6 papers · 1 filter
MemoBench: Benchmarking World Modeling in Dynamically Changing Environments
Haoyu Chen, Kaichen Zhou, Hang Hua +11
Video generation models aspire to simulate dynamic environments, and several benchmarks now evaluate memory consistency across frames. However, most assess consistency only while t…
MOSIV: Multi-Object System Identification from Videos
Chunjiang Liu, Xiaoyuan Wang, Qingran Lin +9
We introduce the challenging problem of multi-object system identification from videos, for which prior methods are ill-suited due to their focus on single-object scenes or discret…
Bias Is a Subspace, Not a Coordinate: A Geometric Rethinking of Post-hoc Debiasing in Vision-Language Models
Dachuan Zhao, Weiyue Li, Zhenda Shen +4
Vision-Language Models (VLMs) have become indispensable for multimodal reasoning, yet their representations often encode and amplify demographic biases, resulting in biased associa…
MASIV: Toward Material-Agnostic System Identification from Videos
Yizhou Zhao, Haoyu Chen, Chunjiang Liu +7
System identification from videos aims to recover object geometry and governing physical laws. Existing methods integrate differentiable rendering with simulation but rely on prede…
Total-Editing: Head Avatar with Editable Appearance, Motion, and Lighting
Yizhou Zhao, Chunjiang Liu, Haoyu Chen +6
Face reenactment and portrait relighting are essential tasks in portrait editing, yet they are typically addressed independently, without much synergy. Most face reenactment method…
3DSRBench: A Comprehensive 3D Spatial Reasoning Benchmark
Wufei Ma, Haoyu Chen, Guofeng Zhang +4
3D spatial reasoning is the ability to analyze and interpret the positions, orientations, and spatial relationships of objects within the 3D space. This allows models to develop a…