4 papers
TASQ: Temporal-Adaptive Bit Sparsification Quantization for Diffusion Models
Seokho Han, Dongwei Wang, Jinhee Kim +4
Static quantization assigns one weight precision to every denoising step. To preserve quality, that precision must accommodate the most quantization-sensitive step, even though man…
MoBiQuant: Mixture-of-Bits Quantization for Token-Adaptive Any-Precision LLM
Dongwei Wang, Jinhee Kim, Seokho Han +8
Dynamic runtime latency and memory constraints necessitate flexible large language model (LLM) deployment, where an LLM can be inferred with various quantization precisions based o…
RangeGuard: Efficient, Bounded Approximate Error Correction for Reliable DNNs
Hanum Ko, Sangheum Yeon, Jong Hwan Ko +1
As DRAM scales in density and adopts 3D integration, raw fault rates increase and multi-bit errors are no longer rare. Such errors can severely impact Deep Neural Networks (DNNs):…
Harnessing Linguistic Dissimilarity for Language Generalization on Unseen Low-Resource Varieties
Jinju Kim, Haeji Jung, Youjeong Roh +2
Low-resource language varieties used by specific groups remain neglected in the development of Multilingual Language Models. A great deal of cross-lingual research focuses on inter…