3 papers
cs.AR2026
SMART-AIMC: Sensitivity-Aware Mixed ADC Resolution with Fine-Grained Tunability for Analog In-Memory Computing
Yung-Chin Chen, Ourania Stouraiti, Naveen Verma
Analog In-Memory Computing (IMC) is a promising paradigm for accelerating GEMM-based AI workloads by executing computations directly within the memory array in the analog domain. W…
cs.AI2026
IMC-CLINIC: Coupled Loss-Informed Newton Iterations for Clipping in Analog In-Memory Computing
Yung-Chin Chen, Chia-Yu Chen, Naveen Verma
Analog in-memory computing (IMC) offers a promising path toward energy-efficient large language model (LLM) inference by executing matrix multiplications (MatMul) directly within m…
cs.LG2026
Massive Spikes in LLMs are Bias Vectors: Mechanistic Uncovering and Spike-Free Quantization
Yung-Chin Chen, Chung Peng Lee, Ze-Wei Liou +1
Massive activation spikes in Large Language Models (LLMs) severely degrade quantization by stretching dynamic ranges. While prior hypotheses characterize these as high-level scalar…