Zobrazeno 1 - 7
of 7
pro vyhledávání: '"Li, Bolian"'
Vision Language Models (VLMs) have become essential backbones for multimodal intelligence, yet significant safety challenges limit their real-world application. While textual inputs are often effectively safeguarded, adversarial visual inputs can eas
Externí odkaz:
http://arxiv.org/abs/2410.06625
Aligning large language models (LLMs) with human preferences is critical for their deployment. Recently, decoding-time alignment has emerged as an effective plug-and-play technique that requires no fine-tuning of model parameters. However, generating
Externí odkaz:
http://arxiv.org/abs/2406.16306
Autor:
Li, Bolian, Zhang, Ruqi
Publikováno v:
ICLR 2024
Bayesian deep learning counts on the quality of posterior distribution estimation. However, the posterior of deep neural networks is highly multi-modal in nature, with local modes exhibiting varying generalization performance. Given a practical budge
Externí odkaz:
http://arxiv.org/abs/2310.05401
Autor:
Li, Bolian, Zhang, Ruqi
Long-tailed classification poses a challenge due to its heavy imbalance in class probabilities and tail-sensitivity risks with asymmetric misprediction costs. Recent attempts have used re-balancing loss and ensemble methods, but they are largely heur
Externí odkaz:
http://arxiv.org/abs/2303.06075
Classification on long-tailed distributed data is a challenging problem, which suffers from serious class-imbalance and accordingly unpromising performance especially on tail classes. Recently, the ensembling based methods achieve the state-of-the-ar
Externí odkaz:
http://arxiv.org/abs/2111.09030
Graph representation learning is crucial for many real-world applications (e.g. social relation analysis). A fundamental problem for graph representation learning is how to effectively learn representations without human labeling, which is usually co
Externí odkaz:
http://arxiv.org/abs/2110.14863
Uncertainty estimation is critical for cost-sensitive deep-learning applications (i.e. disease diagnosis). It is very challenging partly due to the inaccessibility of uncertainty groundtruth in most datasets. Previous works proposed to estimate the u
Externí odkaz:
http://arxiv.org/abs/2110.08030