Related papers: Performance Evaluation of Efficient Hybrid Compres…
The well-known dictionary-based algorithms of the Lempel-Ziv (LZ) 77 family are the basis of several universal lossless compression techniques. These algorithms are asymmetric regarding encoding/decoding time and memory requirements, with…
LLMs demonstrate strong performance on code benchmarks, yet consistent reasoning across forward and backward execution remains elusive. We present RoundTripCodeEval (RTCE), a benchmark of four code execution reasoning tasks that evaluates…
Deep learning is overwhelmingly dominant in the field of computer vision and image/video processing for the last decade. However, for image and video compression, it lags behind the traditional techniques based on discrete cosine transform…
Large language models (LLMs) exhibit degraded performance under prompt compression, but the mechanisms remain poorly understood. We introduce the Compression-Decay Comprehension Test (CDCT), a benchmark that independently measures…
This work addresses the persistent challenges of substantial training time and GPU resource requirements even when training lightweight encoder-vocoder models for Textless NLP. We reduce training steps significantly while improving…
Products codes (PCs) are conventionally decoded with efficient iterative bounded-distance decoding (iBDD) based on hard-decision channel outputs which entails a performance loss compared to a soft-decision decoder. Recently, several hybrid…
Recent deep-learning-based video compression methods brought coding gains over conventional codecs such as AVC and HEVC. However, learning-based codecs generally require considerable computation time and model complexity. In this paper, we…
Efficient data transmission across mobile multi-hop networks that connect edge devices to core servers presents significant challenges, particularly due to the variability in link qualities between wireless and wired segments. This…
With the development of higher resolution contents and displays, its significant volume poses significant challenges to the goals of acquiring, transmitting, compressing, and displaying high-quality video content. In this paper, we propose…
Recently, deep learning-based image compression has made signifcant progresses, and has achieved better ratedistortion (R-D) performance than the latest traditional method, H.266/VVC, in both subjective metric and the more challenging…
Visual encoding followed by token condensing has become the standard architectural paradigm in multi-modal large language models (MLLMs). Many recent MLLMs increasingly favor global native- resolution visual encoding over slice-based…
Compressed bitmap indexes are used in databases and search engines. Many bitmap compression techniques have been proposed, almost all relying primarily on run-length encoding (RLE). However, on unsorted data, we can get superior performance…
Codes are widely used in many engineering applications to offer robustness against noise. In large-scale systems there are several types of noise that can affect the performance of distributed machine learning algorithms -- straggler nodes,…
This paper presents the comparison of compression algorithms for voice transferring method over SMS in satellite communication. Voice transferring method over SMS is useful in situations when signal strength is low and due to poor signal…
In this paper, an extended combined approach of phrase based statistical machine translation (SMT), example based MT (EBMT) and rule based MT (RBMT) is proposed to develop a novel hybrid data driven MT system capable of outperforming the…
In this work, we study leveraging extra text data to improve low-resource end-to-end ASR under cross-lingual transfer learning setting. To this end, we extend our prior work [1], and propose a hybrid Transformer-LSTM based architecture.…
In large-scale distributed computing clusters, such as Amazon EC2, there are several types of "system noise" that can result in major degradation of performance: bottlenecks due to limited communication bandwidth, latency due to straggler…
We describe a novel extension of subspace codes for noncoherent networks, suitable for use when the network is viewed as a communication system that introduces both dimension and symbol errors. We show that when symbol erasures occur in a…
Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level features from big data. However, the current demand of DNNs for…
Communication-constrained algorithms for decentralized learning and optimization rely on local updates coupled with the exchange of compressed signals. In this context, differential quantization is an effective technique to mitigate the…