Enxin Song

4 papers · 2024–2025 · 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 🗺️ Taxonomy Completionist (12) 🐣 Hot Topic Early Bird

Venues

ICLR (2) CVPR (1) ICCV (1)

Top co-authors

Wenhao Chai (3) Tian Ye (3) Gaoang Wang (2) Jenq-Neng Hwang (2) Chenlin Meng (1) Xiangtai Li (1) Yilun Du (1) Feiyang Wu (1) Jinbin Bai (1) Xuexiang Wen (1)

Research topics

Computer Vision (4) Deep Learning (3) Processing (3) Artificial Intelligence (2) Architectures (2) Core AI (2) Models (2) Machine Learning (1) Application Areas (1) Generation (1) Learning Types (1) Optimization & Theory (1)

Keywords

large language model (2) video understanding (2) video captioning (2) multimodal large language model (1) positional encoding (1) memory mechanism (1) linear rnn (1) video-language model (1) model efficiency (1) token merging (1) masked image modeling (1) video foundation model (1) high-resolution image generation (1) generative transformer (1) long video (1) long video processing (1) visual token merge (1) sparse memory (1) cider (1) human elo ranking (1)

Papers

AuroraCap: Efficient, Performant Video Detailed Captioning and a New Benchmark ICLR 2025 Bringing RNNs Back to Efficient Open-Ended Video Understanding ICCV 2025 Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis ICLR 2025 MovieChat: From Dense Token to Sparse Memory for Long Video Understanding CVPR 2024