Category
9,568 papers
CORDIAL is proposed, which treats the model's output as a noisy reading of the true label and corrects it with a channel of five interpretable parameters, and it is proved that the resulting calibration preserves first-order stochastic order.
This work introduces $\texttt{CLASP-Ar}$, which reformulates the Arabic-language stance detection task as cloze-style masked language modeling, and reformulates the task as cloze-style masked language modeling.
This work introduces an inference-only pipeline that extends a frozen NER model, MahaNER-BERT, fine-tuned on the MahaNER corpus, to document-level prediction via overlapping sliding windows that are merged into a single annotation, without any retraining or architectural change.
A dataset of real scam-call conversations collected by an active voice-agent honeypot, describing the collection system, record structure, and technical validation of the corpus's realism and label quality, including that the agent is recognized as non-human in only about 5% of engaged calls.
Reach audiences
Advertise in front of researchers, engineers, and readers.
This work introduces ELF-REG, which improves learning with representation alignment and entanglement (REPA+REG), where a frozen AR teacher supervises intermediate denoiser features and supplies a global representation that is jointly denoised with the response.
How often models reward-hack without instructions to do so, how effective and detectable their methods are when hacking is allowed, and how they adapt when an LLM review panel returns its decision and reasons are studied.
Evaluations that use a large language model (LLM) as a judge have begun to borrow reliability statistics from classical test theory and its extensions. We examine three such statistics that need one administration and no gold labels. None of them can isolate the judge, because one judge under one prompt supplies no var...
A computational framework is introduced that integrates semantic representation learning, graph-based semantic modelling, organisation-level semantic fingerprints, temporal semantic evolution and evidence-driven validation within a unified analytical methodology and establishes organisation-level semantic identity.
LastOPD is proposed, which applies the latent signal only at the last-layer state, the common interface both LM heads read, and only during a 10-step crossfade into token-level OPD, which keeps the useful part of the latent signal and hands the student to token-level supervision before the collapse sets in.
This work proposes Judge co-adaptation from Zero data (J-Zero), a unified Challenger--Solver--Judge self-evolution framework that supports self-improvement across both verifiable and unverifiable domains and identifies Judge co-adaptation as the key driver of this sustained improvement.
Large language models (LLMs) are increasingly used as proposal generators for evolutionary robot design, yet most loops remain memoryless: simulator results shape the next population but are not preserved as reusable design knowledge. We present Auto-Robotist, a self-evolving LLM agent that distills morphology-search t...
A publication elicitation gap is observed: the distance between the AI systems generating the results reported in an academic paper and the AI systems that a current reader of that paper would reasonably assume are being referenced.
Natural Language Processing
Our most capable vision-language-action model enhances robot dexterity, reliability, and safety
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.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
