4 papers
PanoWorld: Towards Spatial Supersensing in 360 Panorama World
Changpeng Wang, Xin Lin, Junhan Liu +5
Multimodal large laboratory models (MLLMs) still struggle with spatial understanding under the dominant perspective-image paradigm, which inherits the narrow field of view of human…
All Circuits Lead to Rome: Rethinking Functional Anisotropy in Circuit and Sheaf Discovery for LLMs
Xi Chen, Mingyu Jin, Jingcheng Niu +7
In this paper, we present empirical and theoretical evidence against a central but largely implicit assumption in circuit and sheaf discovery (CSD), which we term the Functional An…
From Illusion to Intention: Visual Rationale Learning for Vision-Language Reasoning
Changpeng Wang, Haozhe Wang, Xi Chen +6
Recent advances in vision-language reasoning underscore the importance of thinking with images, where models actively ground their reasoning in visual evidence. Yet, prevailing fra…
ROSE: Remove Objects with Side Effects in Videos
Chenxuan Miao, Yutong Feng, Jianshu Zeng +7
Video object removal has achieved advanced performance due to the recent success of video generative models. However, when addressing the side effects of objects, e.g., their shado…