Papers by Zixun Zhang
DCP: Dual-Cue Pruning for Efficient Large Vision-Language Models (2025.emnlp-main)
Copied to clipboard
| Challenge: | Existing pruning methods for large vision language models use visual tokens to prune . existing methods fail to balance efficiency and semantic alignment due to large number of visual token. |
| Approach: | They propose a cross-modal pruning framework that considers textual semantics and visual self-attention to combine them to achieve efficient inference acceleration. |
| Outcome: | The proposed pruning framework can retain only 25% of the visual tokens, with a minimal performance degradation of only 0.063% on LLaVA-1.5-13B. |
DECOR: Improving Coherence in L2 English Writing with a Novel Benchmark for Incoherence Detection, Reasoning, and Rewriting (2024.emnlp-main)
Copied to clipboard
| Challenge: | Existing automated writing evaluation systems only detect incoherence in writing . a recent study has found that incorporating specific reasons for incohence improves the quality of rewrites . |
| Approach: | They propose a benchmark that includes expert annotations for detecting incoherence in L2 English writing, identifying the underlying reasons, and rewriting the incoerent sentences. |
| Outcome: | The proposed benchmark improves coherence in L2 English writing by fine-tuning models . the authors find that incorporating specific reasons improves quality of rewrites . |
ProLex: A Benchmark for Language Proficiency-oriented Lexical Substitution (2024.findings-acl)
Copied to clipboard
| Challenge: | Lexical Substitution fails to consider substitutes of equal or higher proficiency than the target word. |
| Approach: | They propose a task to find appropriate substitutes for a given word in a context sentence but not those that are of equal or higher proficiency than the target. |
| Outcome: | The proposed model outperforms ChatGPT by an average of 3.2% in F-score and achieves comparable results with GPT-4 on ProLex. |