Nguyen-Khang Le
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
Venues
Research topics
Keywords
speculative decoding
(3)
large language model
(2)
model acceleration
(2)
multilingual processing
(1)
efficient computing
(1)
low-resource language
(1)
language model
(1)
inference optimization
(1)
vocabulary adaptation
(1)
language-aware training
(1)
device-aware calibration
(1)
confidence score estimation
(1)
model compression
(1)
tree expansion
(1)
neural network pruning
(1)
multilingual nlp
(1)
Papers
AdaSpec: Adaptive Multilingual Speculative Decoding with Self-Synthesized Language-Aware Training and Vocabulary Simplification
AAAI 2026
UniSpec: Training-Free Speculative Decoding for Robust LLM Acceleration Across Languages and Hardware
ACL 2026
LangCompress: Language-Aware Compression of Large Language Models
IJCNLP 2025
SPECTRA: Faster Large Language Model Inference with Optimized Internal and External Speculation
ACL 2025