相关论文: Decoder-only Streaming Transformer for Simultaneou…

Speech translation (ST) aims to learn transformations from speech in the source language to the text in the target language. Previous works show that multitask learning improves the ST performance, in which the recognition decoder generates…

Multilingual machine translation (MMT) benefits from cross-lingual transfer but is a challenging multitask optimization problem. This is partly because there is no clear framework to systematically learn language-specific parameters.…

The large attention-based encoder-decoder network (Transformer) has become prevailing recently due to its effectiveness. But the high computation complexity of its decoder raises the inefficiency issue. By examining the mathematic…

In this paper, we introduce a data-driven approach for Formality-Sensitive Machine Translation (FSMT) that caters to the unique linguistic properties of four target languages. Our methodology centers on two core strategies: 1)…

Neural machine translation (NMT) becomes a new state-of-the-art and achieves promising translation results using a simple encoder-decoder neural network. This neural network is trained once on the parallel corpus and the fixed network is…

The field of neural machine translation (NMT) has changed with the advent of large language models (LLMs). Much of the recent emphasis in natural language processing (NLP) has been on modeling machine translation and many other problems…

Simultaneous speech-to-speech translation (Simul-S2ST, a.k.a streaming speech translation) outputs target speech while receiving streaming speech inputs, which is critical for real-time communication. Beyond accomplishing translation…

The dominant sequence transduction models are based on complex recurrent or convolutional neural networks in an encoder-decoder configuration. The best performing models also connect the encoder and decoder through an attention mechanism.…

Simultaneous machine translation (SimulMT) speeds up the translation process by starting to translate before the source sentence is completely available. It is difficult due to limited context and word order difference between languages.…

This paper introduces Dynamic Embeddings with Task-Oriented prompting (DETOT), a novel approach aimed at improving the adaptability and efficiency of machine learning models by implementing a flexible embedding layer. Unlike traditional…

3D synthetic-to-real unsupervised domain adaptive segmentation is crucial to annotating new domains. Self-training is a competitive approach for this task, but its performance is limited by different sensor sampling patterns (i.e.,…

Simultaneous speech translation (SST) takes streaming speech input and generates text translation on the fly. Existing methods either have high latency due to recomputation of input representations, or fall behind of offline ST in…

Transformer models serve as the backbone of many state-ofthe-art language models, and most use the scaled dot-product attention (SDPA) mechanism to capture relationships between tokens. However, the straightforward implementation of SDPA…

Machine translation is generally understood as generating one target text from an input source document. In this paper, we consider a stronger requirement: to jointly generate two texts so that each output side effectively depends on the…

The encoder-decoder is the typical framework for Neural Machine Translation (NMT), and different structures have been developed for improving the translation performance. Transformer is one of the most promising structures, which can…

Since context modeling is critical for estimating depth from a single image, researchers put tremendous effort into obtaining global context. Many global manipulations are designed for traditional CNN-based architectures to overcome the…

Streaming recognition of multi-talker conversations has so far been evaluated only for 2-speaker single-turn sessions. In this paper, we investigate it for multi-turn meetings containing multiple speakers using the Streaming Unmixing and…

Current state-of-the-art machine translation systems are based on encoder-decoder architectures, that first encode the input sequence, and then generate an output sequence based on the input encoding. Both are interfaced with an attention…

Decoder-only language models are stateless: hidden representations are discarded after every forward pass and nothing persists across sessions. Jeong (2026a) showed that trained memory adapters give a frozen encoder-decoder backbone…

Generally, the decoder-only large language models (LLMs) are adapted to context-aware neural machine translation (NMT) in a concatenating way, where LLMs take the concatenation of the source sentence (i.e., intra-sentence context) and the…