Akide Liu

5 papers · 2024–2026 · 4 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 (10) 🐣 Hot Topic Early Bird

Venues

AAAI (2) CVPR (1) ECCV (1) NeurIPS (1)

Top co-authors

Bohan Zhuang (4) Yefei He (2) Jing Liu (2) Feng Chen (2) Jianfei Cai (1) Hangjie Yuan (1) Hamid Rezatofighi (1) Zeyu Zhang (1) Haoyu He (1) Zhenbang Sun (1)

Research topics

Artificial Intelligence (3) Machine Learning (3) Core AI (3) Application Areas (2) Computer Vision (1) Deep Learning (1) Natural Language Processing (1) Learning Types (1) Processing (1) Resources & Methods (1) Techniques (1)

Keywords

multimodal large language model (2) token selection (1) model interpretability (1) memory optimization (1) denoising process (1) inference efficiency (1) sparse attention (1) latency reduction (1) inference acceleration (1) kv cache (1) spatial-temporal modeling (1) instruction-based image editing (1) video question answering (1) cross-attention module (1) key-value cache (1) cache compression (1) attention knockout (1) video large language model (1) large language model (1) spatial guidance (1)

Papers

An Empirical Study on How Video-LLMs Answer Video Questions CVPR 2026 MCIE: Multimodal LLM-Driven Complex Instruction Image Editing with Spatial Guidance AAAI 2026 OmniSparse: Training-Aware Fine-Grained Sparse Attention for Long-Video MLLMs AAAI 2026 MiniCache: KV Cache Compression in Depth Dimension for Large Language Models NeurIPS 2024 Motion Mamba: Efficient and Long Sequence Motion Generation ECCV 2024