← Authors

Shaolei Zhang

28 papers · 2021–2025 · 6 conferences · across top CS/AI conferences

Achievements

🐝 Cross-Pollinator (13) 🐣 Hot Topic Early Bird πŸ—ΊοΈ Taxonomy Completionist (51) πŸŒ‰ Interdisciplinary Bridge 🧭 Keyword Pioneer 🌈 Renaissance Researcher (6) 🌍 Conference Polyglot (6) 🀝 Dynamic Duo (28) πŸ”¬ Deep Specialist (14) πŸ† Keyword Champion (5) πŸ—ƒοΈ Keyword Collector (122) ⚑ Prolific Year (6) ❓ The Questioner πŸ”₯ Unstoppable (5) πŸ’Ž Century Club (28)

Conferences

ACL (12) EMNLP (9) ICLR (3) AAAI (2) NAACL (1) NIPS (1)

Top co-authors

Yang Feng (28) Shoutao Guo (11) Zhengrui Ma (6) Qingkai Fang (6) Min Zhang (4) Tian Yu (2) Yan Zhou (2) Liangyou Li (1) Kangyu Qiao (1) Zhongjun He (1)

Keywords

simultaneous machine translation (10) simultaneous translation (7) latency optimization (5) large language model (5) wait-k policy (3) machine translation (3) neural machine translation (3) streaming transformer (2) simultaneous generation (2) translation quality (2) streaming input (2) non-autoregressive generation (2) contrastive learning (2) multi-head attention (2) policy learning (2) speech synthesis (2) hallucination mitigation (2) text generation (2) speech-to-speech translation (2) knowledge editing (1)

Papers

LLaMA-Omni: Seamless Speech Interaction with Large Language Models ICLR 2025
Large Language Models Are Read/Write Policy-Makers for Simultaneous Generation AAAI 2025
LLaMA-Omni 2: LLM-based Real-time Spoken Chatbot with Autoregressive Streaming Speech Synthesis ACL 2025
LLaVA-Mini: Efficient Image and Video Large Multimodal Models with One Vision Token ICLR 2025
IG-Pruning: Input-Guided Block Pruning for Large Language Models EMNLP 2025
AlignX: Advancing Multilingual Large Language Models with Multilingual Representation Alignment EMNLP 2025
TruthX: Alleviating Hallucinations by Editing Large Language Models in Truthful Space ACL 2024
Truth-Aware Context Selection: Mitigating Hallucinations of Large Language Models Being Misled by Untruthful Contexts ACL 2024
A Non-autoregressive Generation Framework for End-to-End Simultaneous Speech-to-Any Translation ACL 2024
Can We Achieve High-quality Direct Speech-to-Speech Translation without Parallel Speech Data? ACL 2024
Decoder-only Streaming Transformer for Simultaneous Translation ACL 2024
StreamSpeech: Simultaneous Speech-to-Speech Translation with Multi-task Learning ACL 2024
Unified Segment-to-Segment Framework for Simultaneous Sequence Generation NIPS 2023
Learning Optimal Policy for Simultaneous Machine Translation via Binary Search ACL 2023
End-to-End Simultaneous Speech Translation with Differentiable Segmentation ACL 2023
Non-autoregressive Streaming Transformer for Simultaneous Translation EMNLP 2023
Simultaneous Machine Translation with Tailored Reference EMNLP 2023
Hidden Markov Transformer for Simultaneous Machine Translation ICLR 2023
Information-Transport-based Policy for Simultaneous Translation EMNLP 2022
Turning Fixed to Adaptive: Integrating Post-Evaluation into Simultaneous Machine Translation EMNLP 2022
Modeling Dual Read/Write Paths for Simultaneous Machine Translation ACL 2022
Gaussian Multi-head Attention for Simultaneous Machine Translation ACL 2022
Reducing Position Bias in Simultaneous Machine Translation with Length-Aware Framework ACL 2022
Wait-info Policy: Balancing Source and Target at Information Level for Simultaneous Machine Translation EMNLP 2022
ICT’s System for AutoSimTrans 2021: Robust Char-Level Simultaneous Translation NAACL 2021
Future-Guided Incremental Transformer for Simultaneous Translation AAAI 2021
Universal Simultaneous Machine Translation with Mixture-of-Experts Wait-k Policy EMNLP 2021
Modeling Concentrated Cross-Attention for Neural Machine Translation with Gaussian Mixture Model EMNLP 2021