Customer-obsessed science
Research areas
-
November 16, 202611 min readNew open-source tool turns existing test suites into sets of formal-verification tasks, which catch buggy solutions that tests alone would miss.
-
November 11, 20265 min read
-
-
-
Featured news
-
ICORES 20272027We study the problem of assigning customer orders to fulfillment centers in Amazon’s logistics network. We analyze this assignment problem in both offline and online settings, developing a range of algorithms for each scenario. In the offline setting, we present solver-based and heuristic approaches including mixed integer programming (MIP), best-fit algorithms, and local search methods. For the online
-
ICDE 20272027A fundamental challenge of vector search is achieving consistently high recall while minimizing computational costs. Fixed search parameters cause significant performance variance across queries, and conventional evaluation on average recall masks these per-query disparities. We introduce QASP (Query-Adaptive robust vector Search Policy), which predicts the complete recall progression curve per query via
-
IAAI 20272027Alexa+ devices with screens display animated icons during conversations to visually reinforce what is being said. The original set of these icons was hand-drawn by designers one at a time, a process that produces polished results but is time-consuming and cannot scale to the range of topics encountered in open-ended conversation. We describe an automated pipeline, deployed in production, that generates
-
NeurIPS 2026 Workshop on Machine Learning for Systems (MLForSys)2026Video Sparse Attention (VSA) accelerates video diffusion by applying exact attention to selected regular blocks, but its 64-token support granularity can discard locally important interactions. We introduce a training-free refinement that scores 8-token sub-blocks while preserving the selected valid-token count of the released 80%-sparse VSA configuration for every query block. Across a matched, fixed-seed
-
2026Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.e., trained adapters that merge retrieved examples into the backbone's forecast, based on the assumption that frozen backbones cannot dynamically incorporate retrieved context on their own. We show this assumption
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all