Xuanwu Yin
4 papers · 2025–2026 · 3 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
Top co-authors
Research topics
Keywords
model compression
(1)
transformer architecture
(1)
post-training quantization
(1)
neural network optimization
(1)
structured sparsity
(1)
inference efficiency
(1)
kv cache
(1)
speculative decoding
(1)
draft model
(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)
early tokens
(1)
mlp heads
(1)
parallel configuration
(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