6 papers
End-to-End Context Compression at Scale
Ang Li, Sean McLeish, Haozhe Chen +12
Long-context language model inference is bottlenecked by memory, as the KV cache grows with context length. Recent techniques to compress the KV cache fall short: they either degra…
Do Language Models Need Sleep? Offline Recurrence for Improved Online Inference
Sangyun Lee, Sean McLeish, Tom Goldstein +1
Transformer-based large language models are increasingly used for long-horizon tasks; however, their attention mechanism scales poorly with context length. To handle this, we study…
Teaching Pretrained Language Models to Think Deeper with Retrofitted Recurrence
Sean McLeish, Ang Li, John Kirchenbauer +7
Recent advances in depth-recurrent language models show that recurrence can decouple train-time compute and parameter count from test-time compute. In this work, we study how to co…
Gemstones: A Model Suite for Multi-Faceted Scaling Laws
Sean McLeish, John Kirchenbauer, David Yu Miller +5
Scaling laws are typically fit using a family of models with a narrow range of frozen hyperparameter choices. In this work we study scaling laws using multiple architectural shapes…
Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
Jonas Geiping, Sean McLeish, Neel Jain +6
We study a novel language model architecture that is capable of scaling test-time computation by implicitly reasoning in latent space. Our model works by iterating a recurrent bloc…
Transformers Can Do Arithmetic with the Right Embeddings
Sean McLeish, Arpit Bansal, Alex Stein +8
The poor performance of transformers on arithmetic tasks seems to stem in large part from their inability to keep track of the exact position of each digit inside of a large span o…