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
-
2026Attribute–value extraction is important for building high-quality product catalogs in e-commerce. Existing systems either rely on generative or tagging strategies for extracting the attribute names and their corresponding values. Tagging models directly label spans in the source, making them fast and grounded, but they cannot produce values that require reformatting or generate rare attribute names outside
-
2026Pruning is a critical technique for compressing Large Language Models (LLMs), yet its effectiveness is highly sensitive to the small calibration set used for parameter-importance estimation. Current selection often relies on heuristics such as random sampling or entropy, leading to substantial variation in post-pruning perplexity. We analyze this instability at two levels. Calibration samples have unequal
-
Transactions on Machine Learning Research2026Recently, there has been growing interest in incorporating textual information into foundation models for time series forecasting. However, it remains unclear whether and under what conditions such multimodal text integration consistently yields gains. We systematically investigate these questions across a diverse benchmark of 16 forecasting tasks spanning 7 domains, including health, environment, and economics
-
2026Unified Multi-Modal Generation (UMMG) models support seamless switching between generation tasks spanning multiple modality combinations within a single conversational interface. However, existing safety benchmarks construct prompts independently per modality, so different modalities cover different harmful intentions, preventing holistic evaluation of UMMG models. We propose an intention-grounded evaluation
-
AACL 20262026Large language model (LLM)-based agents are widely deployed in user-facing services but remain error-prone in new tasks, tend to repeat the same failure patterns, and show substantial run-to-run variability. Fixing failures via environment-specific training or manual patching is costly and hard to scale. To enable self-evolving agents in user-facing service environments, we propose WISE-Flow, a workflow-centric
Collaborations
View allWhether you're a faculty member or student, there are number of ways you can engage with Amazon.
View all