This paper proposes NF-CoT, a latent reasoning framework that preserves the advantages of chain-of-thought in large language models.

This paper introduces a regularization term to variational inference with normalizing flows to improve mode coverage in Bayesian model calibration.

The paper proposes a Lagrangian sub-flow (LSF) framework and geometric diagnostic signals to improve out-of-distribution detection using Continuous Normalizing Flows, overcoming the likelihood paradox…

This paper proposes a novel monolithic 3D-stackable DRAM-based processing-near-memory architecture for efficient Normalizing Flows.

Low-Pass Flow Matching introduces a spectral bias into the flow matching process, allowing it to better model natural data by transitioning from a standard source spectrum to a frequency-decaying bias…

This paper investigates whether intrinsic symmetries in training data lead to conserved quantities during gradient-flow training of neural networks.

Introduces Expanding Generative Flows (EFlows) and Expanding Flow Maps (EFMs) for generating outputs of varying sizes in continuous and discrete state spaces.

This paper proposes a novel distillation framework for flow matching models that enables high-fidelity single-step generation.

This paper proposes AirFlow, a pollutant-aware dual-stream framework for accurate air quality forecasting using a statistic-guided normalization routing mechanism and a hierarchical dual-stream state…

This paper introduces MeanFlowNFT, a method that applies reinforcement learning to MeanFlow generators to improve performance and consistency.

The paper proposes a context-weighted sampler and scaled cross-entropy loss function for discrete generative modeling to improve generation quality and reduce generative perplexity.

This paper studies the fluctuations of infinitesimal gradient boosting and establishes a functional central limit theorem.

The paper introduces a fluency-aware optimization framework to balance low-latency simultaneous speech-to-speech translation and natural speech flow.

The Autonomous Rectified Flow framework is proposed to improve generative speech enhancement by eliminating explicit time-step conditioning and inferring denoising directions from spatial relationship…

This paper explores how different components of the Transformer feedforward block architecture impact rank preservation across depth during initialization.

An approach is described to support rigid α canonical variables in an e-graph.

This paper improves text-to-image generation performance by using the clean data parameterization in RAEs.

This paper proposes a background-set-free and reference-free music quality estimation method using unconditional Flow Matching inversion.