Search Results for author: Neil Band

Found 8 papers, 7 papers with code

Reasoning to Learn from Latent Thoughts

1 code implementation24 Mar 2025 Yangjun Ruan, Neil Band, Chris J. Maddison, Tatsunori Hashimoto

We show that a 1B LM can bootstrap its performance across at least three iterations and significantly outperform baselines trained on raw data, with increasing gains from additional inference compute when performing the E-step.

Math Text Generation

Synthetic continued pretraining

1 code implementation11 Sep 2024 Zitong Yang, Neil Band, Shuangping Li, Emmanuel Candès, Tatsunori Hashimoto

We propose to bridge this gap with synthetic continued pretraining: using the small domain-specific corpus to synthesize a large corpus more amenable to learning, and then performing continued pretraining on the synthesized corpus.

Data Augmentation Language Modelling +2

Linguistic Calibration of Long-Form Generations

1 code implementation30 Mar 2024 Neil Band, Xuechen Li, Tengyu Ma, Tatsunori Hashimoto

Our results demonstrate that long-form generations may be calibrated end-to-end by constructing an objective in the space of the predictions that users make in downstream decision-making.

Decision Making Form +1

Shifts: A Dataset of Real Distributional Shift Across Multiple Large-Scale Tasks

3 code implementations15 Jul 2021 Andrey Malinin, Neil Band, Ganshin, Alexander, German Chesnokov, Yarin Gal, Mark J. F. Gales, Alexey Noskov, Andrey Ploskonosov, Liudmila Prokhorenkova, Ivan Provilkov, Vatsal Raina, Vyas Raina, Roginskiy, Denis, Mariya Shmatova, Panos Tigas, Boris Yangel

However, many tasks of practical interest have different modalities, such as tabular data, audio, text, or sensor data, which offer significant challenges involving regression and discrete or continuous structured prediction.

image-classification Image Classification +6

Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning

3 code implementations NeurIPS 2021 Jannik Kossen, Neil Band, Clare Lyle, Aidan N. Gomez, Tom Rainforth, Yarin Gal

We challenge a common assumption underlying most supervised deep learning: that a model makes a prediction depending only on its parameters and the features of a single input.

3D Part Segmentation Deep Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.