Efficient Homomorphic Integer Computer from CKKS
Speaker: Jaehyung Kim, Stanford University Host: Patrick Longa, Microsoft Research Redmond Fully homomorphic encryption (FHE) has evolved from Gentry’s original blueprint into a diverse family of
452
10.4
Fuzzy Extractors are Practical
Speaker: Amey Shukla, University of Connecticut Host: Melissa Chase Despite decades of effort, a chasm existed between the theory and practice of device-level biometric authentication.
337
10.9
Microsoft Research India 2025 Highlights
Here are some highlights of the research and impact at Microsoft Research India in 2025, along with some glimpses of the lab milieu.
2 458
14
Rick Rashid & Founding Microsoft Research
We were delighted to host a fabulous talk from the founder of Microsoft Research, Rick Rashid!
711
11.5
KDD '25 AI Reasoning Day keynote: Improving AI Reasoning through Intent, Interaction, and Inspection
AI models are increasingly capable of solving sophisticated tasks that require reasoning. But how do we improve the quality of that reasoning, especially when the models operate as black boxes?
437
7.7
Anaximander: Interactive Orchestration and Evaluation of Geospatial Foundation Models
Geospatial Foundation Models – deep learning architectures trained on large-scale Earth observation and remote sensing data – have proved useful for object detection, semantic segmentation, and
239
From Microfarms to the Moon: A Teen Innovator’s Journey in Robotics
A brilliant 13‑year‑old innovator, Pranav, showcases his award‑winning robotics projects from the World Robot Olympiad.
565
10.7
A brain-inspired agentic architecture to improve planning with LLMs
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Continue watching this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
1 614
18.9
Tool-space Interference: An emerging problem for LLM agents
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Watch all talks in this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
1 717
24.5
Data Formulator: Vibe with your data, in control
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Watch all talks in this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
757
31.2
Data Formulator: Vibe with your data, in control
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Watch all talks in this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
1 980
38.5
Watch now: The last episode of Microsoft Research Forum of 2025
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Watch all talks in this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
1 646
22.5
Inside Microsoft Research Asia: Fundamental research powering the future of AI
Fundamental research is the source of all innovation, and Microsoft Research Asia is dedicated to defining new computing paradigms and unlocking long-term breakthroughs.
548
8
Publicly verifiable elections
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Watch all talks in this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
1 292
15
A brain-inspired agentic architecture to improve planning with LLMs
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Watch all talks in this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
1 812
28.4
Data Formulator: Vibe with your data, in control
Data Formulator is an AI-powered tool for analysts to iteratively explore and visualize data.
652
7.4
Accelerating MRI image reconstruction with Tyger
The Tyger framework enables faster, more accessible medical imaging by streaming raw data to the cloud for accelerated reconstruction—reducing patient wait times and discomfort—while empowering
358
6.3
Tool-space Interference: An emerging problem for LLM agents
Tool-space interference occurs when adding an otherwise reasonable agent or tool to a team or agent reduces end-to-end task performance.
461
15
Publicly-verifiable elections
Microsoft’s free, open-source ElectionGuard tools enable voters to verify their votes were accurately counted without compromising privacy or trusting election equipment or personnel.
669
8.7
A brain-inspired agentic architecture to improve planning with LLMs
Inspired by human collective cognition and neuroscience, we conducted two studies showing that a) multi-LLM architectures with mixed communication connectivity lead to better collaborative
843
5.1
Watch now: The last episode of Microsoft Research Forum of 2025
Register for the series to learn about future episodes: aka.ms/registerresearchforumYTs2e2 Watch all talks in this episode: aka.ms/researchforumYTs2e2 Explore all previous episodes
1 824
37.6
Microsoft Research Forum | Season 2, Episode 2
Microsoft Research Forum is a virtual series highlighting purposeful research and its real-world impact, from fundamental exploration to advancing AI responsibly, scaling innovation through products
1 103
10.4
Leveraging Loanword Constraints for Improving Machine Translation in Low-resource Settings
Translating from high-resource to low-resource languages like Emakhuwa remains a challenge due to limited parallel data, orthographic variation, and frequent loanwords and code-switching.
222
Ideas: Community building, machine learning, and the future of AI
As the Women in Machine Learning Workshop (WiML) marks its 20th annual gathering, cofounders, friends, and collaborators Jenn Wortman Vaughan and Hanna Wallach reflect on WiML’s evolution
631
14.7
Coauthor roundtable: Reflecting on healthcare economics, biomedical research, and medical education
For the series finale, Peter Lee, Carey Goldberg, and Dr.
300
Promptions
Promptions (“Prompt” plus “options”) dynamically generates UI to help users steer AI responses more effectively.
892
12.5
Coming December 9th! Microsoft Research Forum | Season 2, Episode 2
aka.ms/researchforum
722
59.7
Spatial Audio Rendering for Speech Live Translation
Language barriers in virtual meetings remain a persistent challenge to global collaboration.
305
Designing safe digital systems for the humanitarian sector
Speaker: Carmela Troncoso Host: Betül Durak In this talk we overview our collaboration with the International Committee of the Red Cross, in which we help them to digitalize their aid
329
21.6
The Illusion of Inclusion How LLMs Misrepresent African Languages and Cultural Contexts
Multilingual LLMs have become so powerful, yet African languages remain misrepresented.
510
11





























