7 papers
Visual Para-Thinker++: A Single-Policy Multi-Agent Framework for Visual Reasoning
Haoran Xu, Hongyu Wang, Yifei Gao +4
Visual reasoning requires integrating evidence distributed across regions, attributes, and relations, making single-chain reasoning prone to early perceptual commitment and halluci…
SCOPE: Simulating Cross-game Operations in Playable Environments for FPS World Models
Zizhao Tong, Yeying Jin, Hongfeng Lai +11
Interactive world models for first-person shooter (FPS) games must resolve high-frequency overlapping control signals at every frame without disrupting unaffected regions. Existing…
ReactiveGWM: Flexible Control and NPC Reactivity in Game World Models
Zeqing Wang, Danze Chen, Zhaohu Xing +4
Existing game world models typically adopt role-specific interactions, where player and NPC roles are bound to fixed characters. This limits their flexibility in multi-character ga…
Incantation: Natural Language as the Action Interface for Multi-Entity Video World Models
Shangwen Zhu, Qianyu Peng, Zhao Pu +12
Modern interactive video world models have achieved impressive visual fidelity, yet lack fine-grained multi-entity control and cross-entity, cross-world generalization. We trace th…
Visual Para-Thinker: Divide-and-Conquer Reasoning for Visual Comprehension
Haoran Xu, Hongyu Wang, Jiaze Li +5
Existing LLM test-time scaling laws emphasize the emergence of self-reflective behaviors through extended reasoning length. Nevertheless, this vertical scaling strategy often encou…
Vision Also You Need: Navigating Out-of-Distribution Detection with Multimodal Large Language Model
Haoran Xu, Yanlin Liu, Zizhao Tong +8
Out-of-Distribution (OOD) detection is a critical task that has garnered significant attention. The emergence of CLIP has spurred extensive research into zero-shot OOD detection, o…
Fidelity-Aware Data Composition for Robust Robot Generalization
Zizhao Tong, Di Chen, Sicheng Hu +6
Generalist robot policies trained on large-scale, visually homogeneous datasets can be susceptible to shortcut learning, which impairs their out-of-distribution (OOD) generalizatio…