Shezheng Song

5 papers · 2024–2026 · 2 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 🗺️ Taxonomy Completionist (11) 🏆 Keyword Champion (2) ❓ The Questioner

Venues

AAAI (4) CVPR (1)

Top co-authors

Shasha Li (5) Jie Yu (4) Xiaopeng Li (4) Shan Zhao (3) Chengyu Wang (3) Bin Ji (2) Tianwei Yan (2) Qian Wan (2) Jun Ma (2) Jing Wang (1)

Research topics

Artificial Intelligence (5) Core AI (5) Natural Language Processing (3) Deep Learning (2) Resources & Methods (2) Machine Learning (1) Applications (1) Architectures (1) Core Methods (1) Learning Types (1)

Keywords

multimodal large language model (2) large language model (2) knowledge update (2) wavelet transform (1) model editing (1) text matching (1) knowledge graph (1) hidden state (1) language model (1) feed-forward network (1) visual prompt (1) multimodal reasoning (1) word embedding (1) knowledge updating (1) parameter updating (1) multimodal entity linking (1) entity representation (1) knowledge embedding (1) vision-language understanding (1) embedding alteration (1)

Papers

Leveraging Image as Compressed Visual Prompt and Hierarchical Visual Knowledge for Effective Image Utilization in MLLMs AAAI 2026 Where Does Vision Meet Language? Understanding and Refining Visual Fusion in MLLMs via Contrastive Attention CVPR 2026 SWEA: Updating Factual Knowledge in Large Language Models via Subject Word Embedding Altering AAAI 2025 A Dual-Way Enhanced Framework from Text Matching Point of View for Multimodal Entity Linking AAAI 2024 PMET: Precise Model Editing in a Transformer AAAI 2024