5 papers
Revisiting Replay and Gradient Alignment for Continual Pre-Training of Large Language Models
Istabrak Abbes, Gopeshh Subbaraj, Matthew Riemer +6
Training large language models (LLMs) typically involves pre-training on massive corpora, only to restart the process entirely when new data becomes available. A more efficient and…
Using Scaling Laws for Data Source Utility Estimation in Domain-Specific Pre-Training
Oleksiy Ostapenko, Charles Guille-Escuret, Luke Kumar +7
We introduce a framework for optimizing domain-specific dataset construction in foundation model training. Specifically, we seek a cost-efficient way to estimate the quality of dat…
Pretraining Generative Flow Networks with Inexpensive Rewards for Molecular Graph Generation
Mohit Pandey, Gopeshh Subbaraj, Artem Cherkasov +2
Generative Flow Networks (GFlowNets) have recently emerged as a suitable framework for generating diverse and high-quality molecular structures by learning from rewards treated as…
Seq-VCR: Preventing Collapse in Intermediate Transformer Representations for Enhanced Reasoning
Md Rifat Arefin, Gopeshh Subbaraj, Nicolas Gontier +4
Decoder-only Transformers often struggle with complex reasoning tasks, particularly arithmetic reasoning requiring multiple sequential operations. In this work, we identify represe…
Enabling Realtime Reinforcement Learning at Scale with Staggered Asynchronous Inference
Matthew Riemer, Gopeshh Subbaraj, Glen Berseth +1
Realtime environments change even as agents perform action inference and learning, thus requiring high interaction frequencies to effectively minimize regret. However, recent advan…