Attention-Only Transformers via Unrolled Subspace Denoising

Despite the popularity of transformers in practice, their architectures are empirically designed and neither mathematically justified nor interpretable. Moreover, as indicated by many empirical studies, some components of transformer architectures may be redundant. To derive a fully interpretable transformer architecture with only necessary components, we contend that the goal of representation learning is to compress a set of noisy initial token representations towards a mixture of low-dimensional subspaces. To compress these noisy token representations, an associated denoising operation naturally takes the form of a multi-head (subspace) self-attention. By unrolling such iterative denoising operations into a deep network, we arrive at a highly compact architecture that consists of \textit{only} self-attention operators with skip connections at each layer. Moreover, we show that each layer performs highly efficient denoising: it improves the signal-to-noise ratio of token representations \textit{at a linear rate} with respect to the number of layers. Despite its simplicity, extensive experiments on vision and language tasks demonstrate that such a transformer achieves performance close to that of standard transformer architectures such as GPT-2 and CRATE.

Understanding Generalization in Diffusion Models via Probability Flow Distance

Diffusion models have emerged as a powerful class of generative models, capable of producing high-quality samples that generalize beyond the training data. However, evaluating this generalization remains challenging: theoretical metrics are often impractical for high-dimensional data, while no practical metrics rigorously measure generalization. In this work, we bridge this gap by introducing probability flow distance ($\texttt{PFD}$), a theoretically grounded and computationally efficient metric to measure distributional generalization. Specifically, $\texttt{PFD}$ quantifies the distance between distributions by comparing their noise-to-data mappings induced by the probability flow ODE. Moreover, by using $\texttt{PFD}$ under a teacher-student evaluation protocol, we empirically uncover several key generalization behaviors in diffusion models, including: (1) scaling behavior from memorization to generalization, (2) early learning and double descent training dynamics, and (3) bias-variance decomposition. Beyond these insights, our work lays a foundation for future empirical and theoretical studies on generalization in diffusion models.

Towards Understanding the Mechanisms of Classifier-Free Guidance

Classifier-free guidance (CFG) is a core technique powering state-of-the-art image generation systems, yet its underlying mechanisms remain poorly understood. In this work, we begin by analyzing CFG in a simplified linear diffusion model, where we show its behavior closely resembles that observed in the nonlinear case. Our analysis reveals that linear CFG improves generation quality via three distinct components: (i) a mean-shift term that approximately steers samples in the direction of class means, (ii) a positive Contrastive Principal Components (CPC) term that amplifies class-specific features, and (iii) a negative CPC term that suppresses generic features prevalent in unconditional data. We then verify that these insights in real-world, nonlinear diffusion models: over a broad range of noise levels, linear CFG resembles the behavior of its nonlinear counterpart. Although the two eventually diverge at low noise levels, we discuss how the insights from the linear analysis still shed light on the CFG's mechanism in the nonlinear regime.

Out-of-Distribution Generalization of In-Context Learning: A Low-Dimensional Subspace Perspective

This work aims to demystify the out-of-distribution (OOD) capabilities of in-context learning (ICL) by studying linear regression tasks parameterized with low-rank covariance matrices. With such a parameterization, we can model distribution shifts as a varying angle between the subspace of the training and testing covariance matrices. We prove that a single-layer linear attention model incurs a test risk with a non-negligible dependence on the angle, illustrating that ICL is not robust to such distribution shifts. However, using this framework, we also prove an interesting property of ICL: when trained on task vectors drawn from a union of low-dimensional subspaces, ICL can generalize to any subspace within their span, given sufficiently long prompt lengths. This suggests that the OOD generalization ability of Transformers may actually stem from the new task lying within the span of those encountered during training. We empirically show that our results also hold for models such as GPT-2, and conclude with (i) experiments on how our observations extend to nonlinear function classes and (ii) results on how LoRA has the ability to capture distribution shifts.

UGoDIT: Unsupervised Group Deep Image Prior Via Transferable Weights

Recent advances in data-centric deep generative models have led to significant progress in solving inverse imaging problems. However, these models (e.g., diffusion models (DMs)) typically require large amounts of fully sampled (clean) training data, which is often impractical in medical and scientific settings such as dynamic imaging. On the other hand, training-data-free approaches like the Deep Image Prior (DIP) do not require clean ground-truth images but suffer from noise overfitting and can be computationally expensive as the network parameters need to be optimized for each measurement set independently. Moreover, DIP-based methods often overlook the potential of learning a prior using a small number of sub-sampled measurements (or degraded images) available during training. In this paper, we propose UGoDIT, an Unsupervised Group DIP via Transferable weights, designed for the low-data regime where only a very small number, M, of sub-sampled measurement vectors are available during training. Our method learns a set of transferable weights by optimizing a shared encoder and M disentangled decoders. At test time, we reconstruct the unseen degraded image using a DIP network, where part of the parameters are fixed to the learned weights, while the remaining are optimized to enforce measurement consistency. We evaluate UGoDIT on both medical (multi-coil MRI) and natural (super resolution and non-linear deblurring) image recovery tasks under various settings. Compared to recent standalone DIP methods, UGoDIT provides accelerated convergence and notable improvement in reconstruction quality. Furthermore, our method achieves performance competitive with SOTA DM-based and supervised approaches, despite not requiring large amounts of clean training data.

The Dual Power of Interpretable Token Embeddings: Jailbreaking Attacks and Defenses for Diffusion Model Unlearning

Despite the remarkable generalization capabilities of diffusion models, recent studies have shown that these models can memorize and generate harmful content when prompted with specific text instructions. Although fine-tuning approaches have been developed to mitigate this issue by unlearning harmful concepts, these methods can be easily circumvented through jailbreaking attacks. This indicates that the harmful concept has not been fully erased from the model. However, existing attack methods, while effective, lack interpretability regarding why unlearned models still retain the concept, thereby hindering the development of defense strategies. In this work, we address these limitations by proposing an attack method that learns an orthogonal set of interpretable attack token embeddings. The attack token embeddings can be decomposed into human-interpretable textual elements, revealing that unlearned models still retain the target concept through implicit textual components. Furthermore, these attack token embeddings are robust and transferable across text prompts, initial noises, and unlearned models. Finally, leveraging this diverse set of embeddings, we design a defense method applicable to both our proposed attack and existing attack methods. Experimental results demonstrate the effectiveness of both our attack and defense strategies.

An Overview of Low-Rank Structures in the Training and Adaptation of Large Models

The rise of deep learning has revolutionized data processing and prediction in signal processing and machine learning, yet the substantial computational demands of training and deploying modern large-scale deep models present significant challenges, including high computational costs and energy consumption. Recent research has uncovered a widespread phenomenon in deep networks: the emergence of low-rank structures in weight matrices and learned representations during training. These implicit low-dimensional patterns provide valuable insights for improving the efficiency of training and fine-tuning large-scale models. Practical techniques inspired by this phenomenon, such as low-rank adaptation (LoRA) and training, enable significant reductions in computational cost while preserving model performance. In this paper, we present a comprehensive review of recent advances in exploiting low-rank structures for deep learning and shed light on their mathematical foundations. Mathematically, we present two complementary perspectives on understanding the low-rankness in deep networks: (i) the emergence of low-rank structures throughout the whole optimization dynamics of gradient and (ii) the implicit regularization effects that induce such low-rank structures at convergence. From a practical standpoint, studying the low-rank learning dynamics of gradient descent offers a mathematical foundation for understanding the effectiveness of LoRA in fine-tuning large-scale models and inspires parameter-efficient low-rank training strategies. Furthermore, the implicit low-rank regularization effect helps explain the success of various masked training approaches in deep neural networks, ranging from dropout to masked self-supervised learning.

Learning Dynamics of Deep Linear Networks Beyond the Edge of Stability

Deep neural networks trained using gradient descent with a fixed learning rate $\eta$ often operate in the regime of "edge of stability" (EOS), where the largest eigenvalue of the Hessian equilibrates about the stability threshold $2/\eta$. In this work, we present a fine-grained analysis of the learning dynamics of (deep) linear networks (DLNs) within the deep matrix factorization loss beyond EOS. For DLNs, loss oscillations beyond EOS follow a period-doubling route to chaos. We theoretically analyze the regime of the 2-period orbit and show that the loss oscillations occur within a small subspace, with the dimension of the subspace precisely characterized by the learning rate. The crux of our analysis lies in showing that the symmetry-induced conservation law for gradient flow, defined as the balancing gap among the singular values across layers, breaks at EOS and decays monotonically to zero. Overall, our results contribute to explaining two key phenomena in deep networks: (i) shallow models and simple tasks do not always exhibit EOS; and (ii) oscillations occur within top features. We present experiments to support our theory, along with examples demonstrating how these phenomena occur in nonlinear networks and how they differ from those which have benign landscape such as in DLNs.

Understanding Representation Dynamics of Diffusion Models via Low-Dimensional Modeling

This work addresses the critical question of why and when diffusion models, despite being designed for generative tasks, can excel at learning high-quality representations in a self-supervised manner. To address this, we develop a mathematical framework based on a low-dimensional data model and posterior estimation, revealing a fundamental trade-off between generation and representation quality near the final stage of image generation. Our analysis explains the unimodal representation dynamics across noise scales, mainly driven by the interplay between data denoising and class specification. Building on these insights, we propose an ensemble method that aggregates features across noise levels, significantly improving both clean performance and robustness under label noise. Extensive experiments on both synthetic and real-world datasets validate our findings.

Understanding How Nonlinear Layers Create Linearly Separable Features for Low-Dimensional Data

Deep neural networks have attained remarkable success across diverse classification tasks. Recent empirical studies have shown that deep networks learn features that are linearly separable across classes. However, these findings often lack rigorous justifications, even under relatively simple settings. In this work, we address this gap by examining the linear separation capabilities of shallow nonlinear networks. Specifically, inspired by the low intrinsic dimensionality of image data, we model inputs as a union of low-dimensional subspaces (UoS) and demonstrate that a single nonlinear layer can transform such data into linearly separable sets. Theoretically, we show that this transformation occurs with high probability when using random weights and quadratic activations. Notably, we prove this can be achieved when the network width scales polynomially with the intrinsic dimension of the data rather than the ambient dimension. Experimental results corroborate these theoretical findings and demonstrate that similar linear separation properties hold in practical scenarios beyond our analytical scope. This work bridges the gap between empirical observations and theoretical understanding of the separation capacity of nonlinear networks, offering deeper insights into model interpretability and generalization.