Category
3,317 papers
CRUX (CRoss-modal Unification via teXt anchoring), a fusion framework that uses clinical text---encoded by a biomedical language model---as an institution-invariant semantic anchor for robust, generalizable multimodal cancer prognosis, is presented.
A three-pillared holistic and intentional policy approach that actively pushes for the adoption of cooperative technologies in existing and emerging systems, sets up collective institutional structures to sustain and maintain them in the long-term, and introduces regulatory proposals that limit private entities from di...
This work asks how far a coding agent can go when it controls a robot instead of a computer, and where it stops, and builds a system that keeps what it learns as code, as a coding agent does when it fixes a failing test.
This work investigates whether a complete outcome-specific prompting design improves compact-model outputs beyond generic route-then-generate prompting, and achieves higher intent understanding, device identification, and action/parameter correctness than generic two-stage prompting, while clarification/mode correctnes...
Reach audiences
Advertise in front of researchers, engineers, and readers.
It is shown that narrow fine-tuning reward models to prefer harm in one domain (medical or financial) generalizes to seven held out domains and that reward models are more vulnerable to preference inversions compared to their language model counterparts.
This work presents HarnessMinimizer, a system for efficient minimization of C/C++ library fuzzing harnesses, which reuses header analysis and prepared libraries and runtimes to reduce the work required to build and execute each simplified harness during the reduction process.
This work introduces MambaAct, an efficient Mamba action expert for flow-matching VLA policies, which retains the pretrained visual-language prefix encoder of $\pi_{0.5}$, while replacing its transformer-based action expert with a compact Mamba-based action expert.
Although the evaluated models remain too computationally demanding for widespread deployment in contemporary malware, rapid progress in compact models may reduce this barrier and help anticipate AI-assisted malware and inform future countermeasures.
Findings show answer-only evaluation obscures important grounding failures and position ANCHOR as a testbed for evaluating accurate and evidence-aligned audio-visual reasoning.
LSNR encodes each article independently and constructs a sparse user vector by combining learned, attention-based weighting of the per-article sparse representations with a dense-projected expansion at the user level, which confirms that learned attention-based aggregation outperforms simpler pooling alternatives.
This reproducibility package contains the data, Python code, statistical outputs, and supporting documentation required to reproduce the descriptive and inferential analyses reported in the study “Context-Aware Chunked Generation With Local Small Language Models for Structured Educational Representation: A Multilayer E...
This archive seals the v1.0 experimental state of the GIS-IR study onexecution-verified multi-step spatial analysis workflows with smalllanguage models. It accompanies a manuscript in preparation: "ExecuteFirst, Verify Always: Verifiable Multi-Step GIS Workflows from a 0.6BLanguage Model". Contents (two bundles; SHA-25...
New research can help AI models understand crystalline materials in 3D and reason about their properties.
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’re on a journey to advance and democratize artificial intelligence through open source and open science.
Learn how Google DeepMind and GovTech Singapore uses lightweight on-device Gemma models to intercept conversational scams in private chats with zero cloud data egress.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
