Microsoft#

38 picked talks across 21 digests with a speaker from Microsoft, newest first.

@Scale: Product 2026#

ML Video Codec (MLVC): Research to Product · Adjacent — Nabakumar Khongbantabam (Microsoft)

Self-Healing PyTorch Training Through Live GPU Migration · Core — Pavneet Ahluwalia, Gavin Cohen — Microsoft Azure (product) and Clockwork Systems

Live Panel: Building at the Roofline — Planning and Delivering Gigawatt-Scale AI Infrastructure · Wildcard — Omar Baldonado (Meta), Amrita Kenue (Meta), Lucas Benson (Microsoft), Nikita Parikh (Google)

SRv6 for Deterministic Path Placement in AI Backends · Core — Ahmed Abdelsalam (Cisco), on behalf of co-authors from Cisco, Microsoft, Oracle Cloud, IBM Cloud, NVIDIA and Arrcus.

Securing Production Debugging at Hyperscale · Adjacent — Shridivya Sharma (Microsoft), Luke Kelly (Microsoft)

Paraglider: Streamlining Cloud Networking · Adjacent — Sarah McClure – UC Berkeley (LF Networking project with Google, Microsoft, IBM)
From Metrics to Investigation: How Agentic SRE Could Change Network Operations · Adjacent — Mohibul Mahmud, Shamir Abdul Aziz, Karthik Srinivas Muthuramakrishnan – Microsoft

TokenWeave: Efficient Compute-Communication Overlap for Distributed LLM Inference · Adjacent — Raja Gond, Nipun Kwatra, Ramachandran Ramjee (Microsoft, per the paper's open-source repository)

Offloading Cloud Network Services at Production Scale with SONiC DASH SmartSwitch · Core — Shaofeng Wu (CUHK and Microsoft Research Asia), Zhixiong Niu (MSRA), Riff Jiang, et al. (Microsoft), Hong Xu (CUHK) — Community Award Winner
KRAKENGUARD: Towards Fine-Grained eBPF Isolation · Core — Jainil Patel (IIT Roorkee), Lucas Graeff Buhl-Nielsen (Quantco), Adrien Ghosn (Microsoft), Marios Kogias (Imperial College London)
Eywa: Automating Model-Based Testing using LLMs · Wildcard — Rajdeep Mondal, Rathin Singha, Todd Millstein, George Varghese (UCLA), Ryan Beckett, Siva Kesava Reddy Kakarla (Microsoft Research)

From Static Tokens to Attestation: The Evolution of Secure Node Joining · Core — Ciprian Hacman & Jack Francis, Microsoft; Michael McCune & Josephine Pfeiffer, Red Hat; Justin Santa Barbara, Google

Supercharging AI With Multi-Gigawatt AI Factories · Core — Gilad Shainer, Peter Salanki (CoreWeave), Omar Baldonado (Meta), Yuya Kawakami (SoftBank), Alexis Bjorlin (NVIDIA), Evan Burness (Microsoft) — Panel, Wednesday, March 18

Strengthening Kubernetes Trust: SIG Auth's Latest Security Enhancements · Core — Anish Ramasekar, Mo Khan, Stanislav Láznička, Rita Zhang & Peter Engelbert, Microsoft — Core
Gateway API: Table Stakes · Adjacent — Shane Utt & Candace Holman, Red Hat; Mike Morris, Microsoft; Lior Lieberman & Kellen Swain, Google — Adjacent
Istio Project Updates: AI Inference, Ambient Multicluster & Default Deny · Adjacent — Keith Mattix, Microsoft — Adjacent

SRv6 for AI Backend · Core — Speakers: Changrong Wu (Microsoft), Abhishek Dosi (Microsoft)
Enabling Technologies for Next Generation Large Scale AI Backend Networking · Core — Speakers: Guohan Lu (Microsoft), Mehak Mahajan (Broadcom)
Disaggregated Leaf-Spine Architecture for Next-gen Azure T2 Network · Core — Speakers: Kamini Santhanagopalan (Broadcom), Rita Hui (Microsoft)
Cryptography in Caliptra · Wildcard — Speakers: Christopher Swenson (Microsoft), Jeff Andersen (Google)

Mosaic: Breaking the Optics versus Copper Trade-off with a Wide-and-Slow Architecture and MicroLEDs · Core — Kaoutar Benyahya et al. (Microsoft Research / Microsoft Azure)
Falcon: A Reliable, Low Latency Hardware Transport · Core — Arjun Singhvi, Nandita Dukkipati et al. (Google, with Meta/Nvidia/Microsoft)
Software-based Live Migration for RDMA (MigrRDMA) · Core — Xiaoyu Li et al. (Tsinghua / Microsoft Research)

Optimizing AI-Ready WAN Infrastructure with Microsoft and Cisco - CSSENT-2100 · Core — Sarav Subramanian (Microsoft), Ruben Lopes da Fonte (Cisco), Gaisin Rustam (Microsoft)

AIOpsLab: A Holistic Framework to Evaluate AI Agents for Enabling Autonomous Clouds · Adjacent — Yinfang Chen, Manish Shetty, Gagan Somashekar, Minghua Ma, Yogesh Simmhan, Jonathan Mace, Chetan Bansal, Rujia Wang, S R (Microsoft Research / academic collaboration)

Everything Matters in Programmable Packet Scheduling (PACKS) · Core — Albert Gran Alcoz (ETH Zürich); Balázs Vass (BME-TMIT); Pooria Namyar (USC); Behnaz Arzani (Microsoft Research); Gábor Rétvári (BME-TMIT); Laurent Vanbever (ETH Zürich). Core.
Securing Public Cloud Networks with Efficient Role-based Micro-Segmentation (ZTS) · Core — Sathiya Kumaran Mani, Kevin Hsieh (Microsoft); Santiago Segarra (Rice); Ranveer Chandra (Microsoft); Yajie Zhou (University of Maryland); Srikanth Kandula (Microsoft). Core.
Efficient Multi-WAN Transport for 5G with OTTER · Adjacent — Mary Hogan (Oberlin College); Gerry Wan (Google); Yiming Qiu (University of Michigan); Sharad Agarwal, Ryan Beckett (Microsoft); Rachee Singh (Cornell); Paramvir Bahl (Microsoft). Adjacent.
Towards Energy Efficient 5G vRAN Servers (RENC) · Wildcard — Anuj Kalia (Microsoft); Nikita Lazarev (MIT); Leyang Xue (University of Edinburgh); Xenofon Foukas, Bozidar Radunovic (Microsoft); Francis Y. Yan (Microsoft Research and UIUC). Wildcard.

SONiC: The Global Networking Operating System for All · Core — Michael Ma, Microsoft; Peter Plak, Dell