6 papers · 1 filter
WorldDynCache: Risk-Controlled Latent Dynamics Approximation for Diffusion World Model
Leyang Chen, Junyi Wu, Shaoqiu Zhang +1
Diffusion world models generate high-quality futures, but re- peated transformer evaluations make inference prohibitively slow. Existing caches reuse intermediate features, selecti…
MoAKE: Toward Unified All-in-One Action Quality Assessment via Mixture of Action Knowledge Experts
Huangbiao Xu, Huanqi Wu, Xiao Ke +3
Action Quality Assessment (AQA) aims to objectively evaluate performance quality from action videos. Most existing methods follow a ``one-by-one'' paradigm, training a separate mod…
Factorized Spectral Representations for Reinforcement Learning
Junyi Wu, Dan Li
Learning a compact model of the world from interaction data is central to sample-efficient deep reinforcement learning. Spectral representation methods have become the leading para…
Diff-Instruct with Diffused Reward: Towards Principled One-step Generator RL
Junyi Wu, Weijian Luo, Haoyang Zheng +2
Recent advances in one-step text-to-image generation have enabled real-time synthesis with remarkable efficiency and quality. Previous reinforcement learning methods for one-step g…
Elastic-dLLM: Position Preserving Context Compression and Augmentation of Diffusion LLMs
Junyi Wu, Tianchen Zhao, Shaoqiu Zhang +3
Unlike autoregressive models, which generate one token at a time, dLLMs denoise a chunk of [MASK] tokens jointly and sample one or more tokens per step; despite enabling parallel d…
AdaTSQ: Pushing the Pareto Frontier of Diffusion Transformers via Temporal-Sensitivity Quantization
Shaoqiu Zhang, Zizhong Ding, Kaicheng Yang +6
Diffusion Transformers (DiTs) have emerged as the state-of-the-art backbone for high-fidelity image and video generation. However, their massive computational cost and memory footp…