10 papers
CNNs in the Air via Reconfigurable Intelligent Surfaces
Meng Hua, Haotian Wu, Deniz Gündüz
This paper introduces AirCNN, a novel paradigm for implementing convolutional neural networks (CNNs) via over-the-air (OTA) analog computation. By leveraging multiple reconfigurabl…
Diffusion-aided Extreme Video Compression with Lightweight Semantics Guidance
Maojun Zhang, Haotian Wu, Richeng Jin +2
Modern video codecs and learning-based approaches struggle for semantic reconstruction at extremely low bit-rates due to reliance on low-level spatiotemporal redundancies. Generati…
Leveraging Overfitting for Low-Complexity and Modality-Agnostic Joint Source-Channel Coding
Haotian Wu, Gen Li, Pier Luigi Dragotti +1
This paper introduces Implicit-JSCC, a novel overfitted joint source-channel coding paradigm that directly optimizes channel symbols and a lightweight neural decoder for each sourc…
Compression Beyond Pixels: Semantic Compression with Multimodal Foundation Models
Ruiqi Shen, Haotian Wu, Wenjing Zhang +2
Recent deep learning-based methods for lossy image compression achieve competitive rate-distortion performance through extensive end-to-end training and advanced architectures. How…
LotteryCodec: Searching the Implicit Representation in a Random Network for Low-Complexity Image Compression
Haotian Wu, Gongpu Chen, Pier Luigi Dragotti +1
We introduce and validate the lottery codec hypothesis, which states that untrained subnetworks within randomly initialized networks can serve as synthesis networks for overfitted…
Actions Speak Louder Than Words: Rate-Reward Trade-off in Markov Decision Processes
Haotian Wu, Gongpu Chen, Deniz Gündüz
The impact of communication on decision-making systems has been extensively studied under the assumption of dedicated communication channels. We instead consider communicating thro…