1.2k citations
- Microsoft (United States)US41 papers
- Microsoft Research (United Kingdom)GB14 papers
- Carnegie Mellon UniversityUS12 papers
- Indian Institute of Science BangaloreIN12 papers
- Institut national de recherche en sciences et technologies du numériqueFR12 papers
- Indian Institute of Technology DelhiIN10 papers
- Indian Institute of Technology KharagpurIN10 papers
- Microsoft (India)IN10 papers
- University of WashingtonUS9 papers
- Indian Institute of Technology KanpurIN8 papers
- Stanford UniversityUS8 papers
- The University of Texas at AustinUS8 papers
188 papers
Extreme Meta-Classification for Large-Scale Zero-Shot Retrieval
Sachin Yadav, Deepak Saini, Anirudh Buvanesh +6
We develop accurate and efficient solutions for large-scale retrieval tasks where novel (zero-shot) items can arrive continuously at a rapid pace. Conventional Siamese-style approa…
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…
Emergence of Transport Regimes from the Axial Field-Induced Interfacial Gradients in Uniform Surface Potential Nanopores
Pramodt Srinivasula, Doyel Pandey
Gate-modulated nanopores have emerged as a promising platform for achieving ion selectivity and ionic current rectification (ICR) with the advantage of active field-based control.…
SKYLINK: Scalable and Resilient Link Management in LEO Satellite Network
Wanja de Sombre, Arash Asadi, Debopam Bhattacherjee +2
The rapid growth of space-based services has established LEO satellite networks as a promising option for global broadband connectivity. Next-generation LEO networks leverage inter…
Interpretable Model Drift Detection
Pranoy Panda, Kancheti Sai Srinivas, Vineeth N Balasubramanian +1
Data in the real world often has an evolving distribution. Thus, machine learning models trained on such data get outdated over time. This phenomenon is called model drift. Knowled…
SageServe: Optimizing LLM Serving on Cloud Data Centers with Forecast Aware Auto-Scaling
Shashwat Jaiswal, Kunal Jain, Yogesh Simmhan +9
Global cloud service providers handle inference workloads for Large Language Models (LLMs) that span latency-sensitive (e.g., chatbots) and insensitive (e.g., report writing) tasks…