Junnan Li

STRIDE: Single-Trip-Time Based Reliable Data Transport Protocol for the Reconfigurable Cloud

2019

In a recent development, reconfigurable clouds become a viable solution to overcome practical problems in clouds, such as scalability, delay, etc., by offloading computation tasks to reconfigurable hardware, FPGA. Several existing techniques, such as TCP/IP …

DivideMix: Learning with Noisy Labels as Semi-supervised Learning

2020 · arXiv (Cornell University)

Deep neural networks are known to be annotation-hungry. Numerous efforts have been devoted to reducing the annotation cost when learning with deep networks. Two prominent directions include learning with noisy labels and semi-supervised learning by …

BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models

2023 · arXiv (Cornell University)

The cost of vision-and-language pre-training has become increasingly prohibitive due to end-to-end training of large-scale models. This paper proposes BLIP-2, a generic and efficient pre-training strategy that bootstraps vision-language pre-training from off-the-shelf frozen pre-trained image …

CodeT5+: Open Code Large Language Models for Code Understanding and Generation

2023

Large language models (LLMs) pretrained on vast source code have achieved prominent progress in code intelligence. However, existing code LLMs have two main limitations. First, they often adopt a specific architecture (encoder-only or decoder-only) or …