Category
9,049 papers
Adaptive Unlearning is presented, a post-deployment framework that surgically suppresses package hallucinations while preserving general model utility and relies entirely on model-generated data and requires no human annotation, representing a post-deployment hallucination mitigation framework.
This work evaluates the framework on two statutory domains using two LLMs using two LLMs (Claude Opus~4.6 and GPT-5.2) with three repair baselines, finding diagnosis-guided scoped repair is the most effective method, with effectiveness contingent on the reliability of the diagnosis function.
This analysis indicates that robust Long-Term Memory security cannot be retrofitted at retrieval or execution time alone, but must be anchored in storage-time provenance, versioning, and policy-aware retention from the outset.
FMMD is introduced, a multimodal and multidisciplinary open peer review dataset curated from F1000Research that supports a range of research tasks, including visual-semantic consistency classification, figure-related review comment generation, and editorial decision prediction based on multimodal manuscript inputs.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Large language models (LLMs) are typically aligned with population-level preferences, despite substantial variation across individual users. We introduce POPI, a user-level personalization framework that separates the problem into two components connected by a natural-language interface: a shared inference model that d...
BigO(Bench) is introduced, a novel coding benchmark designed to evaluate the capabilities of generative language models in understanding and generating code with specified time and space complexities, and results from evaluating multiple state-of-the-art language models on this benchmark are presented.
This work meticulously design a dual-stage pretraining work flow with four dedicated submodels to capture representative dependency agreements at the chunk level, effectively transforming these agreements into embeddings to benefit the pretraining.
DFAH-Bench connects replay observability to evidence, authorization, completion and cost: evidence sufficiency needs direct assessment alongside repeatability, and fixed-state probes reveal higher decision agreement alongside lower agreement with constructed policy labels.
EndoCogniAgent is proposed, a closed-loop agentic framework that formulates endoscopic diagnosis as a controlled state update process for integrating complementary visual and textual evidence and introduces EndoAgentBench, a workflow-oriented benchmark to evaluate diagnostic agents across a comprehensive diagnostic cha...
SpeakerMem-R1 is proposed: its dual-track memory stores speaker-labeled verbatim messages and derived states organized into person-level and group-level views, then combines evidence from both tracks by entity, event, and time at query time, and ablations show that the verbatim and structured tracks, as well as person-...
A small concept generator is optimized with reinforcement learning so that its concepts maximize the downstream success of a larger, frozen answer generator, and can thus be trained into an effective, reusable search policy for a much larger one.
It is shown that measured outcomes can depend on the serving layer rather than model behavior alone rather than model behavior alone, and a checklist for treating serving behavior as part of the evaluation protocol is concluded.
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.
