activity
20192026
most citedHow Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse

3 citations · 4 across the 11 of their papers we have counts for

collaborators

11 papers

cs.AI2026

Falcon-H1R: Pushing the Reasoning Frontiers with a Hybrid Model for Efficient Test-Time Scaling

Falcon LLM Team, Iheb Chaabane, Puneesh Khanna +8

This work introduces Falcon-H1R, a 7B-parameter reasoning-optimized model that establishes the feasibility of achieving competitive reasoning performance with small language models…

cs.LG2024

Alignment with Preference Optimization Is All You Need for LLM Safety

Reda Alami, Ali Khalifa Almansoori, Ahmed Alzubaidi +3

We demonstrate that preference optimization methods can effectively enhance LLM safety. Applying various alignment techniques to the Falcon 11B model using safety datasets, we achi…

cs.LG20243 cited

How Bad is Training on Synthetic Data? A Statistical Analysis of Language Model Collapse

Mohamed El Amine Seddik, Suei-Wen Chen, Soufiane Hayou +2

The phenomenon of model collapse, introduced in (Shumailov et al., 2023), refers to the deterioration in performance that occurs when new models are trained on synthetic data gener…

cs.LG2024

Investigating Regularization of Self-Play Language Models

Reda Alami, Abdalgader Abubaker, Mastane Achab +2

This paper explores the effects of various forms of regularization in the context of language model alignment via self-play. While both reinforcement learning from human feedback (…

stat.ML2024

Performance Gaps in Multi-view Clustering under the Nested Matrix-Tensor Model

Hugo Lebeau, Mohamed El Amine Seddik, José Henrique de Morais Goulart

We study the estimation of a planted signal hidden in a recently introduced nested matrix-tensor model, which is an extension of the classical spiked rank-one tensor model, motivat…

cs.CV2024

Do Vision and Language Encoders Represent the World Similarly?

Mayug Maniparambil, Raiymbek Akshulakov, Yasser Abdelaziz Dahou Djilali +4

Aligned text-image encoders such as CLIP have become the de facto model for vision-language tasks. Furthermore, modality-specific encoders achieve impressive performances in their…