Search Results for author:
Found 18 papers, 4 papers with code
Rethinking Kullback-Leibler Divergence in Knowledge Distillation for Large Language Models
Kullback-Leiber divergence has been widely used in Knowledge Distillation (KD) to compress Large Language Models (LLMs).
Electrocardiogram Instruction Tuning for Report Generation
Electrocardiogram (ECG) serves as the primary non-invasive diagnostic tool for cardiac conditions monitoring, are crucial in assisting clinicians.
RoboCodeX: Multimodal Code Generation for Robotic Behavior Synthesis
Robotic behavior synthesis, the problem of understanding multimodal inputs and generating precise physical control for robots, is an important part of Embodied AI.
Ranked #72 on
Visual Question Answering
on MM-Vet
A Spectral Perspective towards Understanding and Improving Adversarial Robustness
Deep neural networks (DNNs) are incredibly vulnerable to crafted, imperceptible adversarial perturbations.
CrossGET: Cross-Guided Ensemble of Tokens for Accelerating Vision-Language Transformers
Although extensively studied for unimodal models, the acceleration for multimodal models, especially the vision-language Transformers, is relatively under-explored.
DyBit: Dynamic Bit-Precision Numbers for Efficient Quantized Neural Network Inference
To accelerate the inference of deep neural networks (DNNs), quantization with low-bitwidth numbers is actively researched.
UPop: Unified and Progressive Pruning for Compressing Vision-Language Transformers
Real-world data contains a vast amount of multimodal information, among which vision and language are the two most representative modalities.
Frequency Regularization for Improving Adversarial Robustness
Deep neural networks are incredibly vulnerable to crafted, human-imperceptible adversarial perturbations.
LiteVL: Efficient Video-Language Learning with Enhanced Spatial-Temporal Modeling
Recent large-scale video-language pre-trained models have shown appealing performance on various downstream tasks.
ODG-Q: Robust Quantization via Online Domain Generalization
To our best knowledge, this work is the first work that trains both quantized and binary neural networks on ImageNet that consistently improve robustness under different attacks.
Compression of Generative Pre-trained Language Models via Quantization
We find that previous quantization methods fail on generative tasks due to the \textit{homogeneous word embeddings} caused by reduced capacity, and \textit{varied distribution of weights}.
What Do Adversarially trained Neural Networks Focus: A Fourier Domain-based Study
We are hopeful this work can shed light on the design of more robust neural networks.
Interpretable Mammographic Image Classification using Case-Based Reasoning and Deep Learning
Compared to other methods, our model detects clinical features (mass margins) with equal or higher accuracy, provides a more detailed explanation of its prediction, and is better able to differentiate the classification-relevant parts of the image.
IAIA-BL: A Case-based Interpretable Deep Learning Model for Classification of Mass Lesions in Digital Mammography
Mammography poses important challenges that are not present in other computer vision tasks: datasets are small, confounding information is present, and it can be difficult even for a radiologist to decide between watchful waiting and biopsy based on a mammogram alone.
FAT: Learning Low-Bitwidth Parametric Representation via Frequency-Aware Transformation
Prior arts often discretize the network weights by carefully tuning hyper-parameters of quantization (e. g. non-uniform stepsize and layer-wise bitwidths), which are complicated and sub-optimal because the full-precision and low-precision models have a large discrepancy.
Dynamic and Static Context-aware LSTM for Multi-agent Motion Prediction
Existing work addressed this challenge by either learning social spatial interactions represented by the positions of a group of pedestrians, while ignoring their temporal coherence (\textit{i. e.} dependencies between different long trajectories), or by understanding the complicated scene layout (\textit{e. g.} scene segmentation) to ensure safe navigation.
MiniMax Entropy Network: Learning Category-Invariant Features for Domain Adaptation
Unlike most existing approaches which employ a generator to deal with domain difference, MMEN focuses on learning the categorical information from unlabeled target samples with the help of labeled source samples.
This Looks Like That: Deep Learning for Interpretable Image Recognition
In this work, we introduce a deep network architecture -- prototypical part network (ProtoPNet), that reasons in a similar way: the network dissects the image by finding prototypical parts, and combines evidence from the prototypes to make a final classification.
