Advancing Memory and Context in Large Language Models
at
NAVER LABS Europe
Description
Position Overview:
We are seeking a highly motivated intern to support our research on Large Language Models (LLMs) and Information Retrieval, with a focus on Retrieval-Augmented Generation (RAG). Our team is dedicated to exploring the synergy between search, LLMs, and intelligent agents.
Key Qualities in a Candidate:
We value curiosity and a passion for gaining deep insights, especially in model testing and experimentation. The ideal candidate will demonstrate a strong analytical mindset and a drive to experiment with cutting-edge AI technologies.
Your Role:
The intern will join our Retrieval and Memory team, which has conducted pioneering work on sparse retrievers such as SPLADE [6,7], and research on fairness and reinforcement learning in recommendation systems. Recent publications from our team include:
Required skills
- MSc or PhD student with a focus in deep learning, natural language processing, or information retrieval.
- Proficiency in PyTorch.
References
[1] RAGGED: Towards Informed Design of Retrieval Augmented Generation Systems (https://arxiv.org/abs/2403.09040)
[2] Learning to Filter Context for Retrieval-Augmented Generation (https://arxiv.org/abs/2311.08377)
[3] Chain-of-Note: Enhancing Robustness in Retrieval-Augmented Language Models (https://arxiv.org/abs/2311.09210)
[4] Active Retrieval Augmented Generation (https://arxiv.org/abs/2305.06983)
[5] Self-RAG: Learning to Retrieve, Generate, and Critique through Self-Reflection (https://arxiv.org/abs/2310.11511)
[6] SPLADE: Sparse Lexical and Expansion Model for First Stage Ranking (https://arxiv.org/abs/2107.05720)
[7] https://github.com/naver/splade
[8] Zero-shot cross-lingual transfer in instruction tuning of large language models (https://arxiv.org/abs/2402.14778)
[9] Key ingredients for effective zero-shot cross-lingual knowledge transfer in generative tasks (https://arxiv.org/abs/2402.12279)
Application instructions
Applicants must be currently enrolled as students at a university or academic institution. An "Internship Agreement" signed by both the student’s institution and NAVER LABS Europe will be required for final acceptance.
About NAVER LABS
NAVER is Korea’s leading internet portal, with extensive business interests spanning search, commerce, content, finance, and cloud platforms. NAVER LABS, with locations in Korea and France, is dedicated to advancing NAVER’s future through innovative research. NAVER LABS Europe is based in Grenoble, France, in the heart of the French Alps, offering a vibrant setting for research.
At NAVER LABS Europe, researchers are encouraged to tackle long-term challenges with transformative potential. We strive to push research boundaries to develop breakthrough technologies. Teamwork, focus, and perseverance are core values for us, and we actively engage with the academic community, fostering collaborations with leading public research organizations.
NAVER LABS Europe is an equal-opportunity employer.
To make robots autonomous in real-world everyday spaces, they should be able to learn from their interactions within these spaces, how to best execute tasks specified by non-expert users in a safe and reliable way. To do so requires sequential decision-making skills that combine machine learning, adaptive planning and control in uncertain environments as well as solving hard combinatorial optimisation problems. Our research combines expertise in reinforcement learning, computer vision, robotic control, sim2real transfer, large multimodal foundation models and neural combinatorial optimisation to build AI-based architectures and algorithms to improve robot autonomy and robustness when completing everyday complex tasks in constantly changing environments.
VISION
The research we conduct on expressive visual representations is applicable to visual search, object detection, image classification and the automatic extraction of 3D human poses and shapes that can be used for human behavior understanding and prediction, human-robot interaction or even avatar animation. We also extract 3D information from images that can be used for intelligent robot navigation, augmented reality and the 3D reconstruction of objects, buildings or even entire cities.
Our work covers the spectrum from unsupervised to supervised approaches, and from very deep architectures to very compact ones. We’re excited about the promise of big data to bring big performance gains to our algorithms but also passionate about the challenge of working in data-scarce and low-power scenarios.
Furthermore, we believe that a modern computer vision system needs to be able to continuously adapt itself to its environment and to improve itself via lifelong learning. Our driving goal is to use our research to deliver embodied intelligence to our users in robotics, autonomous driving, via phone cameras and any other visual means to reach people wherever they may be.
This web site uses cookies for the site search, to display videos and for aggregate site analytics.
Learn more about these cookies in our privacy notice.
Cookie settings
You may choose which kind of cookies you allow when visiting this website. Click on "Save cookie settings" to apply your choice.
This content is currently blocked. To view the content please either 'Accept social media cookies' or 'Accept all cookies'.
For more information on cookies see our privacy notice.