Xuanwu Yin
4 papers · 2025–2026 · 3 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌍
Conference Polyglot
(2)
🌉
Interdisciplinary Bridge
🐝
Cross-Pollinator
(15)
Conferences
AAAI (2)
ACL (1)
ICML (1)
Top co-authors
Keywords
model compression
(1)
post-training quantization
(1)
neural network optimization
(1)
structured sparsity
(1)
inference efficiency
(1)
kv cache
(1)
weight permutation
(1)
channel pruning
(1)
activation outlier
(1)
unstructured sparsity
(1)
attention computation
(1)
transformer model
(1)
flatness metric
(1)
bidirectional diagonal quantization
(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
Theory-optimal Quantization Based on Flatness
ACL 2026
Gumiho: A Hybrid Architecture to Prioritize Early Tokens in Speculative Decoding
ICML 2025