Related papers: A Modular-based Strategy for Mitigating Gradient C…

Simultaneous Machine Translation (SiMT) requires high-quality translations under strict real-time constraints, which traditional encoder-decoder policies with only READ/WRITE actions cannot fully address. We extend the action space of SiMT…

The rapid advancement of generative artificial intelligence has spurred innovative approaches to semantic communication, giving rise to a new paradigm known as generative semantic communication (GSC). The integration of flexible cross-modal…

Multi-task learning (MTL) paradigm focuses on jointly learning two or more tasks, aiming for significant improvement w.r.t model's generalizability, performance, and training/inference memory footprint. The aforementioned benefits become…

Neural Text-to-Speech (TTS) systems find broad applications in voice assistants, e-learning, and audiobook creation. The pursuit of modern models, like Diffusion Models (DMs), holds promise for achieving high-fidelity, real-time speech…

Dialogue State Tracking (DST) is designed to monitor the evolving dialogue state in the conversations and plays a pivotal role in developing task-oriented dialogue systems. However, obtaining the annotated data for the DST task is usually a…

Auto-regressive speech-text models pre-trained on interleaved text tokens and discretized speech tokens demonstrate strong speech understanding and generation, yet remain substantially less compute-efficient than text LLMs, partly due to…

In multimodal graph learning, graph structures that integrate information from multiple sources, such as vision and text, can more comprehensively model complex entity relationships. However, the continuous growth of their data scale poses…

Transformer-based models have achieved state-of-the-art performance on speech translation tasks. However, the model architecture is not efficient enough for streaming scenarios since self-attention is computed over an entire input sequence…

Large language models have demonstrated exceptional performance across multiple crosslingual NLP tasks, including machine translation (MT). However, persistent challenges remain in addressing context-sensitive units (CSUs), such as…

Increasing AI computing demands and slowing transistor scaling have led to the advent of Multi-Chip-Module (MCMs) based accelerators. MCMs enable cost-effective scalability, higher yield, and modular reuse by partitioning large chips into…

Significant improvements in end-to-end speech translation (ST) have been achieved through the application of multi-task learning. However, the extent to which auxiliary tasks are highly consistent with the ST task, and how much this…

Large language models accumulate extensive parametric knowledge through pre-training. However, knowledge conflicts occur when outdated or incorrect parametric knowledge conflicts with external knowledge in the context. Existing methods…

Prompt learning facilitates the efficient adaptation of Vision-Language Models (VLMs) to various downstream tasks. However, it faces two significant challenges: (1) inadequate modeling of class embedding distributions for unseen instances,…

End-to-end Speech Translation is hindered by a lack of available data resources. While most of them are based on documents, a sentence-level version is available, which is however single and static, potentially impeding the usefulness of…

We consider stochastic convex optimization problems where the objective is an expectation over smooth functions. For this setting we suggest a novel gradient estimate that combines two recent mechanism that are related to notion of…

Multi-task learning (MTL) has shown effectiveness in exploiting shared information across tasks to improve generalization. MTL assumes tasks share similarities that can improve performance. In addition, boosting algorithms have demonstrated…

The study of the attention mechanism has sparked interest in many fields, such as language modeling and machine translation. Although its patterns have been exploited to perform different tasks, from neural network understanding to textual…

Mastering a skill generally relies on both hands-on experience from doers and insightful, high-level guidance by mentors. Will this strategy also work well for solving complex non-convex optimization problems? Here, a common gradient-based…

This paper introduces a novel physical-layer method labelled as Multi-Modal Concurrent Transmission (MMCT) for efficient transmission of multiple data streams with different reliability-latency performance requirements. The MMCT arranges…

Accelerators, like GPUs, have become a trend to deliver future performance desire, and sharing the same virtual memory space between CPUs and GPUs is increasingly adopted to simplify programming. However, address translation, which is the…