15 papers
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…
Just-In-Time Scene Graph Growth: Combating Perceptual Saturation in Long-Horizon Robotics
Yue Chang, Rufeng Chen, Yifan Tian +7
While 3D Scene Graphs (3DSGs) provide crucial structured representations for embodied agents, conventional Ahead-of-Time, "build-everything-then-filter" pipelines conflict with the…
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…
Deconstructing Spatial Complexity: Hierarchical Decomposition for LLM Spatial Reasoning
Yi Wang, Haojie Lu, Zhaofan Zhang +2
LLMs have shown remarkable proficiency in general language understanding and reasoning. However, they consistently underperform in spatial reasoning that severely limits their appl…
A Residual-Subspace Constraint Framework for Fourier Ptychographic Microscopy
Sui-peng Wang, Si-yi Xie, Chang-tao Cai +2
The reconstruction fidelity of computational optical imaging is fundamentally constrained by the model-reality gap, i.e., the inevitable discrepancy between idealized forward model…
SAM-Sode: Towards Faithful Explanations for Tiny Bacteria Detection
Wanying Tan, Shuo Yan, Dazhi Huang +7
Interpretability in object detection provides crucial confidence support for clinical auxiliary diagnosis. However, in tiny bacteria detection, traditional explanation methods ofte…
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…
Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
Rufeng Chen, Zhaofan Zhang, Zhejiang Yang +2
Offline safe reinforcement learning often requires policies to adapt at deployment time to safety budgets that vary across episodes or change within a single episode. While diffusi…
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…
Robust Conditional Conformal Prediction via Branched Normalizing Flow
Rui Xu, Xingyuan Chen, Wenxing Huang +4
Conformal prediction (CP) constructs prediction sets with marginal coverage guarantees under the assumption that the calibration and test distributions are identical. However, unde…
Attribution-Guided Continual Learning for Large Language Models
Yazheng Liu, Yuxuan Wan, Rui Xu +3
Large language models (LLMs) often suffer from catastrophic forgetting in continual learning: after learning new tasks sequentially, they perform worse on earlier tasks. Existing m…
Geometry-Calibrated Conformal Abstention for Language Models
Rui Xu, Yi Chen, Sihong Xie +1
When language models lack relevant knowledge for a given query, they frequently generate plausible responses that can be hallucinations, rather than admitting being agnostic about…
GFM4GA: Graph Foundation Model for Group Anomaly Detection
Jiujiu Chen, Weijun Zeng, Shaofeng Hu +2
Group anomaly detection is crucial in many network applications, but faces challenges due to diverse anomaly patterns. Motivated by the success of large language models (LLMs) in n…
RAG-3DSG: Enhancing 3D Scene Graphs with Re-Shot Guided Retrieval-Augmented Generation
Yue Chang, Rufeng Chen, Zhaofan Zhang +3
Open-vocabulary 3D Scene Graph (3DSG) can enhance various downstream tasks in robotics by leveraging structured semantic representations, yet current 3DSG construction methods suff…
Perturbation-mitigated USV Navigation with Distributionally Robust Reinforcement Learning
Zhaofan Zhang, Minghao Yang, Sihong Xie +1
The robustness of Unmanned Surface Vehicles (USV) is crucial when facing unknown and complex marine environments, especially when heteroscedastic observational noise poses signific…