Related papers: $Z^2$-Sampling: Zero-Cost Zigzag Trajectories for …

Diffusion models have emerged as a powerful framework in generative modeling, typically relying on optimizing neural networks to estimate the score function via forward SDE simulations. In this work, we propose an alternative method that is…

Any well-behaved generative model over a variable $\mathbf{x}$ can be expressed as a deterministic transformation of an exogenous ('outsourced') Gaussian noise variable $\mathbf{z}$: $\mathbf{x}=f_\theta(\mathbf{z})$. In such a model (\eg,…

Zeroth-order or derivative-free optimization (MeZO) is an attractive strategy for finetuning large language models (LLMs) because it eliminates the memory overhead of backpropagation. However, it converges slowly due to the inherent curse…

Persistence-based topological optimization deforms a point cloud $X \subset \mathbb{R}^d$ by minimizing objectives of the form $L(X) = \ell(\mathrm{Dgm}(X))$, where $\mathrm{Dgm}(X)$ is a persistence diagram. In practice, optimization is…

Although synthetic data is widely promoted as a remedy, its prevailing production paradigm -- one optimizing for statistical smoothness -- systematically removes the long-tail, cognitively grounded irregularities that characterize human…

This paper presents Model-guidance (MG), a novel objective for training diffusion model that addresses and removes of the commonly used Classifier-free guidance (CFG). Our innovative approach transcends the standard modeling of solely data…

With the incorporation of the UNet architecture, diffusion probabilistic models have become a dominant force in image generation tasks. One key design in UNet is the skip connections between the encoder and decoder blocks. Although skip…

Zero-Shot Classification (ZSC) equips the learned model with the ability to recognize the visual instances from the novel classes via constructing the interactions between the visual and the semantic modalities. In contrast to the…

In diffusion and flow-matching generative models, guidance techniques are widely used to improve sample quality and consistency. Classifier-free guidance (CFG) is the de facto choice in modern systems and achieves this by contrasting…

Deep learning increasingly relies on massive data with substantial storage, annotation, and training costs. To reduce costs, coreset selection finds a representative subset of data to train models while ideally performing on par with the…

Existing large-scale zero-shot text-to-speech (TTS) models deliver high speech quality but suffer from slow inference speeds due to massive parameters. To address this issue, this paper introduces ZipVoice, a high-quality…

Learning to sample from intractable distributions over discrete sets without relying on corresponding training data is a central problem in a wide range of fields, including Combinatorial Optimization. Currently, popular deep learning-based…

Diffusion models have emerged as a powerful paradigm for modern generative modeling, demonstrating strong potential for large language models (LLMs). Unlike conventional autoregressive (AR) models that generate tokens sequentially,…

Test-time alignment (TTA) aims to adapt models to specific rewards during inference. However, existing methods tend to either under-optimise or over-optimise (reward hack) the target reward function. We propose Null-Text Test-Time Alignment…

Diffusion models have achieved remarkable success as generative models. However, even a well-trained model can accumulate errors throughout the generation process. These errors become particularly problematic when arbitrary guidance is…

Flow matching has demonstrated strong generative capabilities and has become a core component in modern Text-to-Speech (TTS) systems. To ensure high-quality speech synthesis, Classifier-Free Guidance (CFG) is widely used during the…

Evaluating disfluency removal in speech requires more than aggregate token-level scores. Traditional word-based metrics such as precision, recall, and F1 (E-Scores) capture overall performance but cannot reveal why models succeed or fail.…

Diffusion models has emerged as a powerful framework for tasks like image controllable generation and dense prediction. However, existing models often struggle to capture underlying semantics (e.g., edges, textures, shapes) and effectively…

Zero-Shot Learning is an important paradigm within General-Purpose Artificial Intelligence Systems, particularly in those that operate in open-world scenarios where systems must adapt to new tasks dynamically. Semantic spaces play a pivotal…

Accurate semantic segmentation models typically require significant computational resources, inhibiting their use in practical applications. Recent works rely on well-crafted lightweight models to achieve fast inference. However, these…