~ similar to 2610.08726· 19 results
The paper proposes Continuous Reasoning for Vision-Language-Action (VLA) models, arguing that effective reasoning must be a shared, verifiable internal latent space rather than discrete text tokens, l…
Chaehyun Kim, Chi-Pin Huang, Jisoo Kim, Min-Hung Chen +3 more
This paper introduces ThinkWorld, a VLA learning framework that grounds action reasoning in world dynamics and strengthens it through reinforcement learning with world imagination.
Rahul Sajnani, Diego Romeres, Mingyuan Zhang, Kai Gao +8 more
This paper introduces UniWALM, a unified model that integrates video, action, and language in a single representation, improving manipulation and memory-dependent behavior.
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.
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.
Zheng Lu, Mingqi Gao, Qinlei Xie, Wanqi Zhong +7 more
The paper argues that current embodied planning benchmarks prioritize superficial language prediction over true physical reasoning, introducing new benchmarks and a large-scale dataset to demonstrate…
This paper introduces Act2Answer, a protocol to evaluate embodied vision-language-action models by requiring them to answer through action.
Qiuyue Wang, Mingsheng Li, Jian Guan, Jinhui Ye +36 more
Qwen-VLA introduces a unified embodied foundation model that extends vision-language understanding to continuous action generation, enabling robust, multi-task generalization across diverse robotic ta…
Tianhui Liu, Jie Feng, Zhiheng Zheng, Shengyuan Wang +5 more
The paper introduces SpatialAct, a challenging benchmark that reveals a significant 'reasoning-to-action gap,' showing that current VLMs struggle to maintain coherent spatial understanding and perform…
Mingjian Gao, Wenqiao Zhang, Yuqian Yuan, Yang Dai +8 more
VISUALTHINK-VLA introduces a visual intermediate-reasoning framework that guides action prediction using compact visual evidence, achieving high accuracy and significantly low latency for real-time Vi…
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…
Ruoxuan Zhang, Qiaoqiao Wan, Zhengguang Wang, Chenghao Yu +3 more
The paper introduces MindClaw, a closed-loop framework that enables embodied agents to perform real-time mental-state reasoning and intervene with precision, significantly outperforming standard VLM b…