Internship: Advanced Constraint Processing in LLMs F/M
-
Contract type: Internship
-
Work time: Full time
-
Location Meylan
About NAVER LABS Europe
NAVER LABS Europe is part of the R&D division of NAVER, Korea’s leading Internet portal and a global tech company with a range of services that include search, commerce, content, fintech, robotics and cloud.
The position
What we're looking for (depending on your career stage)
- Computer Science / Deep Learning PhD student or an outstanding Master student
- Proficiency with Large Language Models (LLMs) is required, including their training and fine-tuning.
- Being comfortable with the mathematical foundations of these models is a plus.
- Familiarity with PyTorch and alignment techniques (e.g., RLHF) is essential.
- You should feel at ease conducting experiments autonomously.
What we offer
-
Ambitious, multidisciplinary projects with experienced international research teams (30 years research in AI and related fields).
-
Flexible work/life balance.
-
An equal opportunity employer committed to diversity and inclusion.
-
A great location that blends urban life, technology and nature with stunning views of the Alpine mountain ranges (Belledonne, Chartreuse, Vercors).
NAVER LABS, co-located in Korea and France, is the organization dedicated to preparing NAVER’s future. Scientists at NAVER LABS Europe are empowered to pursue long-term research problems that, if successful, can have significant impact and transform NAVER. We take our ideas as far as research can to create the best technology of its kind. Active participation in the academic community and collaborations with world-class public research groups are, among others, important ways to achieve these goals. Teamwork, focus and persistence are important values for us.
When applying for this position online, please don't forget to upload your CV and cover letter. Incomplete applications will not be considered.
NAVER LABS Europe is subject to French jurisdiction requiring organisations to stipulate that a job/internship is open to both women and men. None of our jobs/internships are gender specific.
References
[1] Khalifa et al. A Distributional Approach to Controlled Text Generation. ICLR, 2021
[2] Eikema et al. An Approximate Sampler for Energy-Based Models with Divergence Diagnostics. TMLR, 2022
[3] Korbak et al. Controlling Conditional Language Models without Catastrophic Forgetting. ICML, 2022
[4] Korbak et al. On Reinforcement Learning and Distribution Matching for Fine-Tuning Language Models with No Catastrophic Forgetting. NeurIPS, 2022
[5] Go et al. Aligning Language Models with Preferences through f-Divergence Minimization. ICML, 2023
[6] Kim et al. Guaranteed Generation from Large Language Models. arXiv, 2024
[7] Kruszewski et al. disco: A Toolkit for Distributional Control of Generative Models. ACL, 2023
Réf: 15418c16-2d62-4105-869b-4c69a9242f1a
This position has been filled.