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
-
EMNLP 2026 Workshop on Pluralistic AI and NLP: Diversity-Aware, Sociotechnical, Responsible Alignment (PANDORA)2026Large language models (LLMs) are increasingly used in culturally sensitive settings, where alignment requires representing diverse preferences within populations. Yet existing methods model populations at coarse demographic or community levels and overlook within-group variation. We introduce DEMOGRAPHIC PLURALISM, an inference-time framework that estimates population-level opinion distributions without
-
SOSP 20262026Foundation model (FM) inference platforms must manage scarce accelerator capacity distributed unevenly across regions. They must also handle requests whose token consumption varies widely and may be revealed progressively during generation, while sharing capacity across workloads with different latency and throughput objectives. This paper describes the architecture of the Workload Management System (WLM
-
2026Fine-tuned small language models (SLMs) are attractive defaults for large-scale structured attribute generation—producing values such as materials, colors, or dimensions from product descriptions—as they are inexpensive to serve. However, a fine-tuned SLM is not reliable everywhere as its correctness varies sharply, so deploying it still requires deciding, per output, whether to keep the SLM's value or
-
ICDM 20262026Optimizing embedding systems for production recommendation pipelines demands systematic exploration that consumes disproportionate engineering effort at scale. We apply Andrej Karpathy's AutoResearch paradigm [1]—a large language model that iteratively edits a training script and retains modifications that improve a held-out scalar metric—to automate this exploration. We report on twelve weeks of running
-
2026A key challenge in reliable LLM deployment is recognizing when uncertainty reflects irreducible variability in the task rather than limitations in the model's knowledge. In language tasks, a central source of such aleatoric uncertainty is input ambiguity or underspecification, where multiple interpretations remain plausible. Existing decomposition methods estimate aleatoric uncertainty by generating multiple
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all