STEPS is proposed, a selective OPSD framework that controls the location, direction, and duration of distillation that improves mean accuracy over GRPO and support brief, targeted self-distillation as an efficient complement to reward-driven reasoning training.
Jia-Xuan Wang, Xuan-Xin Ouyang, Z. Chen et al.· 15 citations
Spatio-Temporal Event Graph Navigation is proposed, a training-free framework that extends conventional scene graphs into spatio-temporal event graphs along complementary spatial and temporal axes and demonstrates that event-driven spatio-temporal representations improve navigation reliability and cross-subtask experie...
Yang Chen, Zhen-Yu Huang, Wenbo Fu et al.· 2 citations
External skills provide domain knowledge and procedures without updating model parameters, but flat collections obscure skill applicability, dependencies, and composition. Graphs organize skills into addressable nodes and explicit relations, supporting selection and composition. Yet existing skill-graph methods use thi...
LookStep is proposed, a unified end-to-end framework that combines Language Centric Future State Modeling and Event Driven Rolling Memory that uses language labels to generate coarse-grained navigation progress and future states for each candidate action, while autonomously deciding whether to write each observation in...
Kun-Yang Yu, Ying-Zhe Li, Hongyu Xu et al.· 2 citations
Vision-Language Navigation (VLN) requires an embodied agent to follow natural-language instructions in unseen environments. Recent progress has been largely driven by Multimodal Large Language Models (MLLMs). Existing methods follow a next-step action prediction paradigm, supervising only the expert action, which requi...
Kun-Yang Yu, Ying-Zhe Li, Hongming Xu et al.· 0 citations
This paper combines symbolic regression with LLMs for feature engineering (SymboLLM-FE) to solve the dual challenges of poor interpretability and numerous iterations by employing a statistical prior-grounded LLM refinement mechanism and single-digit LLM calls.
Zi-Jian Cheng, Zi-Yi Jia, Zhi Zhou et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.