11 papers
MARS: Margin-Adversarial Risk-controlled Stopping for Parallel LLM Test-time Scaling
Wenbo Chen, Puheng Li, Mengyang Liu +2
Parallel test-time scaling samples many reasoning traces and majority-votes their answers, improving LLM accuracy but requiring traces to run to completion, incurring substantial c…
One-Step Generative Modeling via Wasserstein Gradient Flows
Jiaqi Han, Puheng Li, Qiushan Guo +3
Diffusion models and flow-based methods have shown impressive generative capability, especially for images, but their sampling is expensive because it requires many iterative updat…
Structured Scaling of AI Discovery Across Diverse Scientific Domains
Haotian Ye, Haowei Lin, Jingyi Tang +30
Scientific discovery often requires many cycles of proposing, testing, and refining candidate solutions. Language models can increasingly participate in these loops, but simply gen…
InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression
Haotian Ye, Qiyuan He, Jiaqi Han +12
Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present…
Adaptive Spectral Feature Forecasting for Diffusion Sampling Acceleration
Jiaqi Han, Juntong Shi, Puheng Li +3
Diffusion models have become the dominant tool for high-fidelity image and video generation, yet are critically bottlenecked by their inference speed due to the numerous iterative…
Data-regularized Reinforcement Learning for Diffusion Models at Scale
Haotian Ye, Kaiwen Zheng, Jiashu Xu +15
Aligning generative diffusion models with human preferences via reinforcement learning (RL) is critical yet challenging. Most existing algorithms are often vulnerable to reward hac…