-
CLeaR 20252025Which set of features was responsible for a certain output of a machine learning model? Which components caused the failure of a cloud computing application? These are just two examples of questions we are addressing in this work by Identifying Coalition-based Explanations for Common and Rare Events in Any Model (ICECREAM). Specifically, we propose an information-theoretic quantitative measure for the influence
-
2025Autonomy via agents based on large language models (LLMs) that can carry out personalized yet standardized tasks presents a significant opportunity to drive human efficiency. There is an emerging need and interest in automating web tasks (e.g., booking a hotel for a given date within a budget). Being a practical use case itself, the web agent also serves as an important proof-of-concept example for various
-
2025This paper presents a new challenge that calls for zero-shot text-to-speech (TTS) systems to augment speech data for the downstream task, personalized speech enhancement (PSE), as part of the Generative Data Augmentation workshop at ICASSP 2025. Collecting high-quality personalized data is challenging due to privacy concerns and technical difficulties in recording audio from the test scene. To address these
-
2025A popular approach to building agents using Language Models (LMs) involves iteratively prompting the LM, reflecting on its outputs, and updating the input prompts until the desired task is achieved. However, our analysis reveals two key shortcomings in the existing methods: (i) limited exploration of the decision space due to repetitive reflections, which result in redundant inputs, and (ii) an inability
-
2025Scaling test-time compute to search for optimal solutions is an important step towards building generally-capable language models that can reason. Recent work, however, shows that tasks of varying complexity require distinct search strategies to solve optimally, thus making it challenging to design a one-size-fits-all approach. Prior solutions either attempt to predict task difficulty to select the optimal
Related content
-
January 11, 2022Learn how the F1 engineering team collaborated with AWS to develop new design specifications to help make races more competitive.
-
December 23, 2021Ban, an Amazon Visiting Academic, won for a paper she co-authored with Duke University professor Cynthia Rudin.
-
December 20, 2021Krishna Gade, the founder of this Alexa Fund portfolio company, answers three questions about ‘responsible AI’.
-
December 09, 2021Gari Clifford, the chair of the Department of Biomedical Informatics at Emory University and an Amazon Research Award recipient, wants to transform healthcare.
-
December 08, 2021With the support of an Amazon Research Award, Papoian’s team is deciphering the dynamics of intrinsically disordered proteins.
-
December 07, 2021Synthetic data produced by perturbing test inputs identify error classes and provide additional data for retraining.