565 citations · 1.4k across the 56 of their papers we have counts for
6 papers · 1 filter
Humanline: Online Alignment as Perceptual Loss
Sijia Liu, Niklas Muennighoff, Kawin Ethayarajh
Online alignment (e.g., GRPO) is generally more performant than offline alignment (e.g., DPO) -- but why? Drawing on prospect theory from behavioral economics, we propose a human-c…
ReasonIR: Training Retrievers for Reasoning Tasks
Rulin Shao, Rui Qiao, Varsha Kishore +8
We present ReasonIR-8B, the first retriever specifically trained for general reasoning tasks. Existing retrievers have shown limited gains on reasoning tasks, in part because exist…
Retro-Search: Exploring Untaken Paths for Deeper and Efficient Reasoning
Ximing Lu, Seungju Han, David Acuna +8
Large reasoning models exhibit remarkable reasoning capabilities via long, elaborate reasoning trajectories. Supervised fine-tuning on such reasoning traces, also known as distilla…
Bridging the Data Provenance Gap Across Text, Speech and Video
Shayne Longpre, Nikhil Singh, Manuel Cherep +40
Progress in AI is driven largely by the scale and quality of training data. Despite this, there is a deficit of empirical analysis examining the attributes of well-established data…
Diagnosing the Impact of AI on Radiology in China
Niklas Muennighoff
Artificial Intelligence will significantly impact the work environment of radiologists. I suggest that up to 50% of a radiologists work in 2021 will be performed by AI-models in 20…
Vilio: State-of-the-art Visio-Linguistic Models applied to Hateful Memes
Niklas Muennighoff
This work presents Vilio, an implementation of state-of-the-art visio-linguistic models and their application to the Hateful Memes Dataset. The implemented models have been fitted…