1 citations
- Microsoft (United States)US3 papers
- Carnegie Mellon UniversityUS2 papers
- Allen InstituteUS1 paper
- Allergan (India)IN1 paper
- Central South UniversityCN1 paper
- Chinese Academy of SciencesCN1 paper
- Drexel UniversityUS1 paper
- Institute of SoftwareCN1 paper
- Microsoft Research (India)IN1 paper
- Microsoft Research New York City (United States)1 paper
- Princeton UniversityUS1 paper
- Shanghai Jiao Tong UniversityCN1 paper
9 papers
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…
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…
Mandol: An Agglomerative Agent Memory System for Long-Term Conversations
Yuhan Zhang, Zhiyuan Guo, Ziheng Zeng +3
Long-term conversational agents need to remember and query cross-session, multi-typed information with complex correlations. Existing agent memory systems rely on heterogeneous vec…
Orchestration for Domain-specific Edge-Cloud Language Models
Prasoon Patidar, Alex Crown, Kevin Hsieh +4
The remarkable performance of Large Language Models (LLMs) has inspired many applications, which often necessitate edge-cloud collaboration due to connectivity, privacy, and cost c…
Spectral bandits for smooth graph functions with applications in recommender systems
Tomáš Kocák, Michal Valko, Rémi Munos +2
Smooth functions on graphs have wide applications in manifold and semi-supervised learning. In this paper, we study a bandit problem where the payoffs of arms are smooth on a graph…
Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics
Nari Johnson, Deepthi Sudharsan, Hamna +7
Measurement is essential to improving AI performance and mitigating harms for marginalized groups. As generative AI systems are rapidly deployed across geographies and contexts, AI…