The paper introduces EgoGenEval, a benchmark that assesses visual generators’ physical consistency during ego‑motion by measuring Camera Motion Grounding and Scene State Preservation across 1,400 cases and 2,360 target views. It shows that current pose‑free models struggle to maintain both camera motion and scene state, and that pairwise supervision in training does not simultaneously improve these aspects. The authors suggest a trajectory‑centric approach that couples self‑conditioned rollouts with explicit pose and visibility supervision to address these limitations.
Ego2Act is a new benchmark that tests video generation models on goal‑directed, egocentric manipulation tasks. It contains 2,640 videos from 110 real‑world tasks, each requiring multiple steps of object manipulation to achieve a high‑level goal. The benchmark includes Ego2ActJudge, a reference‑free evaluation pipeline that better aligns with human judgments of task completion and physics plausibility.
By Patrick Amadeus Irawan, Iskandar Muda Rizky Parlambang, Rava Maulana, Qinrong Cui, Erland Hilman Fuadi, Zayd M. K. Zuhri, Nanda Ryaas Absar, Ahmed Elshabrawy, Wilfried Ariel Mulyawan, Shoubin Yu, Yue Zhang, Mohit Bansal, Alham Fikri Aji
arXiv:2504.15776v2 Announce Type: replace
Abstract: Public autonomous driving datasets underpin the training and benchmarking of perception, mapping, and localization algorithms, yet residual inaccur...
By Quentin Herau, Nathan Piasco, Moussab Bennehar, Luis Rold\~ao, Dzmitry Tsishkou, Bingbing Liu, Cyrille Migniot, Pascal Vasseur, C\'edric Demonceaux
arXiv:2603.25175v2 Announce Type: replace
Abstract: Monocular egocentric 3D pose estimation is difficult because severe foreshortening, self-occlusion, and a restricted field of view often remove the...
By Md Mushfiqur Azam, John Quarles, Kevin Desai
arXiv:2609.21212v1 Announce Type: cross
Abstract: Learned navigation policies typically consume observations as a temporally ordered history, with positional encodings tying each observation to when...
By Beiming Li, Jaime Romero, Jonathan Diller, Vijay Kumar, Alejandro Ribeiro
arXiv:2610.02508v1 Announce Type: new
Abstract: World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an in...
By Fei Zhang, Zhaochong An, Duncan Frost, Yikai Wang, Pengfei Liu, Ya Zhang, Michal Drozdzal, Amir Bar