Acyr Locatelli
7 papers · 2024–2026 · 4 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+2 more ↓ Show less ↑
π Conference Polyglot (3) π Interdisciplinary Bridge π§ Keyword Pioneer π£ Hot Topic Early Bird π Cross-Pollinator (13)
πΊοΈ
Taxonomy Completionist
(19)
β
The Questioner
Conferences
ICLR (3)
NIPS (2)
ACL (1)
EMNLP (1)
Top co-authors
Keywords
large language model
(3)
attention mechanism
(2)
mixture of expert
(2)
model compression
(2)
efficient computing
(1)
perplexity evaluation
(1)
memory efficiency
(1)
feed-forward network
(1)
attention head
(1)
context window
(1)
kv cache compression
(1)
long context inference
(1)
kv cache
(1)
expert specialization
(1)
parameter upcycling
(1)
attention weight
(1)
dense model
(1)
long context
(1)
key-value cache
(1)
model initialization
(1)
Papers
One Tokenizer To Rule Them All: Emergent Language Plasticity via Multilingual Tokenizers
ACL 2026
Procedural Knowledge in Pretraining Drives Reasoning in Large Language Models
ICLR 2025
To Code or Not To Code? Exploring Impact of Code in Pre-training
ICLR 2025
Nexus: Adaptive Upcycling to Efficiently Pretrain Mixture of Experts
EMNLP 2025
Pushing Mixture of Experts to the Limit: Extremely Parameter Efficient MoE for Instruction Tuning
ICLR 2024
BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
NIPS 2024
SnapKV: LLM Knows What You are Looking for Before Generation
NIPS 2024