research
∙
06/27/2023
CLIPA-v2: Scaling CLIP Training with 81.1 within a $10,000 Budget; An Extra $4,000 Unlocks 81.8
The recent work CLIPA presents an inverse scaling law for CLIP training ...
share
research
∙
05/16/2023
SpecInfer: Accelerating Generative LLM Serving with Speculative Inference and Token Tree Verification
The high computational and memory requirements of generative large langu...
research
∙
01/25/2023
On the Adversarial Robustness of Camera-based 3D Object Detection
In recent years, camera-based 3D object detection has gained widespread ...
research
∙
09/06/2022
Bag of Tricks for FGSM Adversarial Training
Adversarial training (AT) with samples generated by Fast Gradient Sign M...
research
∙
06/30/2022
InsMix: Towards Realistic Generative Data Augmentation for Nuclei Instance Segmentation
Nuclei Segmentation from histology images is a fundamental task in digit...
research
∙
05/10/2022
Gamma and Vega Hedging Using Deep Distributional Reinforcement Learning
We use deep distributional reinforcement learning (RL) to develop a hedg...
research
∙
02/06/2020
Value of Information Analysis via Active Learning and Knowledge Sharing in Error-Controlled Adaptive Kriging
Large uncertainties in many phenomena of interest have challenged the re...
research
∙
01/17/2019
