20 results for “Embodiment alignment”
CS papers onlyHybrid search: Keyword + semantic, ranked by combined score.ⓘ
Want pure semantic search? Try claim verification →
Dong Jing, Tianqi Zhang, Jiaqi Liu, Jinman Zhao +4 more
This paper proposes a two-stage training framework to pretrain action modules with motion priors before Vision-Language-Action (VLA) alignment, improving VLA performance and reducing optimization chal…
Jiaming Liu, Yinxi Wang, Chenyang Gu, Siyuan Qian +14 more
LaST-HD: A novel human-to-robot action learning paradigm that aligns human-hand and robot demonstrations in a shared latent reasoning space.
The paper introduces using frozen, generalist value functions as differentiable surrogates to efficiently optimize and analyze new multi-embodiment robot designs without requiring repeated reinforceme…
Sai Kumar Dwivedi, Federica Bogo, Buğra Tekin, Chenhongyi Yang +5 more
The paper introduces IMAGIN-4D, a diffusion-based HOI generator that decomposes image conditioning spatio-temporally to improve fine-grained interaction control.
This paper organizes embodied data sources for multimodal foundation models into a pyramid, focusing on real-robot, UMI-style, egocentric and exocentric, simulation, and general vision-language data.
Dairu Liu, Zekun Qi, Jiayu Zeng, Ruixi Yu +10 more
The paper introduces HumanTracker, a benchmark for humanoid motion tracking evaluation with 153 hours of optical motion trajectories and HumanScore, a preference-aligned metric for better predicting h…
This paper introduces Align4D, a framework for generating coherent video-3D pairs using any-modal input, achieving state-of-the-art quality and consistency in X-to-4D generation.
Tianqi Liu, Hanfei Zhao, Qifeng Liang, Hui En Pang +11 more
The paper presents Ropedia W0, a world model that enables embodied agents to anticipate action consequences across diverse embodiments.
MyoSem introduces an EMG-action semantic alignment framework that transforms low-level muscle signals into a shared semantic space, enabling bidirectional retrieval between EMG data and natural langua…
Wanhao Niu, Qiyan Ke, Yuan Sun, Hao Sun +4 more
This paper presents EAGG, an embodiment-aligned grasp generator that generalizes across objects and end effectors.
Ruizhi Yuan, Zeqiu Yu, Wei Gao, Wei Chen +2 more
This paper proposes a flow-guided target-space alignment method called FlowAlign that improves instance-level correspondence while preserving target-space structure in multimodal alignment problems.
Yuntian Wang, Zesheng Jia, Yuhui Duan, Qibing Wang +4 more
This paper proposes a new framework, Aligned Refinement Policy (ARP), to learn visuomotor policies for long-horizon manipulation tasks.
The paper proposes a sequence-alignment framework using Soft Dynamic Time Warping to evaluate audio-driven talking-head generation, demonstrating that this approach provides more robust and fair compa…
Nabeela Khan, Bowen Wu, Runwu Shi, Benjamin Yen +4 more
This paper presents a system-level framework to mitigate collisions and improve retargeting of sign language generation outputs for humanoid robot execution.
The paper presents Fed-Universe, a generalizable architecture for decentralized learning that addresses the issue of minority suppression in federated learning.
DiffCrossGait proposes a novel trajectory-level alignment method using latent diffusion to overcome domain discrepancies in 2D-3D gait recognition, achieving state-of-the-art performance.
EMCAR is a no-code platform that enables artists and non-technical individuals to design and program robot interactions.