Germán Kruszewski
16 papers · 2014–2025 · 7 conferences · across top CS/AI conferences
Achievements
Jump to papers ↓+5 more ↓ Show less ↑
🗺️ Taxonomy Completionist (35) 🌉 Interdisciplinary Bridge 🧭 Keyword Pioneer 🐣 Hot Topic Early Bird 🐝 Cross-Pollinator (14)
🌈
Renaissance Researcher
(6)
🌍
Conference Polyglot
(7)
🏃
Academic Marathon
(11)
💎
Century Club
(16)
❓
The Questioner
Conferences
ACL (6)
NAACL (3)
EMNLP (2)
ICML (2)
ICLR (1)
IJCNLP (1)
NIPS (1)
Top co-authors
Keywords
language model
(4)
policy gradient
(2)
generative model
(2)
reinforcement learning
(2)
representation learning
(2)
distribution matching
(2)
preference alignment
(2)
large language model
(2)
reinforcement learning from human feedback
(1)
language model alignment
(1)
self-supervised learning
(1)
semantic representation
(1)
conditional generation
(1)
parameter efficient
(1)
kl divergence
(1)
sentiment analysis
(1)
marginal probability
(1)
reward maximization
(1)
distribution learning
(1)
importance sampling
(1)
Papers
FaST: Feature-aware Sampling and Tuning for Personalized Preference Alignment with Limited Data
EMNLP 2025
Compositional Preference Models for Aligning LMs
ICLR 2024
Should you marginalize over possible tokenizations?
ACL 2023
Aligning Language Models with Preferences through $f$-divergence Minimization
ICML 2023
disco: a toolkit for Distributional Control of Generative Models
ACL 2023
On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with no Catastrophic Forgetting
NIPS 2022
Controlling Conditional Language Models without Catastrophic Forgetting
ICML 2022
Cooperative Learning of Disjoint Syntax and Semantics
NAACL 2019
The emergence of number and syntax units in LSTM language models
NAACL 2019
What you can cram into a single $&!#* vector: Probing sentence embeddings for linguistic properties
ACL 2018
Convolutional Neural Network Language Models
EMNLP 2016
The LAMBADA dataset: Word prediction requiring a broad discourse context
ACL 2016
Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model
IJCNLP 2015
So similar and yet incompatible: Toward the automated identification of semantically compatible words
NAACL 2015
Jointly optimizing word representations for lexical and sentential tasks with the C-PHRASE model
ACL 2015
Don’t count, predict! A systematic comparison of context-counting vs. context-predicting semantic vectors
ACL 2014