11 papers
Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics
Yue Chang, Rufeng Chen, Yifan Tian +7
The paper introduces JITOMA, a framework that builds 3D scene graphs on demand by using task-driven heatmaps and large language models to activate only relevant parts of the graph,…
Attribution-Guided Continual Learning for Large Language Models
Yazheng Liu, Yuxuan Wan, Rui Xu +3
The paper introduces an attribution-guided continual learning framework for large language models that uses Layer-wise Relevance Propagation to identify important parameters and li…
Towards the Explainability of Temporal Graph Networks via Memory Backtracking and Topological Attribution
Yazheng Liu, Xi Zhang, Sihong Xie +1
Temporal graphs are ubiquitous in real-world applications and Temporal Graph Networks (TGNs) have achieved superior predictive accuracy. Understanding which historical events drive…
LH-AVLN: A Benchmark for Long-Horizon Audio-Visual-Language Navigation
Rufeng Chen, Yue Chang, Zili Shao +5
Embodied navigation is moving toward long-horizon missions, yet existing long-horizon benchmarks are largely acoustically silent, and audio-visual navigation tasks typically focus…
Quantile Geometry Regularization for Distributional Reinforcement Learning
Zhaofan Zhang, Minghao Yang, Rufeng Chen +2
Quantile-based distributional reinforcement learning methods learn return distributions through sampled quantile regression, but their bootstrapped target quantiles may induce dist…
SCPRM: A Schema-aware Cumulative Process Reward Model for Knowledge Graph Question Answering
Jiujiu Chen, Yazheng Liu, Sihong Xie +1
Large language models excel at complex reasoning, yet evaluating their intermediate steps remains challenging. Although process reward models provide step-wise supervision, they of…