626 citations · 1.7k across the 87 of their papers we have counts for
10 papers · 1 filter
World of SWECraft: Agent Collaboration at Scale via Simulated Software Worlds
Shannon Zejiang Shen, Yapei Chang, Qiyao Liang +13
As teams of AI agents take on larger projects and long-standing open problems, agent collaboration offers another dimension for scaling inference-time compute. To understand what m…
IdeaLens: Detecting AI Ideas in Long-form Writing
Rishanth Rajendhran, Minjoon Choi, Jenna Russell +5
While modern AI detectors identify who wrote the words, emerging policies on AI use increasingly hinge on a different question: who came up with the ideas? We introduce IdeaLens, a…
How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text
Jenna Russell, Ben Glickenhaus, Katherine Thai +4
Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying FineWeb quality filtering, we find that 27.5% of tokens from June 2026 web data…
Recovering Diversity Without Losing Alignment: A DPO Recipe for Post-Trained LLMs
Vinay Samuel, Yapei Chang, Mohit Iyyer
Many open-ended instructions have multiple valid answers that users can benefit from seeing, but post-training often narrows an LLM's output space toward a small set of canonical r…
POLARIS: Guiding Small Models to Write Long Stories
Rishanth Rajendhran, Jenna Russell, Mohit Iyyer +1
Small open-weight models struggle at long-form creative writing: their generated stories either fall far short of the requested length, or their quality significantly degrades as l…
Argument Collapse: LLMs Flatten Long-Form Public Debate
Yekyung Kim, Yapei Chang, Chau Minh Pham +1
As LLMs are increasingly used to draft publicfacing arguments, they may flatten public debate by repeatedly introducing the same polished, plausible arguments. We study argument co…
Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
Nazanin Jafari, James Allan, Mohit Iyyer
Evaluating the factuality of long-form output generated by large language models (LLMs) remains challenging, particularly when responses are open-ended and contain many fine-graine…
StoryScope: Investigating idiosyncrasies in AI fiction
Jenna Russell, Rishanth Rajendhran, Chau Minh Pham +2
As AI-generated fiction becomes increasingly prevalent, questions of authorship and originality are becoming central to how written work is evaluated. While most existing work in t…
Bio-Inspired Self-Supervised Learning for Wrist-worn Accelerometer Data
Prithviraj Tarale, Kiet Chu, Abhishek Varghese +4
Wearable accelerometers enable large-scale health monitoring, yet learning robust human-activity representations has been constrained by scarce labeled data. While self-supervised…
How2Everything: Mining the Web for How-To Procedures to Evaluate and Improve LLMs
Yapei Chang, Kyle Lo, Mohit Iyyer +1
Generating step-by-step "how-to" procedures is a key LLM capability: how-to advice is commonly requested in chatbots, and step-by-step planning is critical for reasoning over compl…