Many Worlds

Follow this topic Ask about this topic

Momentum

1 paper in the last four weeks, against 1 the four weeks before. 0.0% of all new papers.

Jul 6Week of Sep 21

Latest papers 16

All topics

WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon
Sep 28, 2026Haiyu Zhang, Wenqiang Sun, Tengfei Wang +5Video World Models Many Worlds
Can LLMs Discover Scientific Laws in Real and Parallel Worlds?
Sep 1, 2026Yiming Huang, Ziche Liu, Zhuohang Wu +11Scientific Discovery Human-Annotated Benchmark
University of California San Diego · University of California, Irvine · 3Cushing Academy +1
AnyWorld: Factorized Egocentric World Models for Cross-Embodiment Generalization
Aug 29, 2026Cheng Chen, Jerry Bai, Jiacheng Wei +11Cross-Embodiment Transfer World Models
Nanyang Technological University · XPENG Robotics · Zhejiang University +2
OPINE-World: Programmatic World Modeling with Ontology-error-Prioritized Interactive Exploration for ARC-AGI-3
Jul 1, 2026David Courtis, Wenhao Li, Scott SannerWorld Models Many Worlds
Department of Computer Science, University of Toronto
ReWorld: Learning Better Representations for World Action Models
Jun 25, 2026Tianze Xia, Lijun Zhou, Kaixin Xiong +9Efficient World-Action Model World Models
Huazhong University of Science and Technology · Xiaomi EV
Uncertainty Decomposition for Clarification Seeking in LLM Agents
Jun 17, 2026Gregory MatsnevLarge Language Model Uncertainty Clarification
AI Talent Hub, ITMO University Saint Petersburg 197101, Russia
PAIWorld: A 3D-Consistent World Foundation Model for Robotic Manipulation
Jun 16, 2026Yuhang Huang, Xuan Lv, Junyan Xu +25Video World Models Robotic Manipulation
Institute of AI for Industries, Chinese Academy of Sciences
ThousandWorlds: A benchmark for climate emulation of potentially habitable exoplanets
Jun 16, 2026Edward T. Stevenson, Mei Ting Mak, Eric Wolf +4Global Climate Models Exoplanet Atmospheres
University of Cambridge · University of Oxford · University of Colorado Boulder +3
ActWorld: From Explorable to Interactive World Model via Action-Aware Memory
Jun 16, 2026Zhexiao Xiong, Yizhi Song, Hao Kang +11Video World Models Many Worlds
1Washington University in St. Louis · 2Intelligent Creation, ByteDance · *Work done during internship at ByteDance
One Lens, Many Worlds : A Capability-Typed Interface for World-Model Interpretability
Jun 7, 2026Bhavith Chandra Challagundla, Sanskar Pandey, Param Thakkar +7World Models Many Worlds
New York University · Independent Researcher · Veermata Jijabai Technological Institute +5
AnchorWorld: Embodied Egocentric World Simulation with View-based Evolution Customization
Jun 5, 2026Yu Li, Menghan Xia, Gongye Liu +8Video World Models Many Worlds
1Tsinghua University · ∗This work was conducted during the author’s internship at Kling Team, Kuaishou Technology. · 2HUST +3
PiL-World: A Chunk-Wise World Model for VLA Policy-in-the-Loop Evaluation
Jun 4, 2026Chong Ma, Taiyi Su, Jian Zhu +4Flow-Matching Vision-Language-Action Efficient World-Action Model
1Tongji University · 2AIRC, Midea Group
World Machine: Towards Generative World Modeling for Time-Series
May 21, 2026Elton Cardoso do Nascimento, Alexandre da Silva Simões, Esther Luna Colombini +2Many Worlds Energy-Based Transformer
Universidade Estadual de Campinas (UNICAMP), {FEEC, IC} · Universidade Estadual Paulista (UNESP), Instituto de Ciˆencia e Tecnologia, Sorocaba
DeTrack: A Benchmark and Altitude-Aware Dual World Model for Drone-embodied Tracking
May 17, 2026Guyue Hu, Haoming Liu, Siyuan Song +3Autonomous Drones World Models
School of Artificial Intelligence, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, and Anhui Provincial Key Laboratory of Security Artificial Intelligence, Anhui University, Hefei 230601, China · Hefei Si Valley Technology Development Co., Ltd, and also with the Institute of Embodied Intelligence, Anhui University, Hefei 230601, China · School of Computer Science and Technology, State Key Laboratory of Opto-Electronic Information Acquisition and Protection Technology, and Anhui Provincial Key Laboratory of Multimodal Cognitive Computation, Anhui University, Hefei 230601, China
HaM-World: Soft-Hamiltonian World Models with Selective Memory for Planning
May 7, 2026Haoyun Tang, Haodong Cui, Keyao Xu +2World Models Many Worlds
1Xi’an Jiaotong University · 2Huazhong University of Science and Technology · 3Nankai University +1
Evolving Many Worlds: Towards Open-Ended Discovery in Petri Dish NCA via Population-Based Training
Apr 13, 2026Uljad Berdica, Jakob Foerster, Frank Hutter +1Neural Cellular Automata Self-Organization
1FLAIR, University of Oxford · 2ELLIS Institute Tübingen · University of Freiburg +2

Sep 28, 2026, cs.CVJ/K move · Enter open · S save

WorldPlay2: Extending Real-Time Interactive World Models in Control and Horizon

Haiyu Zhang, Wenqiang Sun, Tengfei Wang, Junta Wu+4

Video World Models Many Worlds Long-Horizon Inference Action Space Horizon

Open paper AskPDF arXiv

Interactive world models require responding in real time to versatile controls and maintaining long-horizon consistency. However, modeling heterogeneous controls remains difficult, while explosive contexts and unstable distillation impede achieving both long-horizon consistency and real-time responsiveness. In this paper, we present WorldPlay2, an interactive world model that couples a factorized hybrid control interface with a co-design of compressed memory and stable distillation. 1) Our factorized hybrid control interface integrates frame-aligned action control with structured semantic control that explicitly disentangles scene appearance, character identity, and dynamic semantic events, thereby facilitating effective control learning. 2) To achieve efficient long-horizon modeling, we compress historical contexts into compact memory tokens shared by the autoregressive student and the bidirectional teacher. This design enables clip-wise, memory-conditioned score evaluation instead of jointly processing an entire long rollout, substantially reducing distillation overhead. 3) We further propose Stable Forcing, which initializes the autoregressive student via a few-step strategy and leverages full-rollout replay to preserve the quality of long-horizon rollouts, ensuring robust and stable distillation. Extensive experiments demonstrate the strong generalizability of our model and its superior performance compared to existing methods.

Momentum

Related topics

Latest papers 16