1 citations · 1 across the 1 of their papers we have counts for
3 papers · 1 filter
Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space
Houjun Liu, Shikhar Murty, Christopher D. Manning +1
Current approaches for scaling inference-time compute in transformers train them to emit explicit chain-of-thought tokens before producing an answer. While these methods are powerf…
Do Language Models Use Their Depth Efficiently?
Róbert Csordás, Christopher D. Manning, Christopher Potts
Modern LLMs are increasingly deep, and depth correlates with performance, albeit with diminishing returns. However, do these models use their depth efficiently? Do they compose mor…
Recurrent Neural Networks Learn to Store and Generate Sequences using Non-Linear Representations
Róbert Csordás, Christopher Potts, Christopher D. Manning +1
The Linear Representation Hypothesis (LRH) states that neural networks learn to encode concepts as directions in activation space, and a strong version of the LRH states that model…