the impact of multicollinearity in sparse regression on biological dynamical modeling, revealing that even a small subset of terms can induce severe ill-conditioning. Through comparative analysis of orthogonal polynomial bases and monomial bases under varying data distributions—supported by condition number assessments and numerical experiments on benchmark systems biology models—the study demonstrates that orthogonal bases substantially improve conditioning, numerical stability, and model recovery accuracy only when their associated weight functions align with the data sampling distribution.

This study addresses the challenge of learning extreme events in chaotic systems from short trajectories, which is hindered by transient instabilities. To overcome this, we propose a mechanism-aware conditioning framework that leverages ensemble covariance as an actionable conditioning signal to capture the geometric structure of local destabilization. This signal is injected into Transformer and STORN backbone networks via Feature-wise Linear Modulation (FiLM) modules, enabling Jacobian-free and non-intrusive surrogate modeling. We demonstrate the efficacy of our approach on a quasi-geostrophic flow task, where it significantly improves the statistical characterization of rare events using only limited data. Notably, the proposed method outperforms baseline models trained with ten times higher-resolution data, highlighting its potential for efficient and accurate prediction of extreme events in complex dynamical systems.

This work addresses the lack of a unified theoretical framework and failure mode analysis for existing batch Bayesian optimization methods—such as Constant Liar (CL), Kriging Believer (KB), and fantasy models. We introduce the concept of “efficient conditioning,” showing that these approaches are specific instantiations of a common mechanism, and reveal their intrinsic connections to local penalization and determinantal point processes. Building on this insight, we develop a Structural Diversity Diagnostic (SDD) method and prove that Gaussian processes under this framework generate batch points with theoretically guaranteed diversity. Experiments demonstrate that the implicit penalization in CL/KB matches or outperforms explicit penalization schemes; efficient conditioning achieves performance comparable to joint qEI in high-dimensional tasks and extends effectively to Multiquadric RBF networks; meanwhile, parametric models like random forests often induce batch collapse, whereas neural networks restore diversity at substantial computational cost.

For black-box models applied to complex tasks such as image segmentation, defining meaningful conditional events is challenging, leading to uncertainty estimates that fail to reflect inherent sample difficulty. Method: This paper proposes an input-dependent statistical risk control framework grounded in conformal prediction. It introduces a novel, algorithm-driven mechanism for dynamically selecting conditional function classes—bypassing manual discretization—by adaptively constructing these classes based on test-sample difficulty and integrating online parameter tuning for fine-grained, approximately conditional risk control. Contribution/Results: Experiments on regression and image segmentation demonstrate substantial improvements in uncertainty calibration accuracy. The method guarantees strict statistical risk control while enhancing generalization robustness and predictive reliability.

This work addresses the longstanding limitation in conditional density estimation—namely, the absence of closed-form solutions for multivariate conditional densities under non-Gaussian assumptions. We propose a generative conditional density estimation framework grounded in copula modeling and analytic conditionalization in latent space. Methodologically, we first establish the inheritability of “conditional stability” under mixture and transformation operations, thereby extending analytically tractable conditional families to non-Gaussian, nonlinear, and cross-dimensional settings. The core components include a Gaussian Mixture Copula Model (GMCM), an explicit latent-space conditionalization mechanism, and joint copula modeling. Experiments on synthetic and real-world datasets demonstrate substantial improvements in conditional density estimation accuracy and robustness to missing data imputation. Crucially, our approach enables efficient, differentiable, and sampling-free deterministic conditional inference.

研究通过引入损失条件状态执行方法，决定何时更新世界模型状态以减少下游损失，实验表明该方法在多个基准测试中有效降低了损失。

This study addresses the limitation of temporal world models that, despite high predictive accuracy, exhibit poor mechanistic consistency and struggle to respond to plan changes. We propose a formalized framework and benchmark that explicitly decouple states, actions, and exogenous inputs. Methodologically, we construct quantitative metrics for mechanistic consistency to reveal its divergence from accuracy, and introduce a directional supervision loss. Architecturally, we employ a frozen latent prediction space with gated output fusion, conducting large-scale evaluations across multiple backbones. Experimental results demonstrate that specific architectural designs significantly reduce prediction errors, while directional supervision effectively enhances mechanistic consistency without compromising predictive accuracy.

提出了一种基于目标和条件多速联合扩散机制的扩散模型调节方法，通过插入修正项实现透明可控的条件生成，并引入对数福克-普朗克残差正则化以提高采样质量。

This work addresses the lack of systematic methodologies in model optimization, which often relies on heuristic choices and struggles to accommodate diverse deployment constraints. It formalizes model compression and acceleration as a constraint-aware multi-objective engineering decision problem, establishing a unified and actionable framework grounded in five key dimensions: data availability, latency, memory footprint, accuracy tolerance, and retraining budget. By integrating techniques such as quantization, pruning, knowledge distillation, parameter-efficient fine-tuning (PEFT), and inference optimization, the study proposes tailored optimization pipelines for four representative industrial scenarios, delivering a reproducible and quantifiable guide for technology selection.

This work addresses the lack of verifiability in learned world models when deployed in high-assurance systems by proposing a novel framework that integrates classical model order reduction (MOR) with modern world modeling. The approach combines proper orthogonal decomposition (POD) with an encoder–decoder architecture, incorporates physics-informed error bounds derived from physical priors, and employs measurement-driven action-conditioned modeling to ensure verifiable closed-loop predictions, exceptional data efficiency, and physical consistency. By systematically unifying MOR theory with contemporary world model paradigms, this study establishes a new modeling methodology that simultaneously achieves reliability and performance for safety-critical applications.