Category
3,445 papers
Large language models can translate business descriptions into optimization models, but executable code may misrepresent constraints or objectives. A solver can then return an optimal solution to the wrong problem. Even when the solution satisfies the intended operating rules, a better plan may exist. For organizations...
Large language models (LLMs) increasingly underpin scientific AI applications that reason over structured knowledge, from biomedical question answering to materials informatics. However, their logical reasoning often falls short, producing factual inaccuracies unacceptable in these settings. Reliable evaluation remains...
Reusable Latent Correction (RLC) is proposed, which converts one-off natural-language guidance from a black-box LLM into persistent corrective experiences in the hidden space of an SLM, enabling the SLM to reuse LLM-derived corrections during inference without any online LLM calls.
Combining two-step denoising with representative execution methods substantially reduces inference cost with a small reduction in task performance, motivating joint optimization of model-inference efficiency and robot-system timing.
Reach audiences
Advertise in front of researchers, engineers, and readers.
Comparing empirical cross-lingual transfer with typology-based similarity, it is found that transfer BLEU identifies closely interacting language pairs better than URIEL similarity, though neither predicts which varieties benefit from joint training.
Everyday objects, whether placed by an adversary or introduced by ordinary rearrangement of the environment, are thus sufficient to overturn a refusal, and susceptibility to safety bypass is called a property of the task, which it is shown that it can be predicted before the target is ever queried.
Automatic speech recognition (ASR) still covers only a small fraction of the world’s languages, mainly due to supervised data scarcity. In-context learning (ICL) with large language models (LLMs) addresses this problem, but prior work largely focuses on high-resource languages covered during training and text-only sett...
The EU Artificial Intelligence Act requires high-risk AI systems to record events automatically, requires providers and deployers to keep those logs, and gives authorities access to them. The Act says what logs are for - traceability, monitoring, post-market surveillance - but it does not say what a log proves. That si...
This article analyzes the pedagogical and methodological foundations of developing students’ speaking skills in English language lessons. Speaking skills are regarded as an essential component of communicative competence in foreign language acquisition. The study examines the potential of the communicative approach, Ta...
当前人工智能大模型在长期记忆保持与幻觉抑制方面面临严峻挑战,其核 心痛点在于缺乏一个能够统筹信息存储与生成约束的统一状态场。本文基于 “太极统一场论”的工程落地探索,提出将长期记忆与 AI 幻觉视为同一对偶约 束在不同区间的显化。本文构建了统一标度 K = 观测尺度/记忆场参考尺度(或 等价的对偶失衡度 K,K∈[-1,1]),并明确了三区间判据:K<0...
Materials for an exploratory evaluation of Warrant (https://doi.org/10.5281/zenodo.23029803). Twenty small Python command-line tasks, each with plain-language promises, visible checks, hidden checks, an audit suite, a reference implementation and deliberately broken implementations; the validity gates; the harness; Par...
A Blog post by IBM Granite on Hugging Face
We’re on a journey to advance and democratize artificial intelligence through open source and open science.
Gemini 4 Carbon is our strongest model with state-of-the-art cybersecurity and long horizon capabilities.
A Blog post by Liquid AI on Hugging Face
Genie 4: our new world model unlocking unprecedented realism in real-time simulation.
Generative AI
We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.
