17 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…
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…
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…
PacQ: A SIMT Microarchitecture for Efficient Dataflow in Hyper-asymmetric GEMMs
Ruokai Yin, Yuhang Li, Priyadarshini Panda
Weight-only quantization has been widely explored in large language models (LLMs) to reduce memory storage and data loading overhead. During deployment on single-instruction-multip…
TesseraQ: Ultra Low-Bit LLM Post-Training Quantization with Block Reconstruction
Yuhang Li, Priyadarshini Panda
Large language models (LLMs) have revolutionized natural language processing, albeit at the cost of immense memory and computation requirements. Post-training quantization (PTQ) is…
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…
When In-memory Computing Meets Spiking Neural Networks -- A Perspective on Device-Circuit-System-and-Algorithm Co-design
Abhishek Moitra, Abhiroop Bhattacharjee, Yuhang Li +2
This review explores the intersection of bio-plausible artificial intelligence in the form of Spiking Neural Networks (SNNs) with the analog In-Memory Computing (IMC) domain, highl…
One-stage Prompt-based Continual Learning
Youngeun Kim, Yuhang Li, Priyadarshini Panda
Prompt-based Continual Learning (PCL) has gained considerable attention as a promising continual learning solution as it achieves state-of-the-art performance while preventing priv…
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…
Rethinking Skip Connections in Spiking Neural Networks with Time-To-First-Spike Coding
Youngeun Kim, Adar Kahana, Ruokai Yin +4
Time-To-First-Spike (TTFS) coding in Spiking Neural Networks (SNNs) offers significant advantages in terms of energy efficiency, closely mimicking the behavior of biological neuron…
MINT: Multiplier-less INTeger Quantization for Energy Efficient Spiking Neural Networks
Ruokai Yin, Yuhang Li, Abhishek Moitra +1
We propose Multiplier-less INTeger (MINT) quantization, a uniform quantization scheme that efficiently compresses weights and membrane potentials in spiking neural networks (SNNs).…