Category
9,568 papers
PTC-Bias is proposed, a two-stage framework based on phoneme-level temporal competition that reduces near-homophone and word-segmentation errors while preserving correct transcriptions and shows consistent gains across two SpeechLLMs and bias lists of up to 2000 words.
It is argued that current safety fine-tuning constraints the strategic action space of these LLMs, making them unable to fully engage in naturalistic interactions within domains where character contestation is a normative expectation rather than a mere fallacy.
News headlines frame public issues both by what they select and by how they word it, yet computational framing work typically collapses these operations into a single score. We introduce a two-dimensional framework that separates salience framing, measured through four wording devices (loaded vocabulary, blame attribut...
This exploratory study measures brand inclusion across five industries, 50 brands and 250 queries, each put five times to GPT-5.2, Gemini 3 Flash and Perplexity sonar-pro in February and September 2026 (3,614 and 3,750 scored answers). Category Inclusion Rate, Recommendation Share, Competitive Vacuum Index and Co-Menti...
Reach audiences
Advertise in front of researchers, engineers, and readers.
We propose a variational quantum implementation of self-attention (QSA)-the core operation in transformers and large language models-which predicts future elements of a sequence by forming overlap-weighted combinations of past data. At variance with previous approaches, our QSA realizes the required nonlinearity throug...
In autoregressive language models, each token is sampled by conditioning on all the past tokens; the overall string has thus been sampled from the correct underlying joint distribution represented by the model. In contrast, masked diffusion language models generate text by unmasking tokens out of order and potentially...
JoLT demonstrates that tensor-aware low-rank decomposition and quantized residuals, unified under a single storage budget, achieve near-lossless KV-cache compression across diverse model architectures without retraining.
Coupled query-key dynamics, a pre-scoring transformation that evolves each token's query and key jointly through a shared invertible coupling before standard scoring, is studied, finding that coupling is most useful in composition with a scoring-stage method rather than as a standalone change.
This paper introduces a fast, effective, and low-cost method that effectively removes both verbatim and semantic knowledge, corrects biases, and outperforms prior methods.
The findings support viewing the task of conspiracy detection as a socially embedded interpretation task, in which effective classification depends not only on access to contexts, but also on adaptive reasoning in which the agent uses tools on a per-case basis, asking only for evidence relevant to its current reasoning...
Audio language models pass speech and text through a single decoder. We ask whether that decoder represents a distinctive feature in the same direction when a phoneme is heard and when it is read. For minimal pairs of phonemes differing in one feature, we take the offset between the two members'mean representations. Av...
We consider the decision of whether to return an existing draft answer or revise it using retrieved evidence, as in answer-revision systems. Draft confidence estimates whether the current answer is correct, but the decision requires estimating the effect of a specified revision. For offline training and evaluation, we...
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.
