15 citations · 31 across the 29 of their papers we have counts for
33 papers
Semantic-Aware Neural Video Codec for Error-Resilient Low-Latency Transmission
Matin Mortaheb, Homa Esfahanizadeh, Jinfeng Du +1
Emerging physical AI systems require low-latency, task-oriented video communication over unreliable channels. We propose a semantic-aware multi-level neural video coding method for…
UniTAC: Universal Task-Aware Compression via Weighted Distortion Measures
Homa Esfahanizadeh, Matin Mortaheb, Jinfeng Du +2
Lossy compression is conventionally driven by a task-agnostic distortion (e.g., MSE or MS-SSIM), yet in many emerging applications the receiver cares not about uniform fidelity but…
Enhanced Feedback Mechanisms for Resource-Efficient Incremental Redundancy
Mustafa Cemil Coşkun, Ahmed Elkelesh, Avijit Mandal +1
Incremental redundancy (IR) can reduce error rates by spreading coded bits across multiple transmission attempts. However, conventional stop-and-wait operation with coarse feedback…
Towards Robust Semantic Video Transmission over Block Erasure Channels
Nargis Fayaz, Homa Esfahanizadeh, Matin Mortaheb +2
This paper investigates semantic-aware neural joint source-channel coding (JSCC) for robust video transmission over block erasure channels. We propose a neural video compression fr…
Block Erasure-Aware Semantic Multimedia Compression via JSCC Autoencoder
Homa Esfahanizadeh, Nargis Fayaz, Jinfeng Du +1
We present an AI-based framework for semantic transmission of multimedia data over band-limited, time-varying channels. The method targets scenarios where large content is split in…
Precoding-Oriented CSI Feedback Design with Mutual Information Regularized VQ-VAE
Xi Chen, Homa Esfahanizadeh, Foad Sohrabi
Efficient channel state information (CSI) compression at the user equipment plays a key role in enabling accurate channel reconstruction and precoder design in massive multiple-inp…
Revisiting the Interface between Error and Erasure Correction in Wireless Standards
Vipindev Adat Vasudevan, Homa Esfahanizadeh, Benjamin D. Kim +3
Modern 5G communication systems implement a combination of error correction and feedback-based erasure correction (HARQ/ARQ) as reliability mechanisms, which can introduce substant…
MultiTok: Variable-Length Tokenization for Efficient LLMs Adapted from LZW Compression
Noel Elias, Homa Esfahanizadeh, Kaan Kale +2
Large language models have drastically changed the prospects of AI by introducing technologies for more complex natural language processing. However, current methodologies to train…
Multi-level Reliability Interface for Semantic Communications over Wireless Networks
Tze-Yang Tung, Homa Esfahanizadeh, Jinfeng Du +1
Semantic communication, when examined through the lens of joint source-channel coding (JSCC), maps source messages directly into channel input symbols, where the measure of success…
On the Benefits of Coding for Network Slicing
Homa Esfahanizadeh, Vipindev Adat Vasudevan, Benjamin D. Kim +4
Network slicing has emerged as an integral concept in 5G, aiming to partition the physical network infrastructure into isolated slices, customized for specific applications. We the…
Successive Refinement in Large-Scale Computation: Advancing Model Inference Applications
Homa Esfahanizadeh, Alejandro Cohen, Shlomo Shamai +1
Modern computationally-intensive applications often operate under time constraints, necessitating acceleration methods and distribution of computational workloads across multiple e…
TexShape: Information Theoretic Sentence Embedding for Language Models
Kaan Kale, Homa Esfahanizadeh, Noel Elias +3
With the exponential growth in data volume and the emergence of data-intensive applications, particularly in the field of machine learning, concerns related to resource utilization…
A Non-Asymptotic Analysis of Mismatched Guesswork
Alexander Mariona, Homa Esfahanizadeh, Rafael G. L. D'Oliveira +1
The problem of mismatched guesswork considers the additional cost incurred by using a guessing function which is optimal for a distribution when the random variable to be guess…
PEOPL: Characterizing Privately Encoded Open Datasets with Public Labels
Homa Esfahanizadeh, Adam Yala, Rafael G. L. D'Oliveira +8
Allowing organizations to share their data for training of machine learning (ML) models without unintended information leakage is an open problem in practice. A promising technique…
InfoShape: Task-Based Neural Data Shaping via Mutual Information
Homa Esfahanizadeh, William Wu, Manya Ghobadi +2
The use of mutual information as a tool in private data sharing has remained an open challenge due to the difficulty of its estimation in practice. In this paper, we propose InfoSh…
A Bivariate Invariance Principle
Alexander Mariona, Homa Esfahanizadeh, Rafael G. L. D'Oliveira +1
A notable result from analysis of Boolean functions is the Basic Invariance Principle (BIP), a quantitative nonlinear generalization of the Central Limit Theorem for multilinear po…
Distributed Computations with Layered Resolution
Homa Esfahanizadeh, Alejandro Cohen, Muriel Médard +1
Modern computationally-heavy applications are often time-sensitive, demanding distributed strategies to accelerate them. On the other hand, distributed computing suffers from the b…
Ultra-Reliable Low-Latency Millimeter-Wave Communications with Sliding Window Network Coding
Eurico Dias, Duarte Raposo, Homa Esfahanizadeh +5
Ultra-reliability and low-latency are pivotal requirements of the new 6th generation of communication systems (xURLLC). Over the past years, to increase throughput, adaptive active…
Stream Iterative Distributed Coded Computing for Learning Applications in Heterogeneous Systems
Homa Esfahanizadeh, Alejandro Cohen, Muriel Medard
To improve the utility of learning applications and render machine learning solutions feasible for complex applications, a substantial amount of heavy computations is needed. Thus,…
A Unified Spatially Coupled Code Design: Threshold, Cycles, and Locality
Homa Esfahanizadeh, Eshed Ram, Yuval Cassuto +1
Spatially-Coupled (SC)-LDPC codes are known to have outstanding error-correction performance and low decoding latency. Whereas previous works on LDPC and SC-LDPC codes mostly take…
Syfer: Neural Obfuscation for Private Data Release
Adam Yala, Victor Quach, Homa Esfahanizadeh +5
Balancing privacy and predictive utility remains a central challenge for machine learning in healthcare. In this paper, we develop Syfer, a neural obfuscation method to protect aga…
NeuraCrypt: Hiding Private Health Data via Random Neural Networks for Public Training
Adam Yala, Homa Esfahanizadeh, Rafael G. L. D' Oliveira +6
Balancing the needs of data privacy and predictive utility is a central challenge for machine learning in healthcare. In particular, privacy concerns have led to a dearth of public…
Stream Distributed Coded Computing
Alejandro Cohen, Guillaume Thiran, Homa Esfahanizadeh +1
The emerging large-scale and data-hungry algorithms require the computations to be delegated from a central server to several worker nodes. One major challenge in the distributed c…
Bringing Network Coding into SDN: A Case-study for Highly Meshed Heterogeneous Communications
Alejandro Cohen, Homa Esfahanizadeh, Bruno Sousa +6
Modern communications have moved away from point-to-point models to increasingly heterogeneous network models. In this article, we propose a novel controller-based protocol to depl…