The paper examines latent action models that encode transitions between video frames using algebraic constraints such as additive composition and antisymmetric reversal. It demonstrates that these algebraic consistency conditions do not reliably certify temporal structure, as unconstrained models can achieve similar error reductions and constrained models still outperform unconstrained ones even after temporal pairings are destroyed. The authors find that preserving temporal pairing offers no consistent advantage on downstream tasks and that a direct repair objective yields only marginal improvement, recommending a more rigorous validation protocol.
By Di Wen, Ruodi Zhang, Kailun Yang, Kunyu Peng
arXiv:2609.37297v1 Announce Type: new
Abstract: Cross-skeleton motion generation trains generative models to carry action structure and motion intention from one body to another. Yet a target motion...
By Zhiyuan Li, Wenyan Yang, Pekka Marttinen, Joni Pajarinen
R2M-Bench is a benchmark that evaluates revisit memory in interactive video world models by comparing a revisit pair to two control pairs from the same rollout: a gap‑matched non‑revisit pair and a short‑range pair. It introduces MemoryGain (MG) and Normalized Memory Ratio (NMR) to quantify the revisit advantage over generic temporal stability and normalize it by short‑to‑baseline dynamics. Across 300 instances and seven models, NMR correlates with human judgments and reduces the influence of slow‑motion artifacts, with DreamX‑World‑Memo achieving the highest NMR.
By Qiwen Gu, Bingjie Gao, Rui Chen, Geng Li, Jifan Li, Qishuai Wen, Li Niu, Jing Tang, Xiangxiang Chu, Junqiao Zhao
Slot3R introduces a set‑associative spatial memory that allows multiple states to coexist at the same 3D location, addressing the limitation of Point3R where spatial proximity forces merging of distinct observations. By keeping the pretrained Point3R backbone frozen and adding a bounded sparse readout, Slot3R improves point‑cloud accuracy by up to 72% on benchmark datasets and reduces trajectory error across pose benchmarks, while maintaining real‑time performance up to 1000 frames without exhausting memory.
By Xiyuan Zhang, Yanming Yang, Kaiyuan Xu, Ruibo Li, Chi Zhang
arXiv:2610.22749v1 Announce Type: new
Abstract: Do larger models learn increasingly similar representations of the same world? The Platonic Representation Hypothesis (PRH) predicts that they should,...
By Angus Hoy, Austin Lutterbach, Jasper Chong, Aman Kumar, Michael J. Smith
arXiv:2606. 17536v1 Announce Type: cross Abstract: Generative world models for autonomous driving face two unresolved tensions: heterogeneous control injection, where free-form language, HD-maps, trajectories, and camera poses reside in incompatible representational spaces, and post-hoc cross-view fusion, where per-camera latents fail to encode global 3-D geometry.
By Zijie Meng, Yufei Liu, Chengqian Ma, Zhiyu Li, Jiyuan Liu, Wenhua Nie, Bingcai Wei, Shuqin Chen, Weichen Xu, Jiquan Yuan, Miao Zhang
arXiv:2609.07937v1 Announce Type: cross
Abstract: Structured visual reasoning, such as image puzzles, demands fine-grained visual perception, an ability current Vision Language Models (VLMs) lack. VL...
By Harsha Patnala, Debopriyo Banerjee, Ayush Sunil Munot, Somak Aditya
arXiv:2610.19708v1 Announce Type: new
Abstract: Recent video world models have increasingly adopted 3D memory mechanisms to integrate historical observations into a lightweight and persistent scene r...
By Shuofeng Sun, Wenzhao Zheng, Yunpeng Zhang, Yi Wu, Linqing Zhao, Haibin Yan
arXiv:2606. 09803v1 Announce Type: cross Abstract: We present \textbf{Echo-Memory}, a controlled study of memory mechanisms in action-conditioned world models.
By Wayne King, Zeyue Xue, Yuxuan Bian, Jie Huang, Haoran Li, Yaowei Li, Yaofeng Su, Yuming Li, Haoyu Wang, Shiyi Zhang, Songchun Zhang, Yuwei Niu, Sihan Xu, Junhao Zhuang, Haoyang Huang, Nan Duan
arXiv:2609.25633v1 Announce Type: cross
Abstract: Dynamic 3D Gaussian splats (3DGS) model time-varying scenes using a separate Gaussian set per frame. While neighboring video frames are highly correl...
By Chenjunjie Wang, Zixi Huang, Yao Wang, Jona Ball\'e
arXiv:2608.21402v1 Announce Type: cross
Abstract: World action models (WAMs) jointly denoise future video frames and robot actions, and the video prior is expected to generalize their control. Camera...
By Bingqi Huang, Bingchuan Wei, Yingkai Cai, Zhaokui Wang
Latent visual reasoning (LVR) inserts supervised latent tokens between perception and answer generation in vision-language models (VLMs). The field uses alignment between these latents and their visual targets, i.