Related papers: IsoQuant: Hardware-Aligned SO(4) Isoclinic Rotatio…

The emergence of fine-grained numerical formats like NVFP4 presents new opportunities for efficient Large Language Model (LLM) inference. However, it is difficult to adapt existing Post-Training Quantization (PTQ) strategies to these…

This paper proposes a convolution structure for learning SE(3)-equivariant features from 3D point clouds. It can be viewed as an equivariant version of kernel point convolutions (KPConv), a widely used convolution form to process point…

Large language models (LLMs) are costly to deploy due to their large memory footprint and high inference cost. Weight-activation quantization can reduce these costs, but low-bit activation quantization remains difficult because activation…

Quantizing the weights of a neural network has two steps: (1) Finding a good low bit-complexity representation for weights (which we call the quantization grid) and (2) Rounding the original weights to values in the quantization grid. In…

Efficient inference is critical for deploying deep learning models on edge AI devices. Low-bit quantization (e.g., 3- and 4-bit) with fixed-point arithmetic improves efficiency, while low-power memory technologies like analog nonvolatile…

This paper introduces SD-6DoF-ICLK, a learning-based Inverse Compositional Lucas-Kanade (ICLK) pipeline that uses sparse depth information to optimize the relative pose that best aligns two images on SE(3). To compute this six…

Despite the recent active research on processing point clouds with deep networks, few attention has been on the sensitivity of the networks to rotations. In this paper, we propose a deep learning architecture that achieves discrete…

Efficient data encoding is the main factor affecting how fast hybrid quantum-classical algorithms run, but traditional simulators spend most of their time changing classical features into quantum rotations. This work introduces Hybriqu…

Vector quantization, a problem rooted in Shannon's source coding theory, aims to quantize high-dimensional Euclidean vectors while minimizing distortion in their geometric structure. We propose TurboQuant to address both mean-squared error…

Current quantization methods for LLMs predominantly rely on block-wise structures to maintain efficiency, often at the cost of representational flexibility. In this work, we demonstrate that element-wise quantization can be made as…

Transformers are the backbone of powerful foundation models for many Vision and Natural Language Processing tasks. But their compute and memory/storage footprint is large, and so, serving such models is expensive often requiring high-end…

This paper uses the reconstruction-computation-quantization (RCQ) paradigm to decode low-density parity-check (LDPC) codes. RCQ facilitates dynamic non-uniform quantization to achieve good frame error rate (FER) performance with very low…

Recent works have demonstrated that large quantum circuits can be cut and decomposed into smaller clusters of quantum circuits with fewer qubits that can be executed independently on a small quantum computer. Classical post-processing then…

Every numerical general relativistic investigation starts from the solution of the initial value equations at a given time. Astrophysically relevant initial values for different systems lead to distinct set of equations that obey specific…

Key-Value (KV) cache plays a crucial role in accelerating inference in large language models (LLMs) by storing intermediate attention states and avoiding redundant computation during autoregressive generation. However, its memory footprint…

Enabling On-Device Learning (ODL) for Ultra-Low-Power Micro-Controller Units (MCUs) is a key step for post-deployment adaptation and fine-tuning of Deep Neural Network (DNN) models in future TinyML applications. This paper tackles this…

Large language models (LLMs) have achieved remarkable success, but their rapidly growing scale imposes prohibitive costs in memory, computation, and energy. Post-training quantization (PTQ) is a promising solution for efficient deployment,…

Quantum computers face challenges due to limited resources, particularly in cloud environments. Despite these obstacles, Variational Quantum Algorithms (VQAs) are considered promising applications for present-day Noisy Intermediate-Scale…

Achieving chemical accuracy for strongly correlated molecules is a defining milestone for first-generation, fault-tolerant quantum computers, yet the factorial growth of three, four, and six-index tensor contractions in coupled-cluster…

Developing effective 360-degree (spherical) image compression techniques is crucial for technologies like virtual reality and automated driving. This paper advances the state-of-the-art in on-the-sphere learning (OSLO) for omnidirectional…