5 papers
SPOC-SQL: Stage-wise Preference Optimization for Controllable Text-to-SQL
Yingnan Chen, Chun Ding, Tianshi Xu +2
Text-to-SQL aims to translate natural language questions into executable SQL queries over relational databases, requiring multi-stage structured reasoning over database schemas and…
RoboSynChallenge: Mastering Real-World Dexterity via Generalizing Synthesized Manipulation Skills
Runyi Zhao, Ruixin Wu, Chengkun Li +15
Achieving generalizable robotic manipulation remains a central challenge in embodied intelligence. Despite rapid advances in model architectures and learning algorithms, progress i…
Vid2WAM: Distilling Video Diffusion Priors into World Action Models
Chenhao Qiu, Ruixiang Wang, Runyi Zhao +7
World Action Models (WAMs) improve robot policy learning by jointly modeling future visual dynamics and actions. However, their scalability and generalization remain constrained by…
LoopVLA: cross-subtask event memory for looped task execution
Shoujing Zhu, Zhenyang Liu, Fungmiu Wang +6
Repetitive tasks are common in real-world manipulation, yet current vision-language-action (VLA) policies remain unreliable for repeated actions. We present LoopVLA, a cross-subtas…
Say, Dream, and Act: Learning Video World Models for Instruction-Driven Robot Manipulation
Songen Gu, Yunuo Cai, Tianyu Wang +2
Robotic manipulation requires anticipating how the environment evolves in response to actions, yet most existing systems lack this predictive capability, often resulting in errors…