6 papers
Pretraining Language Models on Historical Text
Xiaoxi Luo, Zachary Shinnick, Niclas Griesshaber +5
We introduce TypewriterLM, a 7.24B History language model (LM) trained exclusively on English text predating 1913. Developing History LMs requires addressing challenges in data qua…
AdaPonderLM: Gated Pondering Language Models with Token-Wise Adaptive Depth
Shixiang Song, He Li, Zitong Wang +6
Test-time scaling via recurrent/iterative Transformers enables large language models to spend more computation at inference, but most pretrained recurrent LMs run a fixed number of…
PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space
Boyi Zeng, He Li, Shixiang Song +5
The remarkable success of Chain-of-Thought (CoT), which enhances performance by scaling generation steps at test-time, inspires us to ask: can we leverage a similar scaling of comp…
PonderLM: Pretraining Language Models to Ponder in Continuous Space
Boyi Zeng, Shixiang Song, Siyuan Huang +6
Humans ponder before articulating complex sentence elements, enabling deeper cognitive processing through focused effort. In this work, we introduce this pondering process into lan…
Next Concept Prediction in Discrete Latent Space Leads to Stronger Language Models
Yuliang Liu, Yunchong Song, Yixuan Wang +6
We propose Next Concept Prediction (NCP), a generative pretraining paradigm built on top of Next Token Prediction (NTP). NCP predicts discrete concepts that span multiple tokens, t…
FreqKV: Key-Value Compression in Frequency Domain for Context Window Extension
Jushi Kai, Yixuan Wang, Boyi Zeng +4
Existing key-value (KV) cache compression methods for large language models (LLMs) often rely on token eviction, which risks losing critical local information in both long prefilli…