58 citations · 93 across the 10 of their papers we have counts for
11 papers
Divergent Paths: Learning an Outcome-Predictive Representation of LLM Agent Trajectories
Alexander Gill, Guram Gogia, Francisco Guzmán
In this work, we reframe agentic trajectories as paths through a shared embedding space of actions and environmental observations. We show that successful and failed rollouts of th…
VLingNav: Embodied Navigation with Adaptive Reasoning and Visual-Assisted Linguistic Memory
Shaoan Wang, Yuanfei Luo, Xingyu Chen +6
VLA models have shown promising potential in embodied navigation by unifying perception and planning while inheriting the strong generalization abilities of large VLMs. However, mo…
Plug-and-Play Homeostatic Spark: Zero-Cost Acceleration for SNN Training Across Paradigms
Rui Chen, Xingyu Chen, Yaoqing Hu +3
Spiking neural networks offer event driven computation, sparse activation, and hardware efficiency, yet training often converges slowly and lacks stability. We present Adaptive Hom…
LET-US: Long Event-Text Understanding of Scenes
Rui Chen, Xingyu Chen, Shaoan Wang +2
Event cameras output event streams as sparse, asynchronous data with microsecond-level temporal resolution, enabling visual perception with low latency and a high dynamic range. Wh…
UC-OWOD: Unknown-Classified Open World Object Detection
Zhiheng Wu, Yue Lu, Xingyu Chen +3
Open World Object Detection (OWOD) is a challenging computer vision problem that requires detecting unknown objects and gradually learning the identified unknown classes. However,…
HybrUR: A Hybrid Physical-Neural Solution for Unsupervised Underwater Image Restoration
Shuaizheng Yan, Xingyu Chen, Zhengxing Wu +2
Robust vision restoration of underwater images remains a challenge. Owing to the lack of well-matched underwater and in-air images, unsupervised methods based on the cyclic generat…
Reveal of Domain Effect: How Visual Restoration Contributes to Object Detection in Aquatic Scenes
Xingyu Chen, Yue Lu, Zhengxing Wu +2
Underwater robotic perception usually requires visual restoration and object detection, both of which have been studied for many years. Meanwhile, data domain has a huge impact on…
Rethinking Temporal Object Detection from Robotic Perspectives
Xingyu Chen, Zhengxing Wu, Junzhi Yu +1
Video object detection (VID) has been vigorously studied for years but almost all literature adopts a static accuracy-based evaluation, i.e., average precision (AP). From a robotic…
Joint Anchor-Feature Refinement for Real-Time Accurate Object Detection in Images and Videos
Xingyu Chen, Junzhi Yu, Shihan Kong +2
Object detection has been vigorously investigated for years but fast accurate detection for real-world scenes remains a very challenging problem. Overcoming drawbacks of single-sta…
Temporally Identity-Aware SSD with Attentional LSTM
Xingyu Chen, Junzhi Yu, Zhengxing Wu
Temporal object detection has attracted significant attention, but most popular detection methods cannot leverage rich temporal information in videos. Very recently, many algorithm…
Towards Real-Time Advancement of Underwater Visual Quality with GAN
Xingyu Chen, Junzhi Yu, Shihan Kong +3
Low visual quality has prevented underwater robotic vision from a wide range of applications. Although several algorithms have been developed, real-time and adaptive methods are de…