4 papers
HyperDCM: Dynamic Cluster Memory Replay in Hyperbolic Space for Continual Robotic Navigation Across Scenes
Zhengfei Lu, Jian Yang, Muyu Wang +7
Continual learning in visual navigation remains challenging due to catastrophic forgetting and the difficulties associated with adapting to diverse and evolving environments. To ad…
The Sword, Shield, and Achilles' Heel: Characterizing the Linguistic Inductive Bias of Large Language Models for Spatial Reasoning in Navigation Planning
Xudong Zhang, Jian Yang, Shengkai Wang +5
Large Language Model (LLM)-based navigation systems commonly construct explicit spatial representations (e.g., topological graphs, semantic raster maps) and translate them into tex…
SENSE: Semantic Embedding Navigation with Soft-gated Evaluation for Retrieval-based Speculative Decoding
Shaowen Chen, Zhicheng Liao, Hongwei Wang
Speculative Decoding (SD) accelerates Large Language Model (LLM) inference by employing a lightweight draft model to propose candidate tokens, which are verified in parallel by the…
Stop Wasting Your Tokens: Towards Efficient Runtime Multi-Agent Systems
Fulin Lin, Shaowen Chen, Ruishan Fang +2
While Multi-Agent Systems (MAS) excel at complex tasks, their growing autonomy with operational complexity often leads to critical inefficiencies, such as excessive token consumpti…