33 citations · 152 across the 18 of their papers we have counts for
18 papers
Semantic IDs for Recommender Systems at Snapchat: Use Cases, Technical Challenges, and Design Choices
Clark Mingxuan Ju, Tong Zhao, Leonardo Neves +15
Effective item identifiers (IDs) are an important component for recommender systems (RecSys) in practice, and are commonly adopted in many use cases such as retrieval and ranking.…
Hamiltonian Score Matching and Generative Flows
Peter Holderrieth, Yilun Xu, Tommi Jaakkola
Classical Hamiltonian mechanics has been widely used in machine learning in the form of Hamiltonian Monte Carlo for applications with predetermined force fields. In this work, we e…
Think While You Generate: Discrete Diffusion with Planned Denoising
Sulin Liu, Juno Nam, Andrew Campbell +4
Discrete diffusion has achieved state-of-the-art performance, outperforming or approaching autoregressive models on standard benchmarks. In this work, we introduce Discrete Diffusi…
DisCo-Diff: Enhancing Continuous Diffusion Models with Discrete Latents
Yilun Xu, Gabriele Corso, Tommi Jaakkola +2
Diffusion models (DMs) have revolutionized generative learning. They utilize a diffusion process to encode data into a simple Gaussian distribution. However, encoding a complex, po…
Particle Guidance: non-I.I.D. Diverse Sampling with Diffusion Models
Gabriele Corso, Yilun Xu, Valentin de Bortoli +2
In light of the widespread success of generative models, a significant amount of research has gone into speeding up their sampling time. However, generative models are often sample…
Restart Sampling for Improving Generative Processes
Yilun Xu, Mingyang Deng, Xiang Cheng +3
Generative processes that involve solving differential equations, such as diffusion models, frequently necessitate balancing speed and quality. ODE-based samplers are fast but plat…
GenPhys: From Physical Processes to Generative Models
Ziming Liu, Di Luo, Yilun Xu +2
Since diffusion models (DM) and the more recent Poisson flow generative models (PFGM) are inspired by physical processes, it is reasonable to ask: Can physical processes offer addi…
Stable Target Field for Reduced Variance Score Estimation in Diffusion Models
Yilun Xu, Shangyuan Tong, Tommi Jaakkola
Diffusion models generate samples by reversing a fixed forward diffusion process. Despite already providing impressive empirical results, these diffusion models algorithms can be f…
PFGM++: Unlocking the Potential of Physics-Inspired Generative Models
Yilun Xu, Ziming Liu, Yonglong Tian +3
We introduce a new family of physics-inspired generative models termed PFGM++ that unifies diffusion models and Poisson Flow Generative Models (PFGM). These models realize generati…
Poisson Flow Generative Models
Yilun Xu, Ziming Liu, Max Tegmark +1
We propose a new "Poisson flow" generative model (PFGM) that maps a uniform distribution on a high-dimensional hemisphere into any data distribution. We interpret the data points a…
Controlling Directions Orthogonal to a Classifier
Yilun Xu, Hao He, Tianxiao Shen +1
We propose to identify directions invariant to a given classifier so that these directions can be controlled in tasks such as style transfer. While orthogonal decomposition is dire…
Learning Representations that Support Robust Transfer of Predictors
Yilun Xu, Tommi Jaakkola
Ensuring generalization to unseen environments remains a challenge. Domain shift can lead to substantially degraded performance unless shifts are well-exercised within the availabl…
Can Subnetwork Structure be the Key to Out-of-Distribution Generalization?
Dinghuai Zhang, Kartik Ahuja, Yilun Xu +2
Can models with particular structure avoid being biased towards spurious correlation in out-of-distribution (OOD) generalization? Peters et al. (2016) provides a positive answer fo…
Anytime Sampling for Autoregressive Models via Ordered Autoencoding
Yilun Xu, Yang Song, Sahaj Garg +4
Autoregressive models are widely used for tasks such as image and audio generation. The sampling process of these models, however, does not allow interruptions and cannot adapt to…
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
Xinwei Sun, Yilun Xu, Peng Cao +4
Fusing data from multiple modalities provides more information to train machine learning systems. However, it is prohibitively expensive and time-consuming to label each modality w…
A Theory of Usable Information Under Computational Constraints
Yilun Xu, Shengjia Zhao, Jiaming Song +2
We propose a new framework for reasoning about information in complex systems. Our foundation is based on a variational extension of Shannon's information theory that takes into ac…
L_DMI: An Information-theoretic Noise-robust Loss Function
Yilun Xu, Peng Cao, Yuqing Kong +1
Accurately annotating large scale dataset is notoriously expensive both in time and in money. Although acquiring low-quality-annotated dataset can be much cheaper, it often badly d…
Max-MIG: an Information Theoretic Approach for Joint Learning from Crowds
Peng Cao, Yilun Xu, Yuqing Kong +1
Eliciting labels from crowds is a potential way to obtain large labeled data. Despite a variety of methods developed for learning from crowds, a key challenge remains unsolved: \em…