21 papers
WorldStream: Streaming Interactive 3D Worlds with Hierarchical Planning and Persistent State
Xiaoxiao Ma, Weiyang Jin, Yanwen Ma +11
We present WorldStream, an open-ended 3D world model with three simultaneous capabilities: it extends playable terrain beyond any pre-specified map, acts on open-ended language in…
REEL: Learning to Retrieve, Evaluate, and Evolve Visual Memory for Any Long-Horizon Multi-Shot Video Generation
Hang Xu, Guohui Zhang, Xiaoxiao Ma +7
Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional components: a planner, an adapter…
ExeWorldBench: Benchmarking Code-Based Executable 3D World Modeling
Xinge Peng, Zhen Fang, Ruibing Wang +8
Coding agents are increasingly evolving beyond reproducing what a world looks like toward constructing executable worlds that capture how a world works. This shift calls for execut…
Long-Horizon Audio-Visual Generation for Persistent Stories and Interactive Worlds
Nan Duan, Haoyang Huang, Weiyang Jin +13
Video generation is progressing beyond isolated clips toward long-form narratives and interactive worlds, requiring models to preserve identities, follow user controls, and remain…
EchoWM: Open and Enterable Omnimodal World Models
Songchun Zhang, Yaowei Li, Junhao Zhuang +19
We present EchoWM, an omnimodal world model for enterable generative media that responds to continuous navigation while jointly generating 720p video, environmental sound, music an…
VideoCoCo: Code-as-CoT for Physically-Consistent Video Generation via an Agentic Dual-Engine System
Haodong Li, Tianfei Ren, Xiaoxiao Ma +25
Text-to-video models have achieved remarkable visual quality, yet they still struggle to generate physically consistent dynamics because the temporal evolution of a scene must be i…
Poly-OPD: Heterogeneous Multi-Teacher On-Policy Distillation for Capability-Selectable Flow Models
Siming Fu, Haojun Xu, Ruizhe He +9
Leading open text-to-image models often carry complementary strengths: one may lead on preference-aligned aesthetics while another follows compositional instructions more faithfull…
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging
Siming Fu, Zheming Fu, Ruizhe He +7
On-policy distillation, in which a teacher corrects samples that the student itself generates, presupposes that the two models speak the same language: identical VAE latents, match…
FlowAWR: Online Adaptive Flow Reinforcement via Advantage-Weighted Rectification
Zheming Fu, Ruizhe He, Wei Shang +5
Aligning generative flow models on continuous spaces via online reinforcement learning is constrained by intractable trajectory likelihoods. Existing density-approximated policy gr…
AnchorEdit: Maintaining Temporal Consistency in Multi-turn Image Editing via Causal Memory
Hang Xu, Xiaoxiao Ma, Guohui Zhang +7
Multi-turn image editing is essential for iterative design, yet current models often struggle with identity drift and error accumulation over successive steps. While existing resea…
Ultra Flash: Scaling Real-Time Streaming Video Generation to High Resolutions
Xin Lu, Luxury, Jie Huang +27
While recent autoregressive video diffusion models achieve remarkable streaming quality, they remain confined to low resolutions (e.g., 480P), leaving efficient, scalable, real-tim…
Kwai Keye-VL-2.0 Technical Report
Kwai Keye Team, Bin Wen, Changyi Liu +50
We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding and agentic intelligence. To…
OmniNFT: Modality-wise Omni Diffusion Reinforcement for Joint Audio-Video Generation
Guohui Zhang, XiaoXiao Ma, Jie Huang +9
Recent advances in joint audio-video generation have been remarkable, yet real-world applications demand strong per-modality fidelity, cross-modal alignment, and fine-grained synch…
MAR-GRPO: Stabilized GRPO for AR-diffusion Hybrid Image Generation
Xiaoxiao Ma, Jiachen Lei, Tianfei Ren +6
Reinforcement learning (RL) has been successfully applied to autoregressive (AR) and diffusion models. However, extending RL to hybrid AR-diffusion frameworks remains challenging d…
Drift-AR: Single-Step Visual Autoregressive Generation via Anti-Symmetric Drifting
Zhen Zou, Xiaoxiao Ma, Mingde Yao +3
Autoregressive (AR)-Diffusion hybrid paradigms combine AR's structured semantic modeling with diffusion's high-fidelity synthesis, yet suffer from a dual speed bottleneck: the sequ…
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…
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…
EDPC: Accelerating Lossless Compression via Lightweight Probability Models and Decoupled Parallel Dataflow
Zeyi Lu, Xiaoxiao Ma, Yujun Huang +4
The explosive growth of multi-source multimedia data has significantly increased the demands for transmission and storage, placing substantial pressure on bandwidth and storage inf…