15 citations · 19 across the 12 of their papers we have counts for
14 papers
ERASE: Eliminating Redundant Visual Tokens via Adaptive Two-Stage Token Pruning
Yuna Lee, Kyoungho Min, Yulhwa Kim
Recent advances in Vision-Language Models (VLMs) enable large language models (LLMs) to process high-resolution images, significantly improving real-world multimodal understanding.…
AnalogToBi: Device-Level Analog Circuit Topology Generation via Bipartite Graph and Grammar Guided Decoding
Seungmin Kim, Mingun Kim, Yuna Lee +1
Analog circuit design remains highly dependent on expert knowledge due to the complexity of device-level interactions and topology design. Recent transformer-based approaches for d…
QTALE: Quantization-Robust Token-Adaptive Layer Execution for LLMs
Kanghyun Noh, Jinheon Choi, Yulhwa Kim
Large language models (LLMs) demand substantial computational and memory resources, posing challenges for efficient deployment. Two complementary approaches have emerged to address…
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…
QWHA: Quantization-Aware Walsh-Hadamard Adaptation for Parameter-Efficient Fine-Tuning on Large Language Models
Hyesung Jeon, Seojune Lee, Beomseok Kang +2
The demand for efficient deployment of large language models (LLMs) has driven interest in quantization, which reduces inference cost, and parameter-efficient fine-tuning (PEFT), w…
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…
FastKV: Decoupling of Context Reduction and KV Cache Compression for Prefill-Decoding Acceleration
Dongwon Jo, Jiwon Song, Yulhwa Kim +1
While large language models (LLMs) excel at handling long-context sequences, they require substantial prefill computation and key-value (KV) cache, which can heavily burden computa…
Mixture of Scales: Memory-Efficient Token-Adaptive Binarization for Large Language Models
Dongwon Jo, Taesu Kim, Yulhwa Kim +1
Binarization, which converts weight parameters to binary values, has emerged as an effective strategy to reduce the size of large language models (LLMs). However, typical binarizat…
SLEB: Streamlining LLMs through Redundancy Verification and Elimination of Transformer Blocks
Jiwon Song, Kyungseok Oh, Taesu Kim +3
Large language models (LLMs) have proven to be highly effective across various natural language processing tasks. However, their large number of parameters poses significant challe…
L4Q: Parameter Efficient Quantization-Aware Fine-Tuning on Large Language Models
Hyesung Jeon, Yulhwa Kim, Jae-joon Kim
Due to the high memory and computational costs associated with large language models (LLMs), model compression techniques such as quantization, which reduces inference costs, and p…
Squeezing Large-Scale Diffusion Models for Mobile
Jiwoong Choi, Minkyu Kim, Daehyun Ahn +6
The emergence of diffusion models has greatly broadened the scope of high-fidelity image synthesis, resulting in notable advancements in both practical implementation and academic…
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…