8 papers
Alaya-EVOKE: From Linear-Scaling Supervision to Endless World
Yuanyang Yin, Gongxuan Wang, Yifan Zhan +3
Interactive world models must support persistent memory, responsive interaction, and long-horizon generation, yet these requirements place conflicting demands on the model. Maintai…
Focal Guidance: Unlocking Controllability from Semantic-Weak Layers in Video Diffusion Models
Yuanyang Yin, Yufan Deng, Shenghai Yuan +3
The task of Image-to-Video (I2V) generation aims to synthesize a video from a reference image and a text prompt. This requires diffusion models to reconcile high-frequency visual c…
MaskFocus: Focusing Policy Optimization on Critical Steps for Masked Image Generation
Guohui Zhang, Hu Yu, Xiaoxiao Ma +3
Reinforcement learning (RL) has demonstrated significant potential for post-training language models and autoregressive visual generative models, but adapting RL to masked generati…
Fast-ARDiff: An Entropy-informed Acceleration Framework for Continuous Space Autoregressive Generation
Zhen Zou, Xiaoxiao Ma, Jie Huang +2
Autoregressive(AR)-diffusion hybrid paradigms combine AR's structured modeling with diffusion's photorealistic synthesis, yet suffer from high latency due to sequential AR generati…
ParaUni: Enhance Generation in Unified Multimodal Model with Reinforcement-driven Hierarchical Parallel Information Interaction
Jiangtong Tan, Lin Liu, Jie Huanng +3
Unified multimodal models significantly improve visual generation by combining vision-language models (VLMs) with diffusion models. However, existing methods struggle to fully bala…
Towards Better & Faster Autoregressive Image Generation: From the Perspective of Entropy
Xiaoxiao Ma, Feng Zhao, Pengyang Ling +6
In this work, we first revisit the sampling issues in current autoregressive (AR) image generation models and identify that image tokens, unlike text tokens, exhibit lower informat…
STAGE: Stable and Generalizable GRPO for Autoregressive Image Generation
Xiaoxiao Ma, Haibo Qiu, Guohui Zhang +4
Reinforcement learning has recently been explored to improve text-to-image generation, yet applying existing GRPO algorithms to autoregressive (AR) image models remains challenging…
Group Critical-token Policy Optimization for Autoregressive Image Generation
Guohui Zhang, Hu Yu, Xiaoxiao Ma +6
Recent studies have extended Reinforcement Learning with Verifiable Rewards (RLVR) to autoregressive (AR) visual generation and achieved promising progress. However, existing metho…