10 papers
MARC: Mechanism-Aware Reflective Correction for Articulated Object Code Generation
Xiong Yang, Junkun Hao, Zijian Xiao +3
Generating an articulated object from images and text requires more than plausible parts and movable joints: the assembled mechanism must execute the intended motion. This is parti…
What Limits Cross-Task Generalization in World Action Models?
Chen Zhao, Zipeng Ye, Yihan Lin +2
Cross-task generalization remains difficult for world action models (WAMs), even when their predicted futures depict plausible manipulation. This gap can be attributed directly: we…
Beyond Placement and Articulation: Usage-Driven Code Scenes for Embodied Interaction
Zijian Xiao, Zipeng Ye, Jinkun Hao +3
Indoor scene synthesis provides essential environments for embodied AI, robotic manipulation, and simulation-based policy learning. Recent code-based scene generation methods produ…
EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents
Mianqiu Huang, Taofeng Xue, Chong Peng +13
Computer-use agents must solve long-horizon tasks through repeated interaction with partially observable, multimodal desktop environments. Although imitation learning and offline t…
USS: Unifying Spatial-Semantic Prompting for End to End Embodied Visual Tracking
Yuchen Xie, Xinyu Zhou, Kuangji Zuo +4
Embodied Visual Tracking (EVT) requires an agent to continuously follow a designated target while moving through dynamic environments. Existing embodied tracking methods generally…
LongCat-Flash-Thinking-2601 Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +162
We introduce LongCat-Flash-Thinking-2601, a 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model with superior agentic reasoning capability. LongCat-Flash-Thi…
EvoCUA: Evolving Computer Use Agents via Learning from Scalable Synthetic Experience
Taofeng Xue, Chong Peng, Mianqiu Huang +13
The development of native computer-use agents (CUA) represents a significant leap in multimodal AI. However, their potential is currently bottlenecked by the constraints of static…
Look, Zoom, Understand: The Robotic Eyeball for Embodied Perception
Jiashu Yang, Yifan Han, Yucheng Xie +2
In embodied AI, visual perception should be active rather than passive: the system must decide where to look and at what scale to sense to acquire maximally informative data under…
Introducing LongCat-Flash-Thinking: A Technical Report
Meituan LongCat Team, Anchun Gui, Bei Li +122
We present LongCat-Flash-Thinking, an efficient 560-billion-parameter open-source Mixture-of-Experts (MoE) reasoning model. Its advanced capabilities are cultivated through a metic…
EgoLoc: A Generalizable Solution for Temporal Interaction Localization in Egocentric Videos
Junyi Ma, Erhang Zhang, Yin-Dong Zheng +3
Analyzing hand-object interaction in egocentric vision facilitates VR/AR applications and human-robot policy transfer. Existing research has mostly focused on modeling the behavior…