5 papers
Leveraging KV Similarity for Online Structured Pruning in LLMs
Jungmin Lee, Gwangeun Byeon, Yulhwa Kim +1
Pruning has emerged as a promising direction for accelerating large language model (LLM) inference, yet existing approaches often suffer from instability because they rely on offli…
Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning
Jiwon Song, Dongwon Jo, Yulhwa Kim +1
Recent reasoning-focused language models achieve high accuracy by generating lengthy intermediate reasoning paths before producing final answers. While this approach is effective i…
Column-wise Quantization of Weights and Partial Sums for Accurate and Efficient Compute-In-Memory Accelerators
Jiyoon Kim, Kang Eun Jeon, Yulhwa Kim +1
Compute-in-memory (CIM) is an efficient method for implementing deep neural networks (DNNs) but suffers from substantial overhead from analog-to-digital converters (ADCs), especial…
BitSplit-Net: Multi-bit Deep Neural Network with Bitwise Activation Function
Hyungjun Kim, Yulhwa Kim, Sungju Ryu +1
Significant computational cost and memory requirements for deep neural networks (DNNs) make it difficult to utilize DNNs in resource-constrained environments. Binary neural network…
Neural Network-Hardware Co-design for Scalable RRAM-based BNN Accelerators
Yulhwa Kim, Hyungjun Kim, Jae-Joon Kim
Recently, RRAM-based Binary Neural Network (BNN) hardware has been gaining interests as it requires 1-bit sense-amp only and eliminates the need for high-resolution ADC and DAC. Ho…