Recent advances in interactive world models have made it possible to generate controllable, dynamic environments from action inputs. Yet current models struggle to maintain coherence beyond roughly one minute of rollout, a limitation rooted not in model capacity but in the scarcity of long-horizon training data. Existi...
Kang He, Wen-Shuo Peng, Chuan-Hao Li et al.· 1 citation
Enzyme function annotation and the identification of candidate enzymes for a given reaction are essential steps in connecting genomic information to biochemical reaction networks. However, existing methods rely on sequence or structural similarity or on training with known enzyme--reaction pairs, making it difficult to...
Yi-Fan Chang, Yun-Ze Li, Fei-Fei Jiang et al.· 0 citations
The Chinese idiom"kou mi fu jian"("honeyed words, hidden daggers") names speech that is polite in form but hostile in function. We present ZhenhuanBench, a 1,592-item benchmark built from expert commentary on Empresses in the Palace, covering speaker intent, emotion-language mismatch, and per-listener uptake. Text-only...
Cai-Xin Kang, Si-Tong Gong, Tian-Yu Yan et al.· 0 citations
Recent 3D world models generate photorealistic, explorable scenes that remain frozen in time. OuroWorld is a mask-free framework that turns any static 3D Gaussian Splatting scene into a 3D cinemagraph: a dynamic scene with vivid, diverse motion looping seamlessly from any viewpoint. A vision-language model infers plaus...
You-Zhe Xie, Ting-Wei Chou, Yu-Hsuan Li et al.· 0 citations
Language-guided panoramic video generation benefits various downstream applications, such as interactive 3D scene exploration, virtual reality experiences, and embodied agent training. Existing panoramic generators follow predefined trajectories, and interactive world models act through low-level actions in perspective...
Yun-Heng Liu, Zi-Qi Cai, Si-Qi Yang et al.· 0 citations
We present FloodDiffusion 2 (FD2), an efficient and controllable framework that builds upon FloodDiffusion (FD1), a state-of-the-art streaming motion generation model. While FD1 produces plausible motion, it suffers from low efficiency and limited controllability, as its attention design requires repeated computation o...
Yi-Yi Cai, Yu-Han Wu, Kun-Hang Li et al.· 0 citations
3D editing methods are usually tested on a single edit, yet an asset is built through a long sequence of revisions, each of which must implement the requested change while leaving everything else unchanged. We introduce EditHero, to our knowledge the first benchmark for long-horizon, part-level 3D editing, with natural...
Rui-Han Yu, Yu-Ju Tsai, Mu-Yao Niu et al.· 0 citations
Interactive panoramic video generation aims to synthesize immersive 360\textdegree{} videos that remain visually coherent while following user-specified camera trajectories during exploration. However, progress is limited by a coupled data-and-model gap: existing panoramic video datasets are often short, weakly annotat...
Jia-Ming Tan, Zhen Li, Shu-Wei Shi et al.· 0 citations
Interactive video world models must maintain broad scene context under camera motion while producing high-fidelity observations with low latency. Existing approaches face a representation trade-off: perspective models operate on local views and must preserve off-screen content over long rollouts, whereas broader spatia...
Jia-Ming Tan, Ming-Liang Zhai, Zhen Li et al.· 2 citations
This work introduces PROWBench, comprising 170 programmatically constructed episodes and 600 proxy videos covering diverse scenes and interactions, and evaluates entity control, long-horizon memory, and adherence to the prescribed timeline and the visual realization of timestamped engine-recorded events.
Zheng-Hui Huang, Gui-Xu Lin, Yu-Ju Tsai et al.· 1 citation
World2Motion, a framework that generates scene-aware 3D human motion and corresponding video from a single image and a text prompt, and proposes a shift-decoupled noise schedule that assigns different noise levels to video and motion through shared denoising progress, reducing motion jitter.
Fang-Yuan Tu, Xiang-Yue Zhang, Yi-Yi Cai et al.· 0 citations
Triangular Resampling is introduced, a post-training method for mitigating long-horizon error accumulation in motion diffusion models that addresses the mismatch between ground-truth-derived training windows and model-generated inference states.
Kun-Hang Li, Yi-Yi Cai, Xiang-Yue Zhang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
