1 citations · 1 across the 5 of their papers we have counts for
7 papers
Just Respect the Semantics: Image-Token Compression via Pre-LLM Semantic Variable-Resolution Tokenization and In-LLM Relevance Pruning
Tianhao Fu, Austin Wang, Charles Chen +5
Image-token compression must reduce computation without hurting the semantics. We introduce Varest, guided by semantic fungibility: tokens within a coherent semantic region can be…
Synthetic Benchmarks Overstate Forward-Forward Scaling: Real-Data Limits of Layer-Local Training
Yucheng Chen
Forward-Forward (FF) learning [Hinton, 2022] replaces backpropagation with strictly layer-local goodness updates. Recent FF-CNN work has narrowed the gap to BP on 32x32 benchmarks,…
SortScrews: A Dataset and Baseline for Real-time Screw Classification
Tianhao Fu, Bingxuan Yang, Juncheng Guo +2
Automatic identification of screw types is important for industrial automation, robotics, and inventory management. However, publicly available datasets for screw classification ar…
CLIP the Divergence: Language-guided Unsupervised Domain Adaptation
Jinjing Zhu, Yucheng Chen, Lin Wang
Unsupervised domain adaption (UDA) has emerged as a popular solution to tackle the divergence between the labeled source and unlabeled target domains. Recently, some research effor…
eMoE-Tracker: Environmental MoE-based Transformer for Robust Event-guided Object Tracking
Yucheng Chen, Lin Wang
The unique complementarity of frame-based and event cameras for high frame rate object tracking has recently inspired some research attempts to develop multi-modal fusion approache…
Source-Free Cross-Modal Knowledge Transfer by Unleashing the Potential of Task-Irrelevant Data
Jinjing Zhu, Yucheng Chen, Lin Wang
Source-free cross-modal knowledge transfer is a crucial yet challenging task, which aims to transfer knowledge from one source modality (e.g., RGB) to the target modality (e.g., de…
Towards Dynamic and Small Objects Refinement for Unsupervised Domain Adaptative Nighttime Semantic Segmentation
Jingyi Pan, Sihang Li, Yucheng Chen +2
Nighttime semantic segmentation plays a crucial role in practical applications, such as autonomous driving, where it frequently encounters difficulties caused by inadequate illumin…