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

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…

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…

The paper proposes Self-Adaptive Monotonic Normalization (SAMN), a hyperparameter-friendly method that improves long-tailed recognition by enforcing monotonicity on per-class weight norms without requ…

The paper proposes Mean MAE (MMAE), a novel self-supervised pre-training framework that uses flow mixing and teacher-student distillation to improve encrypted traffic classification by capturing multi…

This book provides a compact, derivation-oriented mathematical primer that connects major families of generative AI models, showing their underlying structural relationships.

The paper introduces GEM, an effective concept erasure framework for Rectified Flow Transformers, by unifying trajectory-based unlearning with classic teacher-guided flow matching.

DOT-MoE introduces a novel framework that treats the decomposition of dense layers into Mixture of Experts (MoE) as a Differentiable Optimal Transport problem, achieving superior efficiency while pres…

The paper develops a quantitative framework to analyze and improve flow distillation in diffusion models, providing stability guarantees and suggesting non-uniform time scheduling to reduce approximat…

The paper introduces Semantic Flow Regularization (SFR), an auxiliary objective that significantly improves the diversity and quality of LLM responses when fine-tuned for specific styles or personas,…

The paper proposes a novel neural network compression technique that aggregates neurons with similar functional dynamics, achieving significant model size reduction while maintaining high accuracy.

FlowTime proposes a novel Continuous Generative Regression framework using a Flow-based Personalized Prior to accurately model the multimodal and heterogeneous nature of user watch time prediction, si…

The paper introduces an efficient, novel algorithm for incremental Byte Pair Encoding (BPE) tokenization that processes input text prefix by prefix, achieving significant speedups and enabling streami…

The paper proposes a novel geometric embedding hashing method to recover object correspondences (vector links) between two embedding clouds generated by different black-box encoders using only a small…

The paper proposes using pseudo-sensitivities, derived from adjoint sensitivity fields, as an optimal conditioning signal in a Bernoulli flow-matching framework to significantly improve the out-of-dis…

The paper introduces Strong Stochastic Flow Maps (SSFMs), a novel framework that directly learns the strong solution map of additive-noise Stochastic Differential Equations (SDEs), enabling few-step s…

The paper investigates applying Riemannian optimization techniques to low-rank matrix parameters for deep learning, but finds that the proposed methods do not conclusively outperform the AdamW baselin…

The paper introduces Geodesic Flow Matching, a manifold-aware denoising technique that adapts Riemannian transport dynamics to accurately clean high-dimensional structured representations like Spatial…

SANA-Streaming introduces a novel, efficient framework that enables real-time, high-resolution streaming video-to-video editing by combining a hybrid diffusion transformer with specialized training an…

The paper introduces Automatically Differentiable Nonlinear Tensor Networks (ADNTNs) to achieve massive, structured compression of deep neural networks, demonstrating compression ratios up to 77,000x…