Category
17,191 papers
Activation probes are computed directions in a language model's residual stream, used both to detect safety-relevant behaviours and, by adding their direction back into the stream, to steer them, which power an interactive interface through which a user can score and steer text directly.
CTRL-FM, an observation-preserving flow-matching framework that treats structural guidance as an outage-conditioned inference-time decision, is introduced, demonstrating that validating, selecting, and locally adapting structural guidance for each realized outage is more effective than imposing a single global structur...
A spike-aware gradient-based mixed-precision quantization framework for SNNs that adaptively assigns bit-widths using first-order gradient information, avoiding costly second-order Hessian computations is proposed.
Generator-Agent-Verifier (GAV), a scientific experimentation environment that makes new PDE problems verifiable by construction verifiable by construction, is introduced and a theoretical analysis of evaluation reliability and guided development is provided.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work advances Markov chain Monte Carlo algorithms by introducing novel moves that simultaneously resample the parents for multiple nodes of the DAG by introducing duet sampling, a new generalization of the Metropolis-Hastings algorithm.
SWE-Verifier is introduced, a lightweight generative model that selectively triggers candidate sampling and verification that achieves comparable or higher resolution than the trajectory and all-step baselines at substantially lower cost.
PolarGD, the orthogonalized update at the core of Muon, is studied on matrix quadratics, where optimizers can be analyzed in closed form, and update directions under line search are compared to remove the effect of learning-rate tuning.
This work proposes minimal-edit corrective on-policy distillation, a method that preserves on-policy supervision while avoiding full-response imitation, and improves perception-oriented performance, particularly low-level geometric perception, and transfers to external mathematics and perception benchmarks.
A lightweight screening tool that uses four small models to identify patients with high risk of exposure before production-model training and assess if flagged patients could be protected without removing their data is developed.
A comprehensive comparative analysis of four state-of-the-art model compression techniques applied to a high-performance convolutional neural network for predictive maintenance using a real-world dataset of rotating machinery, equipment typically used in industry.
A lightweight Group Equivariance Attention Network (GANet) designed for the prediction and monitoring of 38 types of plant diseases, with only 0.001M parameters, achieves an impressive 99.99% accuracy on the PlantVillage dataset.
No single prompt was best: the strongest prompt depended on the task type and on whether results were summarized by the mean or the median, suggesting that, at least for these tasks, prompt style should be matched to the objective rather than treated as universal.
A machine-learning approach called CheMeleon provides a practical way to develop new drugs or other molecules with much less detailed, expensive experimentation.
A Blog post by Ai2 on Hugging Face
Research Manager Mike Walker reflects on a career spanning hacker culture, cybersecurity, and AI, sharing lessons about trust, teamwork, leadership, and why solving difficult problems requires curiosity, judgment, agility—and an understanding of the rules. The post Learn the rules: The hacker mindset appeared first on Microsoft Research.
Learn how Google Antigravity and our Cheminformatics Skills accelerate drug discovery workflows, search compounds, and propose novel rigidified macrocycles.
Professor Paris Smaragdis develops computers with superhuman hearing for applications like speech recognition, music understanding, and environmental monitoring.
Prabha Jha used her experience with MIT Open Learning’s program for senior executives to develop AI solutions for her employer, Verizon, and to write a book.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
