arXiv subjects

Mike Wong

Publications and source records attributed to Mike Wong.

5 recordsLinked to original sources

arXiv2026

Skim: Speculative Execution for Fast and Efficient Web Agents

Skim is a speculative execution framework for web agents that exploits the predictable structure of purpose-built websites. Today's web-agent expense is not intrinsic to the tasks but a property of how agents are composed: frontier-model inference, browser rendering, and ReAct-style planning are applied to every step of every task regardless of complexity. Skim's key observation is that websites enforce stable URL patterns, answer formats, and task-to-trajectory mappings across queries of the same type, so most queries can bypass these heavyweight components entirely. An offline profiler captures these patterns once per site. At runtime, Skim matches each query to a template, synthesizes the destination URL, and extracts the answer with a small model. A lightweight verifier gates each fast-path output against the query and schema; rare misspeculations cascade to the full agent, warm-started by the fast path's final URL to preserve upstream trajectory progress. Across standard web-agent benchmarks paired with three backboneagents (WebVoyager, AgentOccam, BrowserUse), Skim reduces median per-task cost by 1.9x and latency by 33.4% with no accuracy loss.

cs.AI↗

arXiv2026

Habitable Worlds Observatory (HWO): Living Worlds Community Working Group: The Search for Life on Potentially Habitable Exoplanets

The discovery of a biosphere on another planet would transform how we view ourselves, and our planet Earth, in relation to the rest of the cosmos. We now know Earth is one planet among eight circling our sun; our sun is part of a swirling galaxy of over one hundred billion other suns; and our galaxy is one of untold billions in the universe. While we do not yet know how many, if any, other biospheres exist on the countless worlds orbiting countless other suns, we stand at the precipice of a new era of discovery, enabled by powerful new facilities able to peer across the light years into the atmospheres of planets similar to our own. This article is an adaptation of a science case document (SCDD) developed for the NASA Astrophysics Flagship mission the Habitable Worlds Observatory (HWO) Science, Technology, and Architecture Review Team (START) Living Worlds Community Working Group.

astro-ph.IM↗

arXiv2025

GPUs, CPUs, and... NICs: Rethinking the Network's Role in Serving Complex AI Pipelines

The increasing prominence of AI necessitates the deployment of inference platforms for efficient and effective management of AI pipelines and compute resources. As these pipelines grow in complexity, the demand for distributed serving rises and introduces much-dreaded network delays. In this paper, we investigate how the network can instead be a boon to the excessively high resource overheads of AI pipelines. To alleviate these overheads, we discuss how resource-intensive data processing tasks -- a key facet of growing AI pipeline complexity -- are well-matched for the computational characteristics of packet processing pipelines and how they can be offloaded onto SmartNICs. We explore the challenges and opportunities of offloading, and propose a research agenda for integrating network hardware into AI pipelines, unlocking new opportunities for optimization.

cs.NI↗

arXiv2023

MadEye: Boosting Live Video Analytics Accuracy with Adaptive Camera Configurations

Camera orientations (i.e., rotation and zoom) govern the content that a camera captures in a given scene, which in turn heavily influences the accuracy of live video analytics pipelines. However, existing analytics approaches leave this crucial adaptation knob untouched, instead opting to only alter the way that captured images from fixed orientations are encoded, streamed, and analyzed. We present MadEye, a camera-server system that automatically and continually adapts orientations to maximize accuracy for the workload and resource constraints at hand. To realize this using commodity pan-tilt-zoom (PTZ) cameras, MadEye embeds (1) a search algorithm that rapidly explores the massive space of orientations to identify a fruitful subset at each time, and (2) a novel knowledge distillation strategy to efficiently (with only camera resources) select the ones that maximize workload accuracy. Experiments on diverse workloads show that MadEye boosts accuracy by 2.9-25.7% for the same resource usage, or achieves the same accuracy with 2-3.7x lower resource costs.

cs.DC↗

arXiv2018

The Robo-AO-2 facility for rapid visible/near-infrared AO imaging and the demonstration of hybrid techniques

We are building a next-generation laser adaptive optics system, Robo-AO-2, for the UH 2.2-m telescope that will deliver robotic, diffraction-limited observations at visible and near-infrared wavelengths in unprecedented numbers. The superior Maunakea observing site, expanded spectral range and rapid response to high-priority events represent a significant advance over the prototype. Robo-AO-2 will include a new reconfigurable natural guide star sensor for exquisite wavefront correction on bright targets and the demonstration of potentially transformative hybrid AO techniques that promise to extend the faintness limit on current and future exoplanet adaptive optics systems.

astro-ph.IM↗