Guanchen Li

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 ⭐ Rising Star (5)

Venues

AAAI (2) COLING (1) ICML (1) NAACL (1)

Top co-authors

Dong Li (5) Emad Barsoum (4) Yixing Xu (3) Lu Tian (2) Lian Liu (2) Ji Liu (2) Xiandong Zhao (2) Xuanwu Yin (2) Zeping Li (2) Jie He (1)

Research topics

Machine Learning (5) Artificial Intelligence (4) Application Areas (4) Core AI (4) Optimization & Theory (4) Natural Language Processing (1) Resources & Methods (1)

Keywords

model compression (2) regularization (1) neural network optimization (1) model pruning (1) sparsity (1) structured sparsity (1) inference efficiency (1) pre-trained language model (1) inference acceleration (1) one-shot pruning (1) kv cache (1) speculative decoding (1) weight permutation (1) channel pruning (1) parallel decoding (1) activation outlier (1) non-autoregressive generation (1) unstructured sparsity (1) attention computation (1) large language model (1)

Papers

Learnable Permutation for Structured Sparsity on Transformer Models AAAI 2026 SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning AAAI 2026 Amphista: Bi-directional Multi-head Decoding for Accelerating LLM Inference NAACL 2025 BaWA: Automatic Optimizing Pruning Metric for Large Language Models with Balanced Weight and Activation ICML 2025 Enhancing One-Shot Pruned Pre-trained Language Models through Sparse-Dense-Sparse Mechanism COLING 2025