14 papers
KronQ: LLM Quantization via Kronecker-Factored Hessian
Donghyun Lee, Yuhang Li, Ruokai Yin +1
Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (LLMs) without retraining. Most existing second-order PTQ methods, including GP…
BRIM: Workload-Balanced Dual-Sided Bit-Serial Sparse Inference Accelerator
Varun Manjunath, Ruokai Yin, Donghyun Lee +2
Bit-serial accelerators exploit bit-level sparsity to reduce DNN inference cost, but existing designs exploit sparsity on only one operand, bounding the speedup. Extending sparsity…
OrbitQuant: Data-Agnostic Quantization for Image and Video Diffusion Transformers
Donghyun Lee, Jitesh Chavan, Duy Nguyen +5
Diffusion transformers (DiTs) achieve state-of-the-art image and video generation, but their multi-step sampling and growing parameter count make inference expensive. Post-training…
Optimal Brain Decomposition for Accurate LLM Low-Rank Approximation
Yuhang Li, Donghyun Lee, Ruokai Yin +1
Low-rank decomposition has emerged as an important problem in Large Language Model (LLM) fine-tuning and inference. Through Singular Value Decomposition (SVD), the weight matrix ca…
MD-SNN: Membrane Potential-aware Distillation on Quantized Spiking Neural Network
Donghyun Lee, Abhishek Moitra, Youngeun Kim +2
Spiking Neural Networks (SNNs) offer a promising and energy-efficient alternative to conventional neural networks, thanks to their sparse binary activation. However, they face chal…
SpikePool: Event-driven Spiking Transformer with Pooling Attention
Donghyun Lee, Alex Sima, Yuhang Li +2
Building on the success of transformers, Spiking Neural Networks (SNNs) have increasingly been integrated with transformer architectures, leading to spiking transformers that demon…
OpenWorldSAM: Extending SAM2 for Universal Image Segmentation with Language Prompts
Shiting Xiao, Rishabh Kabra, Yuhang Li +3
The ability to segment objects based on open-ended language prompts remains a critical challenge, requiring models to ground textual semantics into precise spatial masks while hand…
DuoGPT: Training-free Dual Sparsity through Activation-aware Pruning in LLMs
Ruokai Yin, Yuhang Li, Donghyun Lee +1
Large language models (LLMs) deliver strong performance but are difficult to deploy due to high memory and compute costs. While pruning reduces these demands, most methods ignore a…
Memba: Membrane-driven Parameter-Efficient Fine-Tuning for Mamba
Donghyun Lee, Yuhang Li, Ruokai Yin +2
State Space Models (SSMs) have emerged as powerful alternatives to attention-based Transformers, with Mamba demonstrating impressive efficiency and scalability. As these models gro…
GPTAQ: Efficient Finetuning-Free Quantization for Asymmetric Calibration
Yuhang Li, Ruokai Yin, Donghyun Lee +2
We introduce GPTAQ, a novel finetuning-free quantization method for compressing large-scale transformer architectures. Unlike the previous GPTQ method, which independently calibrat…
ReSpike: Residual Frames-based Hybrid Spiking Neural Networks for Efficient Action Recognition
Shiting Xiao, Yuhang Li, Youngeun Kim +2
Spiking Neural Networks (SNNs) have emerged as a compelling, energy-efficient alternative to traditional Artificial Neural Networks (ANNs) for static image tasks such as image clas…
Spiking Transformer with Spatial-Temporal Attention
Donghyun Lee, Yuhang Li, Youngeun Kim +2
Spike-based Transformer presents a compelling and energy-efficient alternative to traditional Artificial Neural Network (ANN)-based Transformers, achieving impressive results throu…
TT-SNN: Tensor Train Decomposition for Efficient Spiking Neural Network Training
Donghyun Lee, Ruokai Yin, Youngeun Kim +3
Spiking Neural Networks (SNNs) have gained significant attention as a potentially energy-efficient alternative for standard neural networks with their sparse binary activation. How…
GenQ: Quantization in Low Data Regimes with Generative Synthetic Data
Yuhang Li, Youngeun Kim, Donghyun Lee +2
In the realm of deep neural network deployment, low-bit quantization presents a promising avenue for enhancing computational efficiency. However, it often hinges on the availabilit…