CybAI news

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs. Source link lol

Women make up 15% to 22% of data science professionals, research from the Boston Consulting Group shows. One of the women who is hoping to increase that number is Chisoo Lyons, the executive director of Women in Data Science Worldwide (WiDS) and a BigDATAwire 2024 Person to Watch. WiDS started in 2015 with a one-day technical conference at Stanford University to give women a voice in data science. Since then, the group has expanded significantly, and it now touches more than 150,000 participants across 160 countries via conferences, datathons, podcasts, upskilling workshops, its Next Gen outreach program, the WiDS Academy,…

arXiv:2411.14507v1 Announce Type: new Abstract: Generative Pre-trained Transformers (GPTs) have demonstrated remarkable performance across diverse domains through the extensive scaling of model parameters. Recent works observe the redundancy across the transformer blocks and develop compression methods by structured pruning of the unimportant blocks. However, such straightforward elimination will always provide irreversible performance degradation. In this paper, we propose FuseGPT, a novel methodology to recycle the pruned transformer blocks to further recover the model performance. Firstly we introduce a new importance detection metric, Macro Influence (MI), to detect the long-term influence of each transformer block by calculating their loss of information…

arXiv:2411.14505v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are widely used for visual perception, understanding, and reasoning. However, long video processing and precise moment retrieval remain challenging due to LLMs' limited context size and coarse frame extraction. We propose the Large Language-and-Vision Assistant for Moment Retrieval (LLaVA-MR), which enables accurate moment retrieval and contextual grounding in videos using MLLMs. LLaVA-MR combines Dense Frame and Time Encoding (DFTE) for spatial-temporal feature extraction, Informative Frame Selection (IFS) for capturing brief visual and motion patterns, and Dynamic Token Compression (DTC) to manage LLM context limitations. Evaluations on benchmarks like Charades-STA and…