Haiduo Huang

5 papers · 2025–2026 · 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 (11) ⭐ Rising Star (5)

Venues

AAAI (2) ACL (1) CVPR (1) ICML (1)

Top co-authors

Pengju Ren (4) Zhenhua Liu (2) Tian Xia (2) Xuanwu Yin (1) Yixing Xu (1) Fuwei Yang (1) Edith C. H. Ngai (1) Dong Li (1) Yadong Zhang (1) Jiangcheng Song (1)

Research topics

Deep Learning (4) Artificial Intelligence (3) Machine Learning (3) Application Areas (3) Core AI (3) Architectures (2) Techniques (2) Natural Language Processing (1) Generation (1) Learning Types (1) Models (1)

Keywords

speculative decoding (2) large language model (2) model quantization (1) curriculum learning (1) knowledge distillation (1) channel attention (1) instruction following (1) efficient inference (1) mixture of expert (1) parameter efficiency (1) inference acceleration (1) draft model (1) parameter compression (1) quantization-aware training (1) mixed precision training (1) parallel decoding (1) partial convolution (1) token acceptance rate (1) bit switching (1) early tokens (1)

Papers

Double Rounding: Nearly Lossless Adaptive Bit Switching for QAT AAAI 2026 Jakiro: Boosting Speculative Decoding via Decoupled MoE ACL 2026 PartialNet: Compute Less, Perform Better AAAI 2026 SelecTKD: Selective Token-Weighted Knowledge Distillation for LLMs CVPR 2026 Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding ICML 2025