732 citations
- Microsoft (United States)US79 papers
- Carnegie Mellon UniversityUS37 papers
- University of WashingtonUS37 papers
- Massachusetts Institute of TechnologyUS34 papers
- University of Science and Technology of ChinaCN30 papers
- University of CambridgeGB29 papers
- Peking UniversityCN28 papers
- Stanford UniversityUS26 papers
- Tsinghua UniversityCN23 papers
- University College LondonGB23 papers
- University of California, BerkeleyUS21 papers
- Georgia Institute of TechnologyUS16 papers
24 papers · 1 filter
Reasoning Up the Instruction Ladder for Controllable Language Models
Zishuo Zheng, Vidhisha Balachandran, Chan Young Park +2
As large language model (LLM) based systems take on high-stakes roles in real-world decision-making, they must reconcile competing instructions from multiple sources within a singl…
Reality Distortion Room: A Study of User Locomotion Responses to Spatial Augmented Reality Effects
You-Jin Kim, Andrew D. Wilson, Jennifer Jacobs +1
Reality Distortion Room (RDR) is a proof-of-concept augmented reality system using projection mapping and unencumbered interaction with the Microsoft RoomAlive system to study a us…
Fair Decisions through Plurality: Results from a Crowdfunding Platform
Joel Miller, E. Glen Weyl, Chris Kanich
We discuss an algorithmic intervention aimed at increasing equity and economic efficiency at a crowdfunding platform that gives cash subsidies to grantees. Through a blend of techn…
A Universal Banach--Bregman Framework for Stochastic Iterations: Unifying Stochastic Mirror Descent, Learning and LLM Training
Johnny R. Zhang, Xiaomei Mi, Gaoyuan Du +4
Stochastic optimization powers the scalability of modern artificial intelligence, spanning machine learning, deep learning, reinforcement learning, and large language model trainin…
From Task to Tutorial: An Automated GUI Framework for Excel Tutorial Document and Video Creation
Yuhang Xie, Jian Mu, Xiaojun Ma +9
Excel is one of the most widely used productivity tools across domains, offering rich functionality but also overwhelming users with its complexity. This creates a persistent deman…
DynamixSFT: Dynamic Mixture Optimization of Instruction Tuning Collections
Haebin Shin, Lei Ji, Xiao Liu +4
As numerous instruction-tuning datasets continue to emerge, dynamically balancing and optimizing their mixtures has become a critical challenge. To address this, we propose Dynamix…