Category
7,776 papers
This work explores the use of synthetic visual data as a solution, using an audio-driven talking-head pipeline to generate lip-synchronized visual content from existing audio data and demonstrates that synthetic data alone can serve as a baseline for AVSR training in languages lacking AV datasets.
The Conversational Distribution Score (CDS) is introduced, which compares distributions of conversational behaviour using human conversations as a reference, and how many minutes and conversations are required before rankings stabilize is examined.
Frequency BPE achieves stronger raw compression, while MDL-SG achieves lower BPC, showing that compression-oriented merge selection and language-model utility need not coincide.
Identifying intertextual references is central to literary scholarship, but computationally difficult when source material is transformed through paraphrase, allusion, historical language, and translation. We investigate this problem through biblical intertextuality in Karen Blixen's Seven Gothic Tales. Drawing on the...
Reach audiences
Advertise in front of researchers, engineers, and readers.
NstAgent is introduced, a training-free agentic framework that allows LLMs to track a structured narrative state including characters, past events and future requirements, and shows that NstAgent achieves better narrative consistency and writing quality as stories grow longer, suggesting that it provides an effective a...
This paper designs TACT to revise student-generated actions, test the revisions through partner responses, and distill useful feedback into the student, which helps improve social goal attainment while reducing communication cost.
QuanReview aligns two annotation streams over the same documents at character level, resolves unambiguous cases by an explicit and logged policy, and routes candidate conflicts to a browser-based adjudication interface where reviewers accept either side, build field-level hybrids, or flag items for re-annotation.
The proposed MSEF represents each character as an era-specific manifold point and learns continuous inter-era transition rules via Neural Ordinary Differential Equations, which can be trained end-to-end through character evolution pairs across any two eras.
Large language models (LLMs) reliably perform entity copying, in which a model copies tokens referring to an entity, termed entity tokens, from the prompt into its output to answer a question. Although entity copying is straightforward for most LLMs, existing research does not provide a systematic account of which laye...
Many language tasks have no single answer that can be checked automatically. Rubrics provide criteria for judging responses to these tasks. For reinforcement learning, the resulting verdicts must be combined into a scalar reward. A common approach sums the points assigned to satisfied criteria. Distinct verdict pattern...
It is demonstrated that verifying evidential support before submission can make diagnostic decisions more reliable, and decouples diagnosis generation from submission through an offline Contrastive Diagnostic Wiki and three online control stages, namely observation management, proposal and witness verification, and dia...
It is demonstrated that valence-related activation patterns leave hidden traces that predictably govern later choices, even when all visible tokens are identical across conditions, and whether these traces are accompanied by any subjective experience relevant to model welfare remains unclear.
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.
A new language-processing tool could help identify the highest-risk individuals from natural language, enabling swifter interventions.
A Blog post by Liquid AI on Hugging Face
Gemini 3.8 Live and Gemini 3.8 Live Extended Thinking are our most advanced live dialogue models yet, built for natural conversation.
A new method, called CW-Net, translates the reasoning process of an autonomous vehicle’s AI system into understandable concepts that explain its behavior.
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
