Tag
提出了一种基于条件归一化流的摊销变分推断方法，构建加权似然的局部后验来处理模型校准中的模型偏差与上下文不确定性，并在Branin-Hoo孪生实验及单柱海洋模型的k-ε湍流闭合校准中验证了其相较于全局后验的误差降低效果。
提出 acquisition function-guided generation (AFGG) 方法，通过将采集函数倾斜的分布嵌入扩散桥，在离散空间上结合预训练生成模型与数据空间代理模型进行贝叶斯优化；在分子设计基准上，基于流的变体在多数场景中超越现有最优方法。
该论文提出 Normalizing Flow Maps（NFM），一种可精确求逆的推前映射类模型，统一了 normalizing flows 与 flow maps，支持高效的精确似然评估与少步生成。在 CIFAR-10、ImageNet-64 条件图像生成和 Boltzmann Generators 平衡采样任务上达到了参数量匹配条件下 normalizing flows 的最先进水平。
该论文提出 LILIE（Language-Informed and Lossless Image Encoder），利用可逆归一化流编码器为文本到图像生成提供语言监督损失，在 GPIC 数据集上将 JiT 模型的 gFD 从 66.84 降至 53.01，相比纯像素损失显著提升保真度。
This paper presents V2TATC, a joint voice–trajectory embedding framework for air traffic controller situational awareness, and introduces a novel dataset for cross-modal retrieval experiments in congested airspaces.
This paper proposes a unified path-integral framework for generative modeling, showing that flow-based, diffusion-based, variational, and adversarial models arise from different evaluation principles of a single master action. It derives a one-loop correction that reduces tree-level error dramatically and introduces a response-weighted score-matching objective.
This paper unifies twelve continuous-time generative models under mean-field game theory via a cost tuple, introduces MFGLab (a PyTorch library that auto-shares training loops and solvers), and proposes DI-Flow with differentiable entropy for better mode coverage.
Proposes Hybrid Latent-Structural Fusion (HLSF), a weighted anomaly fusion framework combining CP-APR structural anomaly scores with latent-space density scores from normalizing flows, improving cyber anomaly detection on real-world compromised user credentials data.
This paper proposes NFTR, a method for offline goal-conditioned reinforcement learning that uses normalizing flows for subgoal policies and a triangle-slack reweighting to address optimistic bias and mode collapse in hierarchical implicit Q-learning.
Warp RL replaces additive residual corrections in reinforcement learning with an invertible, state-conditioned transformation of the base policy's action distribution using monotonic rational-quadratic spline flows, enabling adaptation of distribution shape, scale, and geometry under dynamics shifts. It matches or outperforms residual correction in ManiSkill3 manipulation tasks and achieves 30% faster task completion in a real robot peg-insertion task.
This paper presents a physics-informed conditional normalizing flow model for angles-only orbit determination in the cislunar environment, enabling flexible posterior representation and providing warm starts for classical algorithms.
MIMFlow integrates Masked Image Modeling with Normalizing Flows for end-to-end image generation, achieving a FID of 2.50 on ImageNet 256x256 with 50% fewer tokens than standard models.
A deep learning framework for probabilistic CO2 column retrieval from OCO-2 spectra using Laplace approximations and normalizing flows, achieving faster inference and better uncertainty quantification than traditional methods.
Proposes NF-CoT, a latent reasoning framework using normalizing flows to model continuous thoughts in LLMs, preserving autoregressive advantages and achieving better code generation performance with lower cost.
Proposes a 'lift' method for training input-convex neural networks (ICNNs) that uses an unconstrained hypernetwork to emit non-negative inter-layer weights, softening the loss landscape and escaping gradient attenuation, achieving lower test loss than projected gradient descent and softplus reparametrization.
This paper introduces Normalizing Trajectory Models (NTM), a novel approach to diffusion-based generation that models reverse steps as conditional normalizing flows with exact likelihood training. NTM enables high-quality text-to-image generation in just four steps while retaining the likelihood framework, outperforming baselines on standard benchmarks.
STARFlow2 is a new research paper introducing an architecture that bridges language models and autoregressive normalizing flows for unified multimodal generation. It addresses structural mismatches in existing systems by using a shared causal masking mechanism for interleaved text-image sequences.
FFJORD introduces a scalable reversible generative model using continuous dynamics and Hutchinson's trace estimator to enable unbiased log-density estimation without architectural constraints. The method achieves state-of-the-art results on density estimation and image generation while maintaining efficient sampling.