1 citations · 2 across the 4 of their papers we have counts for
4 papers
Divergent-Convergent Reasoning: Scaling Test-Time Compute through Structured Solution Synthesis
Bo Wen, Yuhao Chen, Erhan Bilal +3
Test-time compute can substantially improve Large Language Model (LLM) reasoning performance, yet how and when additional compute helps remains poorly understood. We study Divergen…
How Modality Shapes Perception and Reasoning: A Study of Error Propagation in ARC-AGI
Bo Wen, Chen Wang, Erhan Bilal
ARC-AGI and ARC-AGI-2 measure generalization-through-composition on small color-quantized grids, and their prize competitions make progress on these harder held-out tasks a meaning…
Deep Gradient Boosting -- Layer-wise Input Normalization of Neural Networks
Erhan Bilal
Stochastic gradient descent (SGD) has been the dominant optimization method for training deep neural networks due to its many desirable properties. One of the more remarkable and l…
Unsupervised Ensemble Regression
Omer Dror, Boaz Nadler, Erhan Bilal +1
Consider a regression problem where there is no labeled data and the only observations are the predictions of experts over many samples . With no knowle…