arXiv:2611.00983v1 Announce Type: new Abstract: Early-exit language models decide for each token how much computation to spend, usually by stopping once the prediction is confident. Yet a token is not a fixed unit: tokenizers cut words into different numbers of pieces in different languages. We ask
arXiv:2611.00986v1 Announce Type: new Abstract: Learning from extensive longitudinal clinical records--spanning repeated encounters, evolving conditions, and heterogeneous documentation--under a finite labeling budget requires solving two coupled problems: deciding what evidence to keep and decidin
arXiv:2611.01065v1 Announce Type: new Abstract: Gated knowledge distillation (KD) weights teacher signals per token or example, aiming to trust an imperfect teacher only where it seems reliable. We test two gates: EWAD (entropy-weighted agreement-aware distillation), which gates tokens by teacher c
arXiv:2611.01113v1 Announce Type: new Abstract: Can a language model learn better ways to reason about other people's minds by improving its own strategies, and are the strategies it learns actually right? We study this with cogrsi. A grounded reader marks who saw each event in a story and uses a s
arXiv:2611.01115v1 Announce Type: new Abstract: LLM agents increasingly rely on skill documents, yet most retrievers rank them by description alone and ignore what earlier executions revealed, even though a relevant skill can hurt execution. We present CompSkill, which indexes skills with learned 5
arXiv:2611.01123v1 Announce Type: new Abstract: Financial restatements correct errors in previously published financial reports. Could managers' language in earnings calls warn of them in advance? Comparing 109 calls that precede restatements with 218 matched control calls, we find that the text pr
arXiv:2611.01133v1 Announce Type: new Abstract: Structured pruning reduces the size of large language models, often at the cost of lower accuracy. Whether this decline reflects diminished reasoning capacity or greater difficulty in sampling correct solutions is less clear. We examine this question
arXiv:2611.01143v1 Announce Type: new Abstract: Generative spoken language models (SLMs) offer a route to learning linguistic structure purely from speech, yet they lag far behind text-based models in both capability and data scaling efficiency. We identify two bottlenecks underlying this gap: the
arXiv:2611.01191v1 Announce Type: new Abstract: Despite growing interest in Arabic natural language processing, curriculum-aligned educational resources remain scarce compared with English, and few public datasets for Arabic curriculum content with structured, generation-ready annotations are avail
arXiv:2611.01219v1 Announce Type: new Abstract: In this work, we present a case study that explores various tasks centered around the topic of migration in Slovak, a low-resource language, such as topic relevance and geographical relevance classification, and migration source/destination location t
arXiv:2611.01261v1 Announce Type: new Abstract: Spoken medical question answering can fail when automatic speech recognition (ASR) corrupts a clinically important term before retrieval. We present MedAstra, a framework that maps frozen WavLM speech representations through a lightweight adapter into
arXiv:2611.01268v1 Announce Type: new Abstract: Voice conversion (VC) models can be used to anonymize speech data while preserving naturalness. Existing models, however, are mainly optimized for English and other high-resource languages, and they fail to generalize well to Arabic due to its distinc
arXiv:2611.01284v1 Announce Type: new Abstract: Character names in large language model (LLM) fiction concentrate on a handful of recurrent names such as 'Elara' and 'Elias', a measurable face of AI slop. Existing fixes either require logit access or retraining, or operate per request and cannot co
arXiv:2611.01301v1 Announce Type: new Abstract: Large Language Models (LLMs) are increasingly deployed in multi-agent settings, exhibiting emergent collective behaviors, yet the role of curiosity as a driver of such dynamics remains understudied. We introduce CuriousTogether, a framework evaluating
arXiv:2611.01304v1 Announce Type: new Abstract: What happens when language models are given tools to iteratively modify their own system prompts? We present an empirical study of LLM self-modification, comprising 54 independent experiments across six language models (Claude Opus 4.5, Claude Sonnet
arXiv:2611.01320v1 Announce Type: new Abstract: Diffusion large language models (dLLMs) generate tokens in parallel via iterative denoising, but their bidirectional attention prevents the KV caching used by autoregressive models and recomputes the full attention map at every step, incurring quadrat
An LLNL germanium sensor aboard JAXA's MMX spacecraft will map the elements on Phobos and help pick where the mission collects samples for return in 2031. The post LLNL’s gamma-ray sensor is bound for a Martian moon appeared first on Research & Development World.
RLWRLD, developer of the RLDX-1 foundation model for five-fingered robot hands, named former IBM Consulting Korea managing partner Min Jung Kim as COO. The post RLWRLD names former IBM consulting executive COO to advance robotics commercialization appeared first on Research & Development World.
Anthropic spent nearly $28 billion on R&D from 2024 through September 2026. Its amended IPO filing says safety measures could slow it relative to rivals. The post After spending tens of billions on R&D, Anthropic sees reasons to slow its pursuit of self-improving AI appeared first on Research & Deve
OpenAI says GPT-6 Astra designed the case, circuit board and firmware for a talking Codex device. A factory built prototypes after several rounds of fixes. The post OpenAI says GPT-6 Astra designed a talking Codex “pet.” Manufacturing took several rounds appeared first on Research & Development Worl