Category
17,191 papers
The uncertainty of a statistical model is most commonly factorized into an aleatoric and an epistemic part. This factorization changes how predictions are interpreted in downstream decision tasks. Importantly, except for the idealistic scenario with no model mismatch, the quantification is a characteristic of the model...
WASP-Mem (Wiki-based Agent-Synthesized Procedural Memory), a nimble but effective method that distills execution traces and feedback into persistent, interlinked wiki pages, enabling continual agent learning is introduced.
OLIVIA, a protocol for point-in-time inputs with company identities masked, selection on validation data only, an analysis plan frozen by cryptographic hash, and a test period unblinded once through a logged lock is proposed.
This work proposes Human-AI-Human collaboration: an interaction topology in which AI connects researchers' contextss and supports inspectable collective evaluation and decision-making, prioritizing shared context and team-visible evaluation checkpoints for controlled follow-up.
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is conjecture that reliably acquiring and maintaining interventional competence when causal commitments fail requires autonomous participation in proposing alternatives, testing their consequences, and revising them in response to error.
LaplaceDiag is introduced, a data-driven method that uses changes in actuator effects to narrow the search for faulty equipment by separating nonlinear prediction based on measured history from an explicit matrix that describes how actuator values affect sensor values.
This work proposes EMBERS, an empirically motivated, defect-guided fuzzing framework for robustness testing of DR systems, and generates stage-targeted test inputs using defect-guided mutation, web-search-assisted fidelity assurance, and diversity-aware seed maintenance.
Before a scientist fits any parameter, they must decide what the model contains: which quantities exist, which are hidden, how they interact, and how they are measured. Physicists call such a trial form an ansatz. Benchmarks for automated equation discovery mostly supply it, by fixing the variables, a library of candid...
Background Adolescent mothers (Girls aged 15-19) constitute 8% of annual global births, but account for 10% of annual maternal deaths. WHO recommended 4-8 Antenatal Care (ANC) visits, in addition to quality care and facility-based deliveries, are well-documented interventions to reduce maternal and child morbidity an...
Long-horizon consistency is essential for video world models, yet it becomes difficult to maintain once observed content falls outside the context window. Existing memory mechanisms either retrieve history as implicit context, which remains constrained by context capacity and entangles static and dynamic information or...
GR4AD-X is presented, which addresses limitations through reliable SID construction, serving-efficient capacity scaling, and unified value alignment, and improves SID reliability through Multi-Path assignment and expands model capacity along multiple complementary dimensions rather than relying solely on wider or deepe...
PDRVLA is introduced, whose lightweight Physical Dynamics Module extracts physical tokens from vision--language features to condition action generation without online video generation, andlations show improved future prediction with world-model supervision and evaluate how subtask conditioning, future object-pose super...
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.
Education Innovation
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
