activity
20172024
most citedInstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning

409 citations · 483 across the 10 of their papers we have counts for

collaborators

14 papers

cs.CL2022

Improving the Sample Efficiency of Prompt Tuning with Domain Adaptation

Xu Guo, Boyang Li, Han Yu

Prompt tuning, or the conditioning of a frozen pretrained language model (PLM) with soft prompts learned from data, has demonstrated impressive performance on a wide range of NLP t…

cs.IR20219 cited

Initialization Matters: Regularizing Manifold-informed Initialization for Neural Recommendation Systems

Yinan Zhang, Boyang Li, Yong Liu +2

Proper initialization is crucial to the optimization and the generalization of neural networks. However, most existing neural recommendation systems initialize the user and item em…

cs.CV20216 cited

Noise-resistant Deep Metric Learning with Ranking-based Instance Selection

Chang Liu, Han Yu, Boyang Li +6

The existence of noisy labels in real-world data negatively impacts the performance of deep learning models. Although much research effort has been devoted to improving robustness…

cs.LG2021

Latent-Optimized Adversarial Neural Transfer for Sarcasm Detection

Xu Guo, Boyang Li, Han Yu +1

The existence of multiple datasets for sarcasm detection prompts us to apply transfer learning to exploit their commonality. The adversarial neural transfer (ANT) framework utilize…

cs.CR20208 cited

Proof of Learning (PoLe): Empowering Machine Learning with Consensus Building on Blockchains

Yixiao Lan, Yuan Liu, Boyang Li

The progress of deep learning (DL), especially the recent development of automatic design of networks, has brought unprecedented performance gains at heavy computational cost. On t…

cs.LG20194 cited

Searching for Stage-wise Neural Graphs In the Limit

Xin Zhou, Dejing Dou, Boyang Li

Search space is a key consideration for neural architecture search. Recently, Xie et al. (2019) found that randomly generated networks from the same distribution perform similarly,…