Found 42,749 document(s)
Page 18 of 2850
-
We present Épi, an autonomous research agent that sustains investigations across model sessions and evolves its methods through accumulated experience. Épi combines persistent research history, hierarchical memory, branc...
-
The near-field evolution of chemically reactive pollutants in the exhaust plume of a 270 m crude oil tanker is investigated using a high-fidelity Computational Fluid Dynamics (CFD) framework coupled with a Conditional Mo...
-
Language models behind coding agents are post-trained with outcome rewards, and recent methods concentrate credit on the turns that decide the outcome. We find that defensive actions beyond what a task requires escape bo...
-
Language model benchmarks assign each question a single outcome from one fixed wording, even though the same underlying request can be expressed in many equivalent ways. We argue that the quantity of interest should ther...
-
Safely overseeing AI is increasingly challenging for the humans doing it, as they must evaluate longer and more complex outputs with every new model generation. To mitigate this challenge, we could leverage complementari...
-
Checklist rubrics applied by large language model (LLM) judges have become a standard instrument for evaluating open-ended outputs and for rewarding them during training. Two assumptions surround this practice: that leni...
-
Video models provide rich priors for generalizable robotic manipulation, but plausible visual futures are not always executable. We introduce DreamCan, a hierarchical policy that grounds video models through sparse visua...
-
This article describes the application of HEXRD, an open-source Python library for X-ray diffraction analysis, and HEXRDGUI, its companion graphical application, to dynamic compression experiments. Built on a generic mul...
-
State media outlets often project their governments' narratives to target both domestic and foreign audiences. Because this content is plentiful and free to access, it appears widely in the web corpora that large languag...
-
In an era where sustainable development is paramount, higher education stands as a pivotal force in shaping the future of international development. "Education for Sustainable Development" (ESD) explores the profound inf...
-
Nous attendons d’un livre qu’il nous mette en garde contre les dangers diététiques du bifteck, qu’il revienne sur l’histoire du scoubidou et qu’il évoque les raffinements de la dentelle. Les derniers romans de Céline, so...
-
"Estava faltando uma obra que analisasse com profundidade teórico-política, e fundamentada na crítica da economia política, o projeto da Reforma Sanitária desde a sua constituição, em meados dos anos 1970, até a atualida...
-
Prompt injection is the dominant security risk for large-language-model (LLM) applications and agents, yet the field still lacks a coherent map of how these attacks are constructed. More than twenty public datasets descr...
-
Nowadays, robotic telemanipulation enables humans to control robots so as to execute tasks in a manner similar to how they perform them, and serves as an essential approach for collecting on-robot data for robot learning...
-
Automated theorem provers often rely on sampling language models, but proof assistants like Lean reject each failed step with a precise error message --- information that pure sampling discards. To overcome this, we intr...