Category
9,261 papers
Runtime monitoring of stochastic systems must distinguish nominal distributional relaxation from regime departure while controlling repeated-test false alarms under explicit validity assumptions. This paper links relative-entropy dissipation, information geometry, and sequential inference in a bounded first-passage mon...
Skills are a natural unit for describing what a language model can do and how its behavior can be changed. However, existing characterizations rely on human-written taxonomies, textual descriptions, or manual profiling pipelines--all external hypotheses about what matters that need not align with the model's internal r...
Enterprises commonly deploy heterogeneous database systems, each of which owns a distinct SQL dialect with different syntax rules, built-in functions, and execution constraints. However, most existing NL2SQL methods assume a single canonical dialect (e.g., SQLite) and struggle to produce queries that are both semantica...
This work introduces Iterative Latent Representation Refinement (ILRR), an efficient framework for steering DLMs using a reference text as a high-level semantic blueprint and introduces Spatially Modulated Steering, an extension that enables long-form generation to be guided by shorter references by regulating intensit...
Reach audiences
Advertise in front of researchers, engineers, and readers.
As humans delegate more tasks and decisions to artificial intelligence (AI), we risk losing control of our individual and collective futures. Relatively simple algorithmic systems already steer human decision-making, such as social media feed algorithms that lead people to unintentionally and absent-mindedly scroll thr...
This work introduces Frame Selection Sensitivity (FSS), a per-sample diagnostic that measures how much VLM accuracy changes when the most relevant frames are replaced with the least relevant ones, and constructs TempCore, compact evaluation subsets that isolate temporal samples from existing benchmarks.
This study offers the first work to systematically explore efficient, low-resource personalization of jargon detection using open-source language models, offering a practical path toward scalable, user-adaptive NLP system.
Calpric, which combines automatic text selection and segmentation, active learning and the use of crowdsourced annotators to generate a large, balanced training set for privacy policies at low cost, and produces models that are accurate over a wider range of data categories, and provide more detailed, fine-grain labels...
Chance-calibrated neighborhood discordance (CANDOR) is applied to 22 frozen encoders on 605,443 images from 20 public datasets, covering 8 binary tasks in 7 domains, and finds that on every task, the best encoder is below 1/2.
This work presents a general framework for training large language models (LLMs) to "Connect the Dots", a meta-capability required by long-lifecycle agents, and presents proof-of-concept implementations of the CoD framework, including a GRPO-style RL algorithm with fine-grained credit assignment.
We consider Representation Misdirection (RM), a class of large language model (LLM) unlearning methods that achieve forgetting by redirecting the latent representations of forget-samples toward a target vector. Despite being important, the roles of the target vector used in RM, however, remain underexplored. Here, we a...
Retrieval of information from graph-structured knowledge bases represents a promising direction for improving the factuality of LLMs. While various solutions have been proposed, a comparison of methods is difficult due to the lack of challenging QA datasets with ground-truth targets for graph retrieval. We present Synt...
A Blog post by Ai2 on Hugging Face
A Blog post by IBM Research on Hugging Face
Flint-interactive gives AI agents a language for creating interactive visualizations. Click a chart, filter data, highlight related content, and explore beyond the view the author originally chose. The post Flint-interactive: A language for creating interactive data visualizations appeared first on Microsoft Research.
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
A new computational approach reveals how cells communicate to assemble into tissues. This could accelerate stem cell engineering, improve disease models, and inform therapies.
Zero-knowledge proofs can verify computing results without rerunning workloads or exposing sensitive data. Magnetar helps bring them into the mainstream with support for standard programming languages, major speed gains, and quantum-resistant security. The post Proof-based general-purpose computing with Magnetar appeared first on Microsoft Research.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
