3 papers
cs.LG2025
The Markovian Thinker: Architecture-Agnostic Linear Scaling of Reasoning
Milad Aghajohari, Kamran Chitsaz, Amirhossein Kazemnejad +4
Reinforcement learning (RL) has recently become a strong recipe for training reasoning LLMs that produce long chains of thought (LongCoT). Yet the standard RL "thinking environment…
cs.LG2025
NovoMolGen: Rethinking Molecular Language Model Pretraining
Kamran Chitsaz, Roshan Balaji, Quentin Fournier +2
Designing de-novo molecules with desired property profiles requires efficient exploration of the vast chemical space ranging from to possible synthesizable cand…
cs.LG2024
Exploring Quantization for Efficient Pre-Training of Transformer Language Models
Kamran Chitsaz, Quentin Fournier, Gonçalo Mordido +1
The increasing scale of Transformer models has led to an increase in their pre-training computational requirements. While quantization has proven to be effective after pre-training…