CybAI news

arXiv:2408.04140v1 Announce Type: new Abstract: Given the prevalence of large language models (LLMs) and the prohibitive cost of training these models from scratch, dynamically forgetting specific knowledge e.g., private or proprietary, without retraining the model has become an important capability. This paper proposes a novel method to achieve this objective called UNLEARN. The approach builds upon subspace methods to identify and specifically target the removal of knowledge without adversely affecting other knowledge in the LLM. Results demonstrate 96% of targeted knowledge can be forgotten while maintaining performance on other knowledge within 2.5% of the original model, significantly outperforming the discriminatory…

arXiv:2408.04107v1 Announce Type: new Abstract: In large-language models, memory constraints in the key-value cache (KVC) pose a challenge during inference, especially with long prompts. In this work, we observed that compressing KV values is more effective than compressing the model regarding accuracy and job completion time (JCT). However, quantizing KV values and dropping less-important tokens incur significant runtime computational time overhead, delaying JCT. These methods also cannot reduce computation time or high network communication time overhead in sequence-parallelism (SP) frameworks for long prompts. To tackle these issues, based on our insightful observations from experimental analysis, we propose ZeroC, a Zero-delay…

arXiv:2408.04103v1 Announce Type: new Abstract: How can we define visual sentiment when viewers systematically disagree on their perspectives? This study introduces a novel approach to visual sentiment analysis by integrating attitudinal differences into visual sentiment classification. Recognizing that societal divides, such as partisan differences, heavily influence sentiment labeling, we developed a dataset that reflects these divides. We then trained a deep learning multi-task multi-class model to predict visual sentiment from different ideological viewpoints. Applied to immigration-related images, our approach captures perspectives from both Democrats and Republicans. By incorporating diverse perspectives into the labeling and model training process, our strategy addresses…