Guangyan Li

3 papers · 2024–2026 · 3 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

🌍 Conference Polyglot · Bronze 🌉 Interdisciplinary Bridge · Bronze 🏆 Keyword Champion

Venues

AAAI (1) ACL (1) ICML (1)

Top co-authors

Wensheng Zhang (2) Yongqiang Tang (2) Luoyang Sun (1) Siyuan Li (1) Li Ding (1) Jianhua Li (1) Jun Wang (1) Haifeng Zhang (1) Cheng Deng (1) Xi Lin (1)

Research topics

Artificial Intelligence (3) Core AI (3) Machine Learning (1) Natural Language Processing (1) Application Areas (1) Applications (1) Core Methods (1)

Keywords

large language model (2) adversarial robustness (1) feed-forward network (1) multi-head self-attention (1) activation sparsity (1) structured pruning (1) low-rank matrix approximation (1) text detection (1) weight sparsity (1) paraphrasing attack (1) magnitude-based pruning (1) sentiment distribution (1) gradient-free structured channel pruning (1) model compression (1) input activation weighted singular value decomposition (1)

Papers

Dual Activation-Weight Sparsity: A Training-Free Framework for Efficient Large Language Model Compression ACL 2026 Model-Agnostic Sentiment Distribution Stability Analysis for Robust LLM-Generated Texts Detection AAAI 2026 LoRAP: Transformer Sub-Layers Deserve Differentiated Structured Compression for Large Language Models ICML 2024