Embodied vision-language models must answer questions from partial, evolving observations. Their success depends on both the reasoning capability selected and the evidence available to it. Expert routers adapt internal computation, while tool-augmented systems acquire external evidence; choosing these independently can...
Wei-Lin Ruan, Ying-Jie Xu, Yang Wei et al.· 0 citations
Embodied spatial intelligence requires more than visual recognition: models must localize entities, reason about their relations, and express this knowledge in action-relevant forms. Yet joint training can conflate the knowledge needed at different stages because supervision is fragmented across incompatible geometric...
Wei-Lin Ruan, Bo-Han Zhou, Jing-Hao Li et al.· 0 citations
This work presents MedZERO, a self-evolving framework for open-ended medical reasoning that couples an Examiner that generates frontier medical question-option pairs with a Reasoner that solves them through evidence-grounded multi-turn reasoning with external knowledge tools.
Xi-Lin Dang, Wei-Lin Ruan, Xue-Xia Yang et al.· 1 citation
The rapid evolution of text-to-image (T2I) generation models has effectively solved the foundational challenge of raw pixel synthesis, shifting the community's focus toward fulfilling increasingly intricate user requests. While recent agentic image generation workflows enhance static inference with advanced capabilitie...
Harold Haodong Chen, Zhiyu Hou, Wenjie Shu et al.· 4 citations
A literature review around the interfaces connecting contextual evidence to execution, distinguishing four families: context-conditioned policies, geometric demonstration transfer, world-model-based control, and skill- and agent-based execution.
Accurate global Subseasonal-to-Seasonal (S2S) climate forecasting is critical for disaster preparedness and resource management, yet it remains challenging due to chaotic atmospheric dynamics. Despite advances in geometry-aware representations, existing methods do not specify how the zonal and meridional interactions t...
Zi-Yu Zhou, Yu-Chen Fang, Wei-Lin Ruan et al.· 0 citations
This work formulations CPRA as a potential game and construct the potential function based on the objective function of CPRA, laying a theoretical foundation for approximating the Nash equilibrium of this NP-hard problem, and proposes a Game-Theoretic Spatio-Temporal Reinforcement Learning (GSTRL) framework to solve it...
Experiments on LoCoMo and LongMemEval show that MemoryCPT improves the cost-performance trade-off over the evaluated baselines, while ablation and sensitivity analyses characterize the contributions of its components and the effects of key design choices.
Songxin Lei, Kun Ouyang, Wei-Lin Ruan et al.· 1 citation· ⚡1
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.