Web Analytics Made Easy - Statcounter

Seminars

Inference and AI Infrastructure (Special Event for #BosTechWeek)

event location_on SEC 3.301, 3.302 & 3.303 person Venkat Pullela (Keysight) & Tushar Krishna (Georgia Tech)

The market focus has shifted from building LLMs and training to how to serve these models and efficient inference. In this meet up we are discussing the AI inference stack and how optimizing it is a multi dimensional problem, the role of hardware and software co-design and how applications are the only deliverable. We also deep dive into MLCommons Chakra, a framework for capturing AI application execution graphs.

Read more →

Firefly: Scalable, Ultra-Accurate Clock Synchronization for Datacenters

event location_on SEC 2.122 & 2.123 person Yuliang Li (Google)

Achieving the sub-10ns clock synchronization required by cloud-based financial exchanges is increasingly difficult because existing methods are often vulnerable to jitter, drift, and the complexities of large-scale network paths. Yuliang will showcase Firefly, a software-driven system that leverages a distributed consensus algorithm and a novel layered synchronization technique to provide resilient, high-precision time alignment across modern datacenters.

Read more →

High-Dimensional Gradient-Free Optimization for Neuroscience, Interpretability and LLMs: Why It Works and How to Make It Better

event location_on SEC 2.122 & 2.123 person Binxu Wang (Harvard University)

Evolution strategies (ES) provide a vital gradient-free alternative for solving complex, high-dimensional optimization problems in fields like neuroscience and LLM fine-tuning where traditional backpropagation is often unavailable or inefficient. Binxu Wang will explore the geometric properties that enable these methods to succeed and demonstrate how identifying task-irrelevant parameter directions can be leveraged to further accelerate optimization in modern large-scale models.

Read more →

Collapsing Towers of Interpreters for Security

event location_on SEC 2.122 & 2.123 person Cameron Wong (Harvard University)

Staged metaprogramming offers an alternative to traditional macros by using annotations to control execution timing, allowing programs to be specialized for known inputs by delaying specific computations. Cameron Wong will demonstrate how this technique can derive compilers from interpreters and reify low-level hardware behaviors to detect side-channel vulnerabilities, while also discussing future applications in address sanitization and decompilation.

Read more →

Practical End-to-End Privacy and Data Use Policy Enforcement

event location_on SEC 2.122 & 2.123 person Malte Schwarzkopf (Brown University)

While modern data is governed by strict privacy policies, developers often lack the practical abstractions needed to ensure their code complies, leading to frequent manual errors and costly violations. Malte Schwarzkopf will introduce Sesame, a framework that utilizes policy containers and static analysis to automate end-to-end privacy enforcement with minimal developer effort and low performance overhead.

Read more →

The Collapse of Constrained Physical AI

event location_on SEC 2.122 & 2.123 person Jason Jabbour (Harvard University)

As AI transitions from digital screens to autonomous physical systems like flight and construction, moving large-scale intelligence from the cloud to the edge presents significant technical and safety hurdles. Jason Jabbour will show these deployment constraints and share recent collaborative research that restores safety and task success within compressed Vision-Language-Action (VLA) models.

Read more →

Open Source Software (OSS) Inference Stack

event location_on SEC 2.122 & 2.123 person Robert Shaw (Red Hat)

Open source inference systems have become critically important as models get bigger and bigger and agentic applications create demanding workloads. In this talk, we will discuss the key trends in model architecture and hardware accelerator server design and how open-source inference systems like vLLM and llm-d optimize performance against these trends.

Read more →

Enhancing Performance Guarantees in Large-Scale Systems

event location_on SEC 2.122 & 2.123 person Yigong Hu (Boston University)

Performance stability is fundamentally challenging because application-defined resources remain invisible to the operating system, leading to unpredictable degradation that escapes traditional system-level monitoring. Yigong Hu will present his research on making application-defined resources first-class entities for performance reasoning and control.

Read more →

Learning-Directed Operating Systems

event location_on SEC 2.122 & 2.123 person Aditya Akella (the University of Texas at Austin)

Modern applications often face performance bottlenecks due to rigid OS policies, even when resources are plentiful. Aditya Akella will present LDOS (Learning-Directed Operating System), which replaces manual policy design with data-driven, system-wide optimization.

Read more →

Resilient Composition for Fault-Tolerant Cloud Applications

event location_on SEC 2.122 & 2.123 person Tianyu Li (the University of Wisconsin-Madison)

As cloud programming grows complex, new abstractions are vital for building correct, simple and efficient applications. Tianyu Li will introduce Resilient Composition, a method that ensures fault tolerance for applications built from distributed components.

Read more →