The paper introduces Constraint-Referenced Strategy (CRS), a method that evaluates manipulation policies by projecting the commanded end-effector twist onto an object's joint axis, thereby distinguishing progress along the joint from off-constraint motion. CRS requires a joint model and a scripted controller but no demonstrations or learned judges. Experiments on 74 simulated articulated objects show that CRS can identify distinct signatures of policy failures and highlight significant off-axis rotation in a door-trained policy compared to a drawer-trained one.
By Baptiste Bonin, Caro Strickland, Audrey Durand
arXiv:2610.08446v1 Announce Type: new
Abstract: Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physi...
By Zhiyuan Qi, Jierui Li, Yifan Shen, Cheng Qian, Jiateng Liu
The paper reports a 2nd place solution for the HANDS 2026 Dexterous Grasp Motion track, targeting the 12‑DoF LinkerHand O6. The method warps a single successful GraspM3 demonstration into a 12‑D trajectory, avoiding step‑by‑step policy generation, and is trained with one‑step PPO across 4,824 objects. It achieved 94.61% success on the easy track and 57.18% on the hard track of the private test set.
By Muneeb A. Khan, Woojin Kim, Shinwoo Kim, Muhammad Munsif, Binod Bhattarai, Seungryul Baek
The paper introduces Artisan, a multi‑agent pipeline that builds on Articraft to generate physically grounded articulated 3D assets. Artisan incorporates physical simulation feedback to ensure attributes such as collision‑free motion, stability under gravity, and accurate mass and material properties. The authors also present a unified benchmark covering spatial fidelity, physical plausibility, downstream task performance, and overall quality, evaluated on 100 reference assets and 100 stability prompts, where Artisan shows competitive spatial fidelity and the lowest collision and highest stability rates among tested models.
By Xudong Cai, Ruijie Zhu, Haoliang Shang, Ruining Li, Marc Pollefeys, Shangzhe Wu, Andrea Vedaldi, Chuanxia Zheng
Multimodal large language models (MLLMs) have made significant progress in visual understanding, but precise 3D spatial reasoning integrated with physical environment remains difficult. Furniture asse...
Masked Generative Motion Planning (MGMP) extends learned trajectory priors by using a masked generative transformer to produce discrete trajectory candidates in parallel and a Geometry‑Guided Token Search (GGTS) to target and evaluate edits based on scene geometry. This approach turns refinement into an efficient search over discrete motion alternatives, allowing route‑level restructuring rather than only local deformation. MGMP achieves high success rates—96% on Ring Maze and 82% repair success on Controlled Route Invalidation—outperforming external baselines by 23–25 percentage points and generalizes to unseen layouts, additional obstacles, unseen geometries, single‑ and dual‑arm planning, and real‑world Baxter tasks.
By Lipeng Zhuang, Yingdong Ru, Shiyu Fan, Edmond S. L. Ho, Gerardo Aragon Camarasa, Paul Henderson