Liangzhen Lai

4 papers · 2022–2025 · 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 (15) 🐣 Hot Topic Early Bird

Venues

ACL (1) CVPR (1) ICML (1) NAACL (1)

Top co-authors

Vikas Chandra (3) Yangyang Shi (2) Changsheng Zhao (2) Ernie Chang (2) Jiaqi Gu (1) Saurabh Agarwal (1) Ahmed Aly (1) Zechun Liu (1) Anas Mahmoud (1) Yu-Hsin Chen (1)

Research topics

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

Keywords

model compression (1) semantic segmentation (1) vision transformer (1) model architecture (1) automatic speech recognition (1) efficient inference (1) embedding sharing (1) early exit (1) weight sharing (1) dense prediction (1) inference optimization (1) inference acceleration (1) speculative decoding (1) model optimization (1) high resolution (1) multi-scale representation (1) model efficiency (1) on-device inference (1) multi-scale learning (1) power efficiency (1)

Papers

Breaking Down Power Barriers in On-Device Streaming ASR: Insights and Solutions NAACL 2025 LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding ACL 2024 MobileLLM: Optimizing Sub-billion Parameter Language Models for On-Device Use Cases ICML 2024 Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation CVPR 2022