6 papers
STED and Consistency Scoring: A Framework for Evaluating LLM Structured Output Reliability
Guanghui Wang, Jinze Yu, Xing Zhang +5
Large Language Models (LLMs) are increasingly deployed for structured data generation, yet output consistency remains critical for production applications. We introduce a comprehen…
Tracking Moose using Aerial Object Detection
Christopher Indris, Raiyan Rahman, Goetz Bramesfeld +1
Aerial wildlife tracking is critical for conservation efforts and relies on detecting small objects on the ground below the aircraft. It presents technical challenges: crewed aircr…
ABKD: Pursuing a Proper Allocation of the Probability Mass in Knowledge Distillation via --Divergence
Guanghui Wang, Zhiyong Yang, Zitai Wang +3
Knowledge Distillation (KD) transfers knowledge from a large teacher model to a smaller student model by minimizing the divergence between their output distributions, typically usi…
Autoencoder-Based Hybrid Replay for Class-Incremental Learning
Milad Khademi Nori, Il-Min Kim, Guanghui Wang
In class-incremental learning (CIL), effective incremental learning strategies are essential to mitigate task confusion and catastrophic forgetting, especially as the number of tas…
Federated Class-Incremental Learning: A Hybrid Approach Using Latent Exemplars and Data-Free Techniques to Address Local and Global Forgetting
Milad Khademi Nori, Il-Min Kim, Guanghui Wang
Federated Class-Incremental Learning (FCIL) refers to a scenario where a dynamically changing number of clients collaboratively learn an ever-increasing number of incoming tasks. F…
A Survey on Mamba Architecture for Vision Applications
Fady Ibrahim, Guangjun Liu, Guanghui Wang
Transformers have become foundational for visual tasks such as object detection, semantic segmentation, and video understanding, but their quadratic complexity in attention mechani…