Mingyuan Ma

6 papers · 2023–2026 · 6 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 · Silver 🌉 Interdisciplinary Bridge · Bronze 🗺️ Taxonomy Completionist (17) 🐣 Hot Topic Early Bird 👥 Mega-Team · Squad

Venues

ICCV (1) ICLR (1) ICML (1) NAACL (1) OSDI (1) WACV (1)

Top co-authors

Yiran Chen (2) Yang Wang (1) Xinyuan Tong (1) Yudong Liu (1) Hancheng Ye (1) Junyi Shu (1) Zhiyuan Li (1) Jiahang Xu (1) Qingda Lu (1) Fan Yang (1)

Research topics

Artificial Intelligence (5) Machine Learning (5) Core AI (4) Deep Learning (3) Learning Types · Machine Learning (3) Application Areas (2) Computer Science (1) Computer Vision (1) Analysis (1) Architectures (1) Learning Paradigms (1) Learning Types · Deep Learning (1) Models (1) Systems (1)

Keywords

large language model (2) vision-language model (2) catastrophic forgetting (1) semantic segmentation (1) point cloud (1) 3d vision (1) neural architecture search (1) model serving (1) hierarchical model (1) monte carlo tree search (1) weight averaging (1) zero-shot transfer (1) token pruning (1) hardware acceleration (1) on-device model (1) feature distillation (1) inference serving (1) resource efficiency (1) function calling (1) small language model (1)

Papers

Prism: Cost-Efficient Multi-LLM Serving via GPU Memory Ballooning OSDI 2026 CoreMatching: A Co-adaptive Sparse Inference Framework with Token and Neuron Pruning for Comprehensive Acceleration of Vision-Language Models ICML 2025 Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solver ICLR 2025 Octopus: On-device language model for function calling of software APIs NAACL 2025 PIDS: Joint Point Interaction-Dimension Search for 3D Point Cloud WACV 2023 Preventing Zero-Shot Transfer Degradation in Continual Learning of Vision-Language Models ICCV 2023