Game engines and coding agents can specify the layout, motion, and camera of a scene, yet turning such coarse structure into realistic video requires a renderer that follows the structure and completes the appearance it leaves open. Existing renderers are tied to the representation of one engine, need tens of denoising...
Guian Fang, Sheng-Ju Qian, Dong-Yue Lu et al.· 1 citation· ⚡1
Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluati...
Dong-Yue Lu, Guian Fang, Hur Lim et al.· 1 citation
Video generators serve as interactive worlds for exploration and simulation, yet realistic and visually appealing frames do not necessarily depict a consistent 3D world. Existing benchmarks assess selected geometric properties or use vision-language models to judge memory and consistency, leaving systematic 3D evaluati...
Dong-Yue Lu, Guian Fang, Hur Lim et al.· 0 citations
Autoregressive robot video world models based on discrete visual tokens remain unreliable over long rollout horizons. Retaining the entire generated history does not necessarily improve prediction quality. We investigate a possible memory-role conflict in Full Context decoding: persistent scene information, recent visu...
Hao Wu, Tian-Yu Shao, Sheng-Ju Qian et al.· 0 citations
Robotic world models predict action-conditioned future scenes, providing a foundation for understanding action outcomes. However, turning alternative predictions into useful learning signals remains challenging: similar candidates limit informative quality comparisons, while diverging trajectories require persistent ma...
Hao Wu, Sheng-Ju Qian, Wei-Yan Wang et al.· 0 citations
MOTIVATION
Single-cell foundation models (scFMs) are transforming computational biology by enabling generalizable, task-agnostic representations for versatile single-cell analysis. Despite their progress in facilitating rapid deployment for downstream tasks, off-the-shelf scFMs still have some overlooked concerns: (I)...
Tian-Yu Liu, Fan Zhang, Jia-Yuan Chen et al.· Bioinformatics· 0 citations
CoverPrune is introduced, a training-free framework that formulates inference-time token pruning as an Optimal Transport (OT) problem, and the Feature-Spatial-Temporal (FST) transport cost and target capacity, along with an efficient Spatial-Guided Greedy Selection (SGS) algorithm to approximate the OT objective.
Peng Ling, Ying-Da Yin, Ling-Ting Zhu et al.· 0 citations
PaW is a Policy and World modeling co-training framework that adds auxiliary WM supervision to the same policy during RL, without changing the inference paradigm, and shows consistent improvements over strong RL baselines across models and RL algorithms.
Ning Lu, Baijiong Lin, Sheng-Cai Liu et al.· arXiv.org· 12 citations· ⚡2
Mask Forcing, a Dual-Noise Masking Rollout strategy that perturbs the AR student self-rollout to mitigate mode collapse induced by reverse-KL mode seeking, improves multiple AR video diffusion distillation methods with higher visual quality efficiently, without incorporating real video data or additional post-training...
Zhuo-Ran Zhao, Sheng-Ju Qian, Tong-Tong Liang et al.· 2 citations
SolarWM, a fully open foundation for building interactive video world models from data preparation through long-horizon inference, is introduced, providing a reproducible and extensible foundation for interactive world-model research.
Jun-Chao Huang, Guian Fang, Sheng-Ju Qian et al.· 12 citations
MemVLN is proposed, a novel VLN framework that achieves state-of-the-art performance with real-time inference efficiency (14 FPS) and introduces Procedural Memory for fast action with a compact vocabulary of atomic mid-level actions to bypass auto-regressive decoding latency.
