Szymon Tworkowski
6 papers · 2022–2025 · 5 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓
🌉
Interdisciplinary Bridge
🧭
Keyword Pioneer
🌍
Conference Polyglot
(5)
🐝
Cross-Pollinator
(7)
🐣
Hot Topic Early Bird
Conferences
NIPS (2)
AAAI (1)
ACL (1)
ICLR (1)
NAACL (1)
Top co-authors
Keywords
large language model
(2)
context utilization
(2)
long context
(2)
in-context learning
(1)
language modeling
(1)
language model
(1)
context length
(1)
automated theorem proving
(1)
context window
(1)
key-value cache
(1)
model efficiency
(1)
premise selection
(1)
hierarchical architecture
(1)
language model pre-training
(1)
causal masking
(1)
document concatenation
(1)
knowledge memorization
(1)
transformer model
(1)
interactive theorem prover
(1)
sequence composition
(1)
Papers
Structured Packing in LLM Training Improves Long Context Utilization
AAAI 2025
Analysing The Impact of Sequence Composition on Language Model Pre-Training
ACL 2024
Magnushammer: A Transformer-Based Approach to Premise Selection
ICLR 2024
Focused Transformer: Contrastive Training for Context Scaling
NIPS 2023
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
NIPS 2022
Hierarchical Transformers Are More Efficient Language Models
NAACL 2022