Related papers: Trellis-Extended Codebooks and Successive Phase Ad…
KEPLMs are pre-trained models that utilize external knowledge to enhance language understanding. Previous language models facilitated knowledge acquisition by incorporating knowledge-related pre-training tasks learned from relation triples…
Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly stemming from communication bottlenecks in attention…
In frequency division duplex (FDD) multiple-input multiple-output (MIMO) wireless communications, limited channel state information (CSI) feedback is a central tool to support advanced single- and multi-user MIMO beamforming/precoding. To…
Test-time scaling (TTS) has become an effective approach for improving large language model performance by allocating additional computation during inference. However, existing TTS strategies are largely hand-crafted: researchers manually…
Over the past decade, a series of unflagging efforts have been dedicated to developing highly expressive and controllable text-to-speech (TTS) systems. In general, the holistic TTS comprises two interconnected components: the frontend…
Large language models (LLMs) often exhibit performance disparities across languages, with naive multilingual fine-tuning frequently degrading performance due to negative cross-lingual interference. To address this, we introduce COMPASS…
Large Language Models (LLMs) have become widely used across diverse NLP tasks and domains, demonstrating their adaptability and effectiveness. In the realm of Electronic Design Automation (EDA), LLMs show promise for tasks like…
Efficient channel state information (CSI) compression is essential in frequency division duplexing (FDD) massive multiple-input multiple-output (MIMO) systems due to the substantial feedback overhead. Recently, deep learning-based…
Backward compatibility is an essential ingredient for the success of new technologies. In the context of in-band full-duplex (FD) communication, FD base stations (BSs) should support half-duplex (HD) users' equipment (UEs) without…
Frame Synchronization (FS) is required in several communication standards in order to recover the individual frames that have been aggregated in a burst. This paper proposes a low-delay and reducedcomplexity Sliding Trellis (ST)-based FS…
Beam codebooks are a recent feature to enable high dimension multiple-input multiple-output in 5G. Codebooks comprised of customizable beamforming weights can be used to transmit reference signals and aid the channel state information (CSI)…
Current text to speech (TTS) systems usually leverage a cascaded acoustic model and vocoder pipeline with mel-spectrograms as the intermediate representations, which suffer from two limitations: 1) the acoustic model and vocoder are…
Existing speech semantic communication systems mainly based on Joint Source-Channel Coding (JSCC) architectures have demonstrated impressive performance, but their effectiveness remains limited by model structures specifically designed for…
End-to-end text-to-speech (TTS) synthesis is a method that directly converts input text to output acoustic features using a single network. A recent advance of end-to-end TTS is due to a key technique called attention mechanisms, and all…
The emergence of multi-codebook neutral audio codecs such as Residual Vector Quantization (RVQ) and Group Vector Quantization (GVQ) has significantly advanced Large-Language-Model (LLM) based Text-to-Speech (TTS) systems. These codecs are…
Time division duplexing (TDD) has become the dominant duplexing mode in 5G and beyond due to its ability to exploit channel reciprocity for efficient downlink channel state information (CSI) acquisition. However, channel aging caused by…
In the last decade, the demand for Internet applications has been increased, which increases the number of data centers across the world. These data centers are usually connected to each other using long-distance and high-speed networks. As…
In this paper, we propose a novel non-orthogonal multiple access (NOMA) scheme based on trellis-coded modulation (TCM). Different from those in the traditional code-domain NOMA, the incoming data streams of multiple users are jointly coded…
With the number of smart devices increasing, the demand for on-device text-to-speech (TTS) increases rapidly. In recent years, many prominent End-to-End TTS methods have been proposed, and have greatly improved the quality of synthesized…
Large Language Models (LLMs) have demonstrated impressive performance on multiple-choice question answering (MCQA) benchmarks, yet they remain highly vulnerable to minor input perturbations. In this paper, we introduce and evaluate Token…