Search Results for author:
Found 25 papers, 7 papers with code
Huff-LLM: End-to-End Lossless Compression for Efficient LLM Inference
As they become more capable, large language models (LLMs) have continued to rapidly increase in size.
MM-GEN: Enhancing Task Performance Through Targeted Multimodal Data Curation
Vision-language models (VLMs) are highly effective but often underperform on specialized tasks; for example, Llava-1. 5 struggles with chart and diagram understanding due to scarce task-specific training data.
A Remedy to Compute-in-Memory with Dynamic Random Access Memory: 1FeFET-1C Technology for Neuro-Symbolic AI
To address these challenges-and mitigate the typical data-transfer bottleneck of classical Von Neumann architectures-we propose a ferroelectric charge-domain compute-in-memory (CiM) array as the foundational processing element for neuro-symbolic AI.
Dataset Distillation via Knowledge Distillation: Towards Efficient Self-Supervised Pre-Training of Deep Networks
Dataset distillation (DD) generates small synthetic datasets that can efficiently train deep networks with a limited amount of memory and compute.
Slax: A Composable JAX Library for Rapid and Flexible Prototyping of Spiking Neural Networks
Recent advances to algorithms for training spiking neural networks (SNNs) often leverage their unique dynamics.
Data-Efficient Contrastive Language-Image Pretraining: Prioritizing Data Quality over Quantity
We show that subsets that closely preserve the cross-covariance of the images and captions of the full data provably achieve a superior generalization performance.
Investigating the Benefits of Projection Head for Representation Learning
An effective technique for obtaining high-quality representations is adding a projection head on top of the encoder during training, then discarding it and using the pre-projection representations.
Improvements in Interlayer Pipelining of CNN Accelerators Using Genetic Algorithms
Deploying Convolutional Neural Networks (CNNs) on edge platforms necessitates efficient hardware acceleration.
Estimating Post-Synaptic Effects for Online Training of Feed-Forward SNNs
We show improved scaling for multi-layer networks using a novel approximation of temporal effects on the subsequent layer's activity.
Understanding the Robustness of Multi-modal Contrastive Learning to Distribution Shift
Recently, multimodal contrastive learning (MMCL) approaches, such as CLIP, have achieved a remarkable success in learning representations that are robust against distribution shift and generalize to new domains.
Hadamard Domain Training with Integers for Class Incremental Quantized Learning
In this paper, we propose a technique that leverages inexpensive Hadamard transforms to enable low-precision training with only integer matrix multiplications.
Towards Mitigating more Challenging Spurious Correlations: A Benchmark & New Datasets
Deep neural networks often exploit non-predictive features that are spuriously correlated with class labels, leading to poor performance on groups of examples without such features.
Augmenting Hessians with Inter-Layer Dependencies for Mixed-Precision Post-Training Quantization
To address this challenge, we propose a mixed-precision post training quantization (PTQ) approach that assigns different numerical precisions to tensors in a network based on their specific needs, for a reduced memory footprint and improved latency while preserving model accuracy.
Which Features are Learnt by Contrastive Learning? On the Role of Simplicity Bias in Class Collapse and Feature Suppression
However, supervised CL is prone to collapsing representations of subclasses within a class by not capturing all their features, and unsupervised CL may suppress harder class-relevant features by focusing on learning easy class-irrelevant features; both significantly compromise representation quality.
NeuroBench: A Framework for Benchmarking Neuromorphic Computing Algorithms and Systems
To address these shortcomings, we present NeuroBench: a benchmark framework for neuromorphic computing algorithms and systems.
Data-Efficient Contrastive Self-supervised Learning: Most Beneficial Examples for Supervised Learning Contribute the Least
In this work, we address this problem for the first time, by proving that examples that contribute the most to contrastive SSL are those that have the most similar augmentations to other examples, in expectation.
The Hardware Impact of Quantization and Pruning for Weights in Spiking Neural Networks
Energy efficient implementations and deployments of Spiking neural networks (SNNs) have been of great interest due to the possibility of developing artificial systems that can achieve the computational powers and energy efficiency of the biological brain.
Mixed Precision Post Training Quantization of Neural Networks with Sensitivity Guided Search
In this paper, we propose a method to efficiently determine quantization configurations of different tensors in ML models using post-training mixed precision quantization.
Edge Inference with Fully Differentiable Quantized Mixed Precision Neural Networks
Quantizing the parameters and operations to lower bit-precision offers substantial memory and energy savings for neural network inference, facilitating the use of DNNs on edge computing platforms.
Edge AI without Compromise: Efficient, Versatile and Accurate Neurocomputing in Resistive Random-Access Memory
Realizing today's cloud-level artificial intelligence functionalities directly on devices distributed at the edge of the internet calls for edge hardware capable of processing multiple modalities of sensory data (e. g. video, audio) at unprecedented energy-efficiency.
Analog vs. Digital Spatial Transforms: A Throughput, Power, and Area Comparison
Spatial linear transforms that process multiple parallel analog signals to simplify downstream signal processing find widespread use in multi-antenna communication systems, machine learning inference, data compression, audio and ultrasound applications, among many others.
Memory Organization for Energy-Efficient Learning and Inference in Digital Neuromorphic Accelerators
The energy efficiency of neuromorphic hardware is greatly affected by the energy of storing, accessing, and updating synaptic parameters.
Training a Probabilistic Graphical Model with Resistive Switching Electronic Synapses
Current large scale implementations of deep learning and data mining require thousands of processors, massive amounts of off-chip memory, and consume gigajoules of energy.
Forward Table-Based Presynaptic Event-Triggered Spike-Timing-Dependent Plasticity
We present a novel method for realizing both causal and acausal weight updates using only forward lookup access of the synaptic connectivity table, permitting memory-efficient implementation.
Stochastic Synapses Enable Efficient Brain-Inspired Learning Machines
Recent studies have shown that synaptic unreliability is a robust and sufficient mechanism for inducing the stochasticity observed in cortex.
