arXiv：cs.CL· Peng Xie, Amr Alanwar·· 6 小时前AI 评分54
视频世界模型对隐藏物体保持多少持久性：V-JEPA 2 追踪不等于永久性
Tracking Is Not Permanence: What Video World Models Keep of a Hidden Object
AI 导读
arXiv 论文（arXiv:2610.07355）研究冻结的 V-JEPA 2 视频世界模型对不可见物体的表征：编码器能以 1.00 读出物体存在、闭合容器内容可解码 3.5 s。
正文
Abstract:Video world models track objects they can see; we ask what they keep of objects they cannot. We hide an object from a frozen V-JEPA 2 predictor and compare its prediction for the hidden region with the encoder's representation of two worlds that differ only inside that region. The predictor's decision keeps a stationary object in part and one carried inside a container not at all, and loses a moving one within 0.3 s (0.5 s under V-JEPA's own tube mask; ViT-H keeps it to 1.1 s at pretraining's 90% masking ratio); in projection a trace remains, below the midpoint, at 14-60% of what a baseline copying the last view retains. The information is there: the encoder reads the object's presence at 1.00 and keeps a closed container's contents decodable for 3.5 s, while the predictor's output, read with the encoder's own probe, contains the ball in 2% of scenes once the box has been closed for half a second. On rendered scenes, permanence is missing on the predictor's side, and training installs it cheaply as a prior: three thousand predictor-only steps on synthetic containers take this belief from 0.05 to 1.00 against two matched controls. They also raise IntPhys-2019 from 84.2% to 93.3%, but so does a curriculum without containers, and which training habit the benchmark credits changes with its scoring rule. Continued training with tube masks produces 1.1-1.6 s of moving-object carry-over on manipulation and internet-style video, so the deficit is not intrinsic to latent prediction. VideoMAE keeps almost nothing, and Cosmos's next-token prediction keeps a stationary hidden object but not one carried inside a moving container.
| Subjects: | Computer Vision and Pattern Recognition (cs.CV); Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.07355 [cs.CV] |
| (or arXiv:2610.07355v1 [cs.CV] for this version) | |
| https://doi.org/10.48550/arXiv.2610.07355 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Peng Xie [view email]
[v1]
Mon, 5 Oct 2026 20:22:43 UTC (157 KB)
来源：arXiv：cs.CL · arxiv.org