Anej Svete
18 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 ↓+6 more ↓ Show less ↑
🗺️ Taxonomy Completionist (35) 🐣 Hot Topic Early Bird 🌍 Conference Polyglot · Silver 🌉 Interdisciplinary Bridge · Diamond 🤝 Dynamic Duo (18)
🤝
Dynamic Duo
(18)
🌈
Renaissance Researcher
(6)
❓
The Questioner
(2)
⚡
Prolific Year · Prolific
💎
Century Club · Bronze
🗃️
Keyword Collector
(81)
Venues
Top co-authors
Research topics
Machine Learning
(15)
Deep Learning
(14)
Optimization & Theory · Machine Learning
(13)
Architectures
(10)
Artificial Intelligence
(5)
Natural Language Processing
(5)
Core AI
(5)
Generation
(4)
Models
(4)
Computer Science
(3)
Mathematics & Optimization
(3)
Core Methods
(3)
Foundations
(3)
Optimization & Theory · Deep Learning
(3)
Learning Types
(2)
Keywords
language model
(10)
recurrent neural network
(8)
representational capacity
(4)
regular language
(3)
transformer architecture
(2)
formal language
(2)
n-gram model
(2)
hard attention
(2)
n-gram language model
(2)
theoretical analysis
(2)
finite state automaton
(2)
formal language theory
(2)
inductive bia
(2)
neural language model
(2)
probability distribution
(1)
label smoothing
(1)
attention mechanism
(1)
automata learning
(1)
formal methods
(1)
transfer learning
(1)
Papers
Gumbel Counterfactual Generation From Language Models
ICLR 2025
Information Locality as an Inductive Bias for Neural Language Models
ACL 2025
Training Neural Networks as Recognizers of Formal Languages
ICLR 2025
Unique Hard Attention: A Tale of Two Sides
ACL 2025
An L* Algorithm for Deterministic Weighted Regular Languages
EMNLP 2024
A Probability–Quality Trade-off in Aligned Language Models and its Relation to Sampling Adaptors
EMNLP 2024
Can Transformers Learn n-gram Language Models?
EMNLP 2024
Computational Expressivity of Neural Language Models
ACL 2024
Lower Bounds on the Expressivity of Recurrent Neural Language Models
NAACL 2024
On Affine Homotopy between Language Encoders
NeurIPS 2024
On Efficiently Representing Regular Languages as RNNs
ACL 2024
On the Representational Capacity of Neural Language Models with Chain-of-Thought Reasoning
ACL 2024
The Role of n-gram Smoothing in the Age of Neural Networks
NAACL 2024
Transformers Can Represent n-gram Language Models
NAACL 2024
What Languages are Easy to Language-Model? A Perspective from Learning Probabilistic Regular Languages
ACL 2024
On the Representational Capacity of Recurrent Neural Language Models
EMNLP 2023
Recurrent Neural Language Models as Probabilistic Finite-state Automata
EMNLP 2023
Algorithms for Acyclic Weighted Finite-State Automata with Failure Arcs
EMNLP 2022