9 citations · 18 across the 17 of their papers we have counts for
18 papers
Nav-EE: Navigation-Guided Early Exiting for Efficient Vision-Language Models in Autonomous Driving
Haibo Hu, Lianming Huang, Xinyu Wang +4
Vision-Language Models (VLMs) are increasingly applied in autonomous driving for unified perception and reasoning, but high inference latency hinders real-time deployment. Early-ex…
Beyond Semantic Similarity: Reducing Unnecessary API Calls via Behavior-Aligned Retriever
Yixin Chen, Ying Xiong, Shangyu Wu +4
Tool-augmented LLMs invoke external functions to extend their capabilities, but errors in the invocation decision, such as calling a tool when none is needed or omitting a needed c…
AD-EE: Early Exiting for Fast and Reliable Vision-Language Models in Autonomous Driving
Lianming Huang, Haibo Hu, Yufei Cui +4
With the rapid advancement of autonomous driving, deploying Vision-Language Models (VLMs) to enhance perception and decision-making has become increasingly common. However, the rea…
Advancing Multiple Instance Learning with Continual Learning for Whole Slide Imaging
Xianrui Li, Yufei Cui, Jun Li +1
Advances in medical imaging and deep learning have propelled progress in whole slide image (WSI) analysis, with multiple instance learning (MIL) showing promise for efficient and a…
VLM-C4L: Continual Core Dataset Learning with Corner Case Optimization via Vision-Language Models for Autonomous Driving
Haibo Hu, Jiacheng Zuo, Yang Lou +6
With the widespread adoption and deployment of autonomous driving, handling complex environments has become an unavoidable challenge. Due to the scarcity and diversity of extreme s…
RALAD: Bridging the Real-to-Sim Domain Gap in Autonomous Driving with Retrieval-Augmented Learning
Jiacheng Zuo, Haibo Hu, Zikang Zhou +6
In the pursuit of robust autonomous driving systems, models trained on real-world datasets often struggle to adapt to new environments, particularly when confronted with corner cas…
GeneQuery: A General QA-based Framework for Spatial Gene Expression Predictions from Histology Images
Ying Xiong, Linjing Liu, Yufei Cui +4
Gene expression profiling provides profound insights into molecular mechanisms, but its time-consuming and costly nature often presents significant challenges. In contrast, whole-s…
IHC Matters: Incorporating IHC analysis to H&E Whole Slide Image Analysis for Improved Cancer Grading via Two-stage Multimodal Bilinear Pooling Fusion
Jun Wang, Yu Mao, Yufei Cui +2
Immunohistochemistry (IHC) plays a crucial role in pathology as it detects the over-expression of protein in tissue samples. However, there are still fewer machine learning model s…
RAEE: A Robust Retrieval-Augmented Early Exit Framework for Efficient Inference
Lianming Huang, Shangyu Wu, Yufei Cui +6
Deploying large language model inference remains challenging due to their high computational overhead. Early exit optimizes model inference by adaptively reducing the number of inf…
BAHOP: Similarity-based Basin Hopping for A fast hyper-parameter search in WSI classification
Jun Wang, Yu Mao, Yufei Cui +2
Pre-processing whole slide images (WSIs) can impact classification performance. Our study shows that using fixed hyper-parameters for pre-processing out-of-domain WSIs can signific…
ReFusion: Improving Natural Language Understanding with Computation-Efficient Retrieval Representation Fusion
Shangyu Wu, Ying Xiong, Yufei Cui +4
Retrieval-based augmentations (RA) incorporating knowledge from an external database into language models have greatly succeeded in various knowledge-intensive (KI) tasks. However,…
NFL: Robust Learned Index via Distribution Transformation
Shangyu Wu, Yufei Cui, Jinghuan Yu +3
Recent works on learned index open a new direction for the indexing field. The key insight of the learned index is to approximate the mapping between keys and positions with piece-…
A Fast Transformer-based General-Purpose Lossless Compressor
Yu Mao, Yufei Cui, Tei-Wei Kuo +1
Deep-learning-based compressor has received interests recently due to much improved compression ratio. However, modern approaches suffer from long execution time. To ease this prob…
Weight Rescaling: Effective and Robust Regularization for Deep Neural Networks with Batch Normalization
Ziquan Liu, Yufei Cui, Jia Wan +2
Weight decay is often used to ensure good generalization in the training practice of deep neural networks with batch normalization (BN-DNNs), where some convolution layers are inva…
Variational Nested Dropout
Yufei Cui, Yu Mao, Ziquan Liu +5
Nested dropout is a variant of dropout operation that is able to order network parameters or features based on the pre-defined importance during training. It has been explored for:…
Direct Quantization for Training Highly Accurate Low Bit-width Deep Neural Networks
Tuan Hoang, Thanh-Toan Do, Tam V. Nguyen +1
This paper proposes two novel techniques to train deep convolutional neural networks with low bit-width weights and activations. First, to obtain low bit-width weights, most existi…
Improve Generalization and Robustness of Neural Networks via Weight Scale Shifting Invariant Regularizations
Ziquan Liu, Yufei Cui, Antoni B. Chan
Using weight decay to penalize the L2 norms of weights in neural networks has been a standard training practice to regularize the complexity of networks. In this paper, we show tha…
Accelerating Monte Carlo Bayesian Inference via Approximating Predictive Uncertainty over Simplex
Yufei Cui, Wuguannan Yao, Qiao Li +2
Estimating the predictive uncertainty of a Bayesian learning model is critical in various decision-making problems, e.g., reinforcement learning, detecting adversarial attack, self…