首次探索如何利用基础模型推动因果生成建模，为新范式研究提供理论基石。
arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable o…
通过不确定性感知的分布到分布流匹配，为科学成像提供更可靠的生成模型
arXiv:2603.21717v4 Announce Type: replace Abstract: Distribution-to-distribution generative models support scientific imaging tasks ranging from model…
结合层代数与神经ODE，实现高保真脑动力学生成，为脑科学计算建模开辟新路径。
arXiv:2605.19324v1 Announce Type: new Abstract: Efficient neural network models that generate brain-like dynamic activity can be a valuable resource f…
提出抑制散度的耦合方法用于整流流，改善生成模型的稳定性和效率
arXiv:2605.17733v1 Announce Type: cross Abstract: The promise of Rectified Flow rests on producing self-generated couplings whose trajectories are str…
为视频生成注入物理规律，让模型理解重力、碰撞等真实性，推动世界模型迈向新高度
arXiv:2605.19242v1 Announce Type: cross Abstract: World simulators can provide safe and scalable environments for training Physical AI systems before …
系统评估AI艺术生成中风格泄露现象，揭示生成模型模仿艺术风格时的版权与伦理风险。
arXiv:2605.17500v1 Announce Type: new Abstract: Generative text-to-image models are typically trained on large-scale web-scraped datasets that include…
新方法Controlla通过图约束潜在几何实现可控性学习，为生成模型中的控制能力提供理论框架。
arXiv:2605.16603v1 Announce Type: new Abstract: Controllable multimodal generation is commonly formulated as an inference-time conditioning problem us…
最新研究利用潜在后验采样预测3D结构，为分子建模与生成提供新颖高效的统计方法。
arXiv:2605.10830v2 Announce Type: replace-cross Abstract: The remarkable achievements of both generative models of 2D images and neural field represen…
PyTorch生成建模工具包，简化VAE、GAN、扩散模型等实现与实验。
arXiv:2605.17605v1 Announce Type: new Abstract: Modern generative modeling has grown into a broad collection of related but often separately implement…
多尺度物理模拟的流匹配小波方法，高效生成高保真物理场。
arXiv:2605.16573v1 Announce Type: new Abstract: Accurate emulation of multi-scale physical systems governed by PDEs demands models that remain stable …
提出PDI-Bench框架，量化评估生成视频模型的几何一致性，攻克3D结构合理性难题。
arXiv:2605.15185v1 Announce Type: cross Abstract: Generative video models are increasingly studied as implicit world models, yet evaluating whether th…
这篇论文提出了利用自回归序列模型进行条件属性估计的新方法，直击生成模型在全局结构控制上的痛点，值得关注。
arXiv:2605.14004v1 Announce Type: new Abstract: Generative models are often trained with a next-token prediction objective, yet many downstream applic…
OpenAI提出的变分损失自编码器，结合VAE与有损压缩，优化潜在表示学习。
突破生成模型重尾难题：Tail Annealing让流匹配生成幂律尾分布，解决Lipschitz架构局限性。
arXiv:2605.20068v1 Announce Type: cross Abstract: Standard generative models struggle with heavy-tailed data: Lipschitz architectures cannot produce p…
从标题看，这篇论文或聚焦于置信度与流模型的结合，可能为生成式AI或不确定性估计带来新思路。
arXiv:2605.18472v1 Announce Type: cross Abstract: Generative models can produce nonsensical text, unrealistic images, and unstable materials faster th…
OpenAI改进一致性模型训练，突破一步生成高质量样本，无需对抗训练
Consistency models are a nascent family of generative models that can sample high quality data in one step without the need for adversarial training.
新能量模型破解生成扩散模型两大难题，实现线性逆问题无偏采样。
arXiv:2605.15487v1 Announce Type: new Abstract: Generative diffusion models can provide powerful prior probability models for inverse problems in imag…
提出f-轨迹平衡损失族，统一了GFlowNets和LLM的on/off-policy训练，梯度对应KL散度，低方差高效。
arXiv:2605.15417v1 Announce Type: cross Abstract: In GFlowNets and variational inference, it has been shown that the mean square error between target …
arXiv新论文提出无需训练框架，用音频和文本协同调谐实现视频运动编辑，突破生成模型局限。
arXiv:2605.15307v1 Announce Type: cross Abstract: Motion-centric video editing remains difficult for large generative video models, which often respon…
创新性双网络生成框架，用学习标量势在线评分桥接样本，突破传统均匀回归权重局限
arXiv:2605.14631v1 Announce Type: cross Abstract: We introduce Action-Inspired Generative Models (AGMs), a dual-network generative framework motivated…