4 papers
Fine-Grained Activation Steering: Steering Less, Achieving More
Zijian Feng, Tianjiao Li, Zixiao Zhu +7
Activation steering has emerged as a cost-effective paradigm for modifying large language model (LLM) behaviors. Existing methods typically intervene at the block level, steering t…
QMAVIS: Long Video-Audio Understanding using Fusion of Large Multimodal Models
Zixing Lin, Jiale Wang, Gee Wah Ng +4
Large Multimodal Models (LMMs) for video-audio understanding have traditionally been evaluated only on shorter videos of a few minutes long. In this paper, we introduce QMAVIS (Q T…
QCaption: Video Captioning and Q&A through Fusion of Large Multimodal Models
Jiale Wang, Gee Wah Ng, Lee Onn Mak +3
This paper introduces QCaption, a novel video captioning and Q&A pipeline that enhances video analytics by fusing three models: key frame extraction, a Large Multimodal Model (LMM)…
Restoring Pruned Large Language Models via Lost Component Compensation
Zijian Feng, Hanzhang Zhou, Zixiao Zhu +5
Pruning is a widely used technique to reduce the size and inference cost of large language models (LLMs), but it often causes performance degradation. To mitigate this, existing re…