49 citations · 53 across the 4 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2025
Activation Quantization of Vision Encoders Needs Prefixing Registers
Seunghyeon Kim, Taesun Yeom, Jinho Kim +3
Large pretrained vision encoders are central to multimodal intelligence, powering applications from on-device vision processing to vision-language models. Since these applications…
cs.LG2024★ 4 cited
MimiQ: Low-Bit Data-Free Quantization of Vision Transformers with Encouraging Inter-Head Attention Similarity
Kanghyun Choi, Hye Yoon Lee, Dain Kwon +5
Data-free quantization (DFQ) is a technique that creates a lightweight network from its full-precision counterpart without the original training data, often through a synthetic dat…
cs.LG2024
Prefixing Attention Sinks can Mitigate Activation Outliers for Large Language Model Quantization
Seungwoo Son, Wonpyo Park, Woohyun Han +2
Despite recent advances in LLM quantization, activation quantization remains to be challenging due to the activation outliers. Conventional remedies, e.g., mixing precisions for di…