10 papers
Autoencoding-Free Context Compression for LLMs via Contextual Semantic Anchors
Xin Liu, Runsong Zhao, Pengcheng Huang +7
Context compression is an advanced technique that accelerates large language model (LLM) inference by converting long inputs into compact representations. Existing methods primaril…
Consensus-Aligned Neuron Efficient Fine-Tuning Large Language Models for Multi-Domain Machine Translation
Shuting Jiang, Ran Song, Yuxin Huang +4
Multi-domain machine translation (MDMT) aims to build a unified model capable of translating content across diverse domains. Despite the impressive machine translation capabilities…
M-CIF: Multi-Scale Alignment For CIF-Based Non-Autoregressive ASR
Ruixiang Mao, Xiangnan Ma, Qing Yang +7
The Continuous Integrate-and-Fire (CIF) mechanism provides effective alignment for non-autoregressive (NAR) speech recognition. This mechanism creates a smooth and monotonic mappin…
MTP-S2UT: Enhancing Speech-to-Speech Translation Quality with Multi-token Prediction
Jianjin Wang, Runsong Zhao, Xiaoqian Liu +6
Current direct speech-to-speech translation methods predominantly employ speech tokens as intermediate representations. However, a single speech token is not dense in semantics, so…
Multilingual Generative Retrieval via Cross-lingual Semantic Compression
Yuxin Huang, Simeng Wu, Ran Song +4
Generative Information Retrieval is an emerging retrieval paradigm that exhibits remarkable performance in monolingual scenarios.However, applying these methods to multilingual ret…
Multilingual Knowledge Graph Completion via Efficient Multilingual Knowledge Sharing
Cunli Mao, Xiaofei Gao, Ran Song +4
Large language models (LLMs) based Multilingual Knowledge Graph Completion (MKGC) aim to predict missing facts by leveraging LLMs' multilingual understanding capabilities, improvin…