Scholar
Yucheng Li
Google Scholar ID: 6lwf5TcAAAAJ
University of Surrey
Citations & Impact
Citations
930
H-index
14
i10-index
15
Publications
20
Co-authors
0
Publications
Resume
Academic Achievements
- Published 'SecurityLingua: Efficient Defense of LLM Jailbreak Attacks via Security-Aware Prompt Compression' at COLM 2025.
- Published 'MMInference: Accelerating Pre-filling for Long-Context VLMs via Modality-Aware Permutation Sparse Attention' at ICML 2025.
- Published 'SCBench: A KV Cache-Centric Analysis of Long-Context Methods' at ICLR 2025.
- Published 'MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention' at NeurIPS 2024 (Spotlight).
- Published 'With Ears to See and Eyes to Hear: Sound Symbolism Experiments with Multimodal Large Language Models' at EMNLP 2024.
- Published 'On the Rigour of Scientific Writing: Criteria, Analysis, and Insights' and 'An Open Source Data Contamination Report for Large Language Models' in EMNLP 2024 Findings.
- Published 'LatestEval: Addressing Data Contamination in Language Model Evaluation through Dynamic and Time-Sensitive Test Construction' at AAAI 2024.
- Published 'Compressing Context to Enhance Inference Efficiency of Large Language Models' at EMNLP 2023.
- Published 'Metaphor Detection via Explicit Basic Meanings Modelling' at ACL 2023.
- Published 'FrameBERT: Conceptual Metaphor Detection with Frame Embedding Learning' and another 'Metaphor Detection via Explicit Basic Meanings Modelling' at EACL 2023.
- Published 'The Secret of Metaphor on Expressing Stronger Emotion' at FigLang@EMNLP 2022.
- Published 'CM-Gen: A Neural Framework for Chinese Metaphor Generation with Explicit Context Modelling' at COLING 2022.
- Published 'Nominal Metaphor Generation with Multitask Learning' at INLG 2022.
- Published 'An Argument Extraction Decoder in Open Information Extraction' at ECIR 2021.
- Authored several preprints including 'Evaluating Large Language Models for Generalization and Robustness via Data Compression' and 'Recent Advances in Neural Text Generation: A Task-Agnostic Survey'.