19 citations · 80 across the 35 of their papers we have counts for
35 papers
Magnitude-Direction Decoupling for Fast Video Generation with Flow Matching Models
Haonan Xu, Feiyang Chen, Songkui Chen +5
Flow matching models for video generation achieve impressive performance but suffer from high computational overhead due to iterative denoising. In fact, the original model is not…
MLLM-Guided Semantic Correction for Text-to-Video Generation
Junhao Chen, Zheqi Lv, Keting Yin +6
Recent advances in diffusion models and Transformer architectures have led to significant progress in text-to-video generation. However, these models often suffer from semantic err…
: Attention-Aware Accurate KV Cache Fusion for Fast Large Language Model Serving
Yuechi Zhou, Yi Su, Jianxin Zhang +5
Large language models (LLMs) have demonstrated strong capabilities in processing long contexts, enabling them to tackle tasks involving long textual inputs such as multi-turn conve…
Adacc: An Adaptive Framework Unifying Compression and Activation Recomputation for LLM Training
Ping Chen, Zhuohong Deng, Ping Li +6
Training large language models (LLMs) is often constrained by GPU memory limitations. To alleviate memory pressure, activation recomputation and data compression have been proposed…
Huawei Cloud Model-as-a-Service on the CloudMatrix384 SuperPod
Ao Xiao, Bangzheng He, Baoquan Zhang +125
Scaled-out MoE LLMs and scaled-up SuperPods create new systems challenges for production Model-as-a-Service (MaaS), requiring disaggregation, low-latency communication, and decentr…
Alignment-Augmented Speculative Decoding with Alignment Sampling and Conditional Verification
Jikai Wang, Zhenxu Tian, Juntao Li +5
Recent works have revealed the great potential of speculative decoding in accelerating the autoregressive generation process of large language models. The success of these methods…
Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models
Yunxin Li, Zhenyu Liu, Zitao Li +19
Reasoning lies at the heart of intelligence, shaping the ability to make decisions, draw conclusions, and generalize across domains. In artificial intelligence, as systems increasi…
Taming the Titans: A Survey of Efficient LLM Inference Serving
Ranran Zhen, Juntao Li, Yixin Ji +7
Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applicat…
MSceneSpeech: A Multi-Scene Speech Dataset For Expressive Speech Synthesis
Qian Yang, Jialong Zuo, Zhe Su +6
We introduce an open source high-quality Mandarin TTS dataset MSceneSpeech (Multiple Scene Speech Dataset), which is intended to provide resources for expressive speech synthesis.…
A General and Flexible Multi-concept Parsing Framework for Multilingual Semantic Matching
Dong Yao
Sentence semantic matching is a research hotspot in natural language processing, which is considerably significant in various key scenarios, such as community question answering, s…
TransFace: Unit-Based Audio-Visual Speech Synthesizer for Talking Head Translation
Xize Cheng, Rongjie Huang, Linjun Li +7
Direct speech-to-speech translation achieves high-quality results through the introduction of discrete units obtained from self-supervised learning. This approach circumvents delay…
StyleSinger: Style Transfer for Out-of-Domain Singing Voice Synthesis
Yu Zhang, Rongjie Huang, Ruiqi Li +6
Style transfer for out-of-domain (OOD) singing voice synthesis (SVS) focuses on generating high-quality singing voices with unseen styles (such as timbre, emotion, pronunciation, a…
Mirror: A Universal Framework for Various Information Extraction Tasks
Tong Zhu, Junfei Ren, Zijian Yu +7
Sharing knowledge between information extraction tasks has always been a challenge due to the diverse data formats and task variations. Meanwhile, this divergence leads to informat…
TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models
Shengpeng Ji, Jialong Zuo, Minghui Fang +5
Recently, there has been a growing interest in the field of controllable Text-to-Speech (TTS). While previous studies have relied on users providing specific style factor values ba…
Recognizing Unseen Objects via Multimodal Intensive Knowledge Graph Propagation
Likang Wu, Zhi Li, Hongke Zhao +5
Zero-Shot Learning (ZSL), which aims at automatically recognizing unseen objects, is a promising learning paradigm to understand new real-world knowledge for machines continuously.…
AraMUS: Pushing the Limits of Data and Model Scale for Arabic Natural Language Processing
Asaad Alghamdi, Xinyu Duan, Wei Jiang +9
Developing monolingual large Pre-trained Language Models (PLMs) is shown to be very successful in handling different tasks in Natural Language Processing (NLP). In this work, we pr…
Reference Matters: Benchmarking Factual Error Correction for Dialogue Summarization with Fine-grained Evaluation Framework
Mingqi Gao, Xiaojun Wan, Jia Su +2
Factuality is important to dialogue summarization. Factual error correction (FEC) of model-generated summaries is one way to improve factuality. Current FEC evaluation that relies…
CopyNE: Better Contextual ASR by Copying Named Entities
Shilin Zhou, Zhenghua Li, Yu Hong +3
End-to-end automatic speech recognition (ASR) systems have made significant progress in general scenarios. However, it remains challenging to transcribe contextual named entities (…
CED: Catalog Extraction from Documents
Tong Zhu, Guoliang Zhang, Zechang Li +7
Sentence-by-sentence information extraction from long documents is an exhausting and error-prone task. As the indicator of document skeleton, catalogs naturally chunk documents int…
A Survey on Arabic Named Entity Recognition: Past, Recent Advances, and Future Trends
Xiaoye Qu, Yingjie Gu, Qingrong Xia +3
As more and more Arabic texts emerged on the Internet, extracting important information from these Arabic texts is especially useful. As a fundamental technology, Named entity reco…
ReCo: Reliable Causal Chain Reasoning via Structural Causal Recurrent Neural Networks
Kai Xiong, Xiao Ding, Zhongyang Li +4
Causal chain reasoning (CCR) is an essential ability for many decision-making AI systems, which requires the model to build reliable causal chains by connecting causal pairs. Howev…
Distantly-Supervised Named Entity Recognition with Adaptive Teacher Learning and Fine-grained Student Ensemble
Xiaoye Qu, Jun Zeng, Daizong Liu +3
Distantly-Supervised Named Entity Recognition (DS-NER) effectively alleviates the data scarcity problem in NER by automatically generating training samples. Unfortunately, the dist…
Mining Word Boundaries in Speech as Naturally Annotated Word Segmentation Data
Lei Zhang, Zhenghua Li, Shilin Zhou +4
Inspired by early research on exploring naturally annotated data for Chinese word segmentation (CWS), and also by recent research on integration of speech and text processing, this…
Revisiting Pre-trained Language Models and their Evaluation for Arabic Natural Language Understanding
Abbas Ghaddar, Yimeng Wu, Sunyam Bagga +11
There is a growing body of work in recent years to develop pre-trained language models (PLMs) for the Arabic language. This work concerns addressing two major problems in existing…