14 papers
OneLA: Learning Many Worlds from Latent Actions
Ziyu Zhu, Zhaoxu Sun, Fan Jiang +3
Learning world models across diverse domains calls for a unified control space, yet ac- tion interfaces vary across domains and action annotations are often scarce. Latent ac- tion…
GAD: Geometry Attention Distillation for Consistent Video Generation
Junfeng Ni, Ziyu Zhu, Fan Jiang +7
Video diffusion models generate visually compelling short-term sequences but often struggle to preserve scene geometry and object structure over time. In this paper, we first demon…
LongForcing: Scaling Temporal Manifold Matching for Long-Horizon World Rollout
Ziyu Zhu, Zhaoxu Sun, Fan Jiang +5
Autoregressive video diffusion models have emerged as a foundation for long-horizon world rollout. However, when extended far beyond their training windows, these models suffer fro…
ABot-World-0: Infinite Interactive World Rollout on a Single Desktop GPU
Fan Jiang, Zhaoxu Sun, Mengchao Wang +38
We present ABot-World-0, an action-conditioned video world model for real-time, long-horizon closed-loop interaction, supported by a multi-source data infrastructure spanning AAA g…
WorldRoamBench: An Open-World Benchmark for Long-Horizon Stability of Interactive World Models
Ting-Bing Xu, Jiacheng Sui, Zhe Gao +12
Despite rapid progress in interactive world models (IWMs), short-horizon performance does not establish sustained action following, visual stability, physical plausibility, or memo…
Grounded Forcing: Bridging Time-Independent Semantics and Proximal Dynamics in Autoregressive Video Synthesis
Jintao Chen, Chengyu Bai, Junjun Hu +2
Autoregressive video synthesis offers a promising pathway for infinite-horizon generation but is fundamentally hindered by three intertwined challenges: semantic forgetting from co…
FantasyVLN: Unified Multimodal Chain-of-Thought Reasoning for Vision-Language Navigation
Jing Zuo, Lingzhou Mu, Fan Jiang +3
Achieving human-level performance in Vision-and-Language Navigation (VLN) requires an embodied agent to jointly understand multimodal instructions and visual-spatial context while…
FantasyWorld: Geometry-Consistent World Modeling via Unified Video and 3D Prediction
Yixiang Dai, Fan Jiang, Chiyu Wang +2
High-quality 3D world models are pivotal for embodied intelligence and Artificial General Intelligence (AGI), underpinning applications such as AR/VR content creation and robotic n…
FantasyHSI: Video-Generation-Centric 4D Human Synthesis In Any Scene through A Graph-based Multi-Agent Framework
Lingzhou Mu, Qiang Wang, Fan Jiang +4
Human-Scene Interaction (HSI) seeks to generate realistic human behaviors within complex environments, yet it faces significant challenges in handling long-horizon, high-level task…
FantasyTalking2: Timestep-Layer Adaptive Preference Optimization for Audio-Driven Portrait Animation
MengChao Wang, Qiang Wang, Fan Jiang +1
Recent advances in audio-driven portrait animation have demonstrated impressive capabilities. However, existing methods struggle to align with fine-grained human preferences across…
FantasyPortrait: Enhancing Multi-Character Portrait Animation with Expression-Augmented Diffusion Transformers
Qiang Wang, Mengchao Wang, Fan Jiang +3
Producing expressive facial animations from static images is a challenging task. Prior methods relying on explicit geometric priors (e.g., facial landmarks or 3DMM) often suffer fr…
FantasyTalking: Realistic Talking Portrait Generation via Coherent Motion Synthesis
Mengchao Wang, Qiang Wang, Fan Jiang +5
Creating a realistic animatable avatar from a single static portrait remains challenging. Existing approaches often struggle to capture subtle facial expressions, the associated gl…
FantasyID: Face Knowledge Enhanced ID-Preserving Video Generation
Yunpeng Zhang, Qiang Wang, Fan Jiang +3
Tuning-free approaches adapting large-scale pre-trained video diffusion models for identity-preserving text-to-video generation (IPT2V) have gained popularity recently due to their…
Controllable Longer Image Animation with Diffusion Models
Qiang Wang, Minghua Liu, Junjun Hu +2
Generating realistic animated videos from static images is an important area of research in computer vision. Methods based on physical simulation and motion prediction have achieve…