Szymon Tworkowski
6 papers · 2022–2025 · 5 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 · Silver
🌉
Interdisciplinary Bridge · Bronze
🗺️
Taxonomy Completionist
(11)
🐣
Hot Topic Early Bird
Venues
Top co-authors
Research topics
Artificial Intelligence
(6)
Core AI
(6)
Machine Learning
(4)
Natural Language Processing
(4)
Resources & Methods
(4)
Deep Learning
(3)
Learning Types · Machine Learning
(2)
Learning Types · Deep Learning
(2)
Optimization & Theory · Machine Learning
(2)
Architectures
(1)
Optimization & Theory · Deep Learning
(1)
Keywords
large language model
(2)
automated theorem proving
(2)
context utilization
(2)
contrastive learning
(2)
premise selection
(2)
long context
(2)
context length
(1)
context window
(1)
key-value cache
(1)
model efficiency
(1)
hierarchical architecture
(1)
language model pretraining
(1)
causal masking
(1)
document concatenation
(1)
knowledge memorization
(1)
transformer model
(1)
interactive theorem prover
(1)
sequence composition
(1)
automated theorem prover
(1)
sequence modeling
(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
NeurIPS 2023
Hierarchical Transformers Are More Efficient Language Models
NAACL 2022
Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Provers
NeurIPS 2022