10 papers
Reinforcement Learning without Ground-Truth Solutions can Improve LLMs
Yingyu Lin, Qiyue Gao, Nikki Lijing Kuang +6
Reinforcement learning with verifiable rewards (RLVR) for training LLMs typically rely on ground-truth answers to assign rewards, limiting their applicability to tasks where the gr…
Latent Shadows: The Gaussian-Discrete Duality in Masked Diffusion
Guinan Chen, Xunpeng Huang, Ying Sun +3
Masked discrete diffusion is a dominant paradigm for high-quality language modeling where tokens are iteratively corrupted to a mask state, yet its inference efficiency is bottlene…
On the -Free Inference Complexity of Absorbing Discrete Diffusion
Xunpeng Huang, Yingyu Lin, Nishant Jain +4
Absorbing discrete diffusion has emerged as a dominant framework for discrete data generation. However, a significant disparity remains between its empirical success and theoretica…
Almost Linear Convergence under Minimal Score Assumptions: Quantized Transition Diffusion
Xunpeng Huang, Yingyu Lin, Nikki Lijing Kuang +4
Continuous diffusion models have demonstrated remarkable performance in data generation across various domains, yet their efficiency remains constrained by two critical limitations…
Multi-Step Consistency Models: Fast Generation with Theoretical Guarantees
Nishant Jain, Xunpeng Huang, Yian Ma +1
Consistency models have recently emerged as a compelling alternative to traditional SDE-based diffusion models. They offer a significant acceleration in generation by producing hig…
Capturing Conditional Dependence via Auto-regressive Diffusion Models
Xunpeng Huang, Yujin Han, Difan Zou +2
Diffusion models have demonstrated appealing performance in both image and video generation. However, many works discover that they struggle to capture important, high-level relati…
Faster Sampling via Stochastic Gradient Proximal Sampler
Xunpeng Huang, Difan Zou, Yi-An Ma +2
Stochastic gradients have been widely integrated into Langevin-based methods to improve their scalability and efficiency in solving large-scale sampling problems. However, the prox…
Reverse Transition Kernel: A Flexible Framework to Accelerate Diffusion Inference
Xunpeng Huang, Difan Zou, Hanze Dong +3
To generate data from trained diffusion models, most inference algorithms, such as DDPM, DDIM, and other variants, rely on discretizing the reverse SDEs or their equivalent ODEs. I…
An Improved Analysis of Langevin Algorithms with Prior Diffusion for Non-Log-Concave Sampling
Xunpeng Huang, Hanze Dong, Difan Zou +1
Understanding the dimension dependency of computational complexity in high-dimensional sampling problem is a fundamental problem, both from a practical and theoretical perspective.…
Faster Sampling without Isoperimetry via Diffusion-based Monte Carlo
Xunpeng Huang, Difan Zou, Hanze Dong +2
To sample from a general target distribution beyond the isoperimetric condition, Huang et al. (2023) proposed to perform sampling through reverse diffusion, g…