8 papers
Capek 0.5: An Execution-Centric Vision-Language Model for Embodied Intelligence
Ying Chen, Weizhen Li, Zhe Hu +7
Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution is inherently iterative: each action reshapes the scene and physical state…
Athena-Brain Technical Report: An Efficient Robot Brain for General Intelligence and Embodied Interaction
Jialian Li, Junhong Liu, Yuchen Cao +6
Large language models (LLMs) have demonstrated remarkable capabilities in language understanding, reasoning, and world knowledge. As embodied agents become increasingly capable, th…
Robots as Tokens: Unified Diffusion Transformer for Coordinated Multi-Robot Trajectory Generation
Ruofei Bai, Jie Chen, Yuxin Cai +3
The success of generative models in language and visual generation has inspired extensive applications to generative robot planning. However, most existing works either focus on si…
Engagement Process: Rethinking the Temporal Interface of Action and Observation
Jialian Li, Yuchen Cao, Junhong Liu +5
Task completion in digital and physical environments increasingly involves complex temporal interaction, where actions and observations unfold over different time scales rather tha…
Done, But Not Sure: Disentangling World Completion from Self-Termination in Embodied Agents
Ying Chen, Lihuang Fang, Rui Jiang +4
Standard embodied evaluations do not independently score whether an agent correctly commits to task completion at episode closure, a capacity we call terminal commitment. Behaviora…
ImagiNav: Scalable Embodied Navigation via Generative Visual Prediction and Inverse Dynamics
Jie Chen, Yuxin Cai, Yizhuo Wang +6
Enabling robots to navigate open-world environments via natural language is critical for general-purpose autonomy. Yet, Vision-Language Navigation has relied on end-to-end policies…
Beyond Imitation: Reinforcement Learning Fine-Tuning for Adaptive Diffusion Navigation Policies
Junhe Sheng, Ruofei Bai, Kuan Xu +5
Diffusion-based robot navigation policies trained on large-scale imitation learning datasets, can generate multi-modal trajectories directly from the robot's visual observations, b…
LaMoGen: Language to Motion Generation Through LLM-Guided Symbolic Inference
Junkun Jiang, Ho Yin Au, Jingyu Xiang +1
Human motion is highly expressive and naturally aligned with language, yet prevailing methods relying heavily on joint text-motion embeddings struggle to synthesize temporally accu…