works on

From the 1 of 14 linked papers with an AI index.

collaborators

14 papers

cs.LG2026

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…

cs.CV2026

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…

cs.LG2026

Factorized Spectral Representations for Reinforcement Learning

Junyi Wu, Dan Li

The paper introduces FaStR, a method that factorizes the transition kernel of a reinforcement learning environment as a three-way tensor using CP decomposition, learning separate e…

cs.CV2026

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…

cs.LG2026

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…

cs.CV2026

FlashEdit: Decoupling Speed, Structure, and Semantics for Precise Image Editing

Junyi Wu, Zhiteng Li, Haotong Qin +2

Text-guided image editing with diffusion models has achieved remarkable quality but often suffers from prohibitive latency. We introduce \textbf{FlashEdit}, a real-time localized i…