Prépublication
· 2026 arXiv
EN
Venus and Mars are unique laboratories for understanding the evolution and diversity of terrestrial planets. Despite their broadly similar rocky compositions, their atmospheres, climates, and surface environments have evolved into dramatically different states...
Hideo Sagawa, Arianna Piccialli et al.
#astro-ph.IM
Prépublication
· 2026 arXiv
EN
Simulating chaotic planetary system evolution requires resolving small time-scales due to close encounters, scattering, collisions, and more. Simulations typically assign fixed timesteps to all particles, however, which is inefficient and wastes compute resour...
David M. Hernandez, Tenri Jinno et al.
#astro-ph.EP
Document numérisé
· 1582 Gallica (BnF)
FR
Document numérisé par la Bibliothèque nationale de France, publié en 1582. Thème : astronomie. Consultable en ligne sur Gallica.
Bibliothèque nationale de France
#Astronomie
Document numérisé
· 1582 Gallica (BnF)
FR
Document numérisé par la Bibliothèque nationale de France, publié en 1582. Thème : astronomie. Consultable en ligne sur Gallica.
Bibliothèque nationale de France
#Astronomie
Document numérisé
· 1506 Gallica (BnF)
FR
Document numérisé par la Bibliothèque nationale de France, publié en 1506. Thème : astronomie. Consultable en ligne sur Gallica.
Bibliothèque nationale de France
#Astronomie
Prépublication
· 2026 arXiv
EN
Recent advances in robot learning have driven rapid progress in humanoid control, enabling increasingly agile behaviors in the real world. However, humanoid control networks are typically obtained through conventional training procedures, while comparatively l...
Huixuan Cheng, Bike Zhang et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Training language agents is bottlenecked by the high cost of long-horizon rollouts, yet standard agentic reinforcement learning (RL) learns only from a terminal scalar reward, leaving the supervision in intermediate steps largely unused. Prior work exploits th...
Haofei Yu, Yixing Chen et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Scaling up transformers has produced models with broad capabilities, deployed across heterogeneous hardware and fluctuating workloads. Yet, model families offer only a few fixed sizes (e.g., S, B, L), forcing users to commit to a model based on hardware and la...
Walter Simoncini, Dheeraj Varghese et al.
#cs.LG
Prépublication
· 2026 arXiv
EN
We introduce Continuum Attention (CA), a causal Transformer attention operator that replaces discrete key and value lookup with integration over a continuous, piecewise linear memory curve. Each query induces an exponential relevance density along the curve. I...
Afshin Khadangi
#cs.LG
Prépublication
· 2026 arXiv
EN
Computer-use agents have demonstrated strong capabilities in interpreting screens and executing keyboard and mouse actions. However, games, with their visually rich worlds and diverse mechanics, remain challenging and offer a demanding next step toward general...
Mingyu Ouyang, Yiran Wang et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
We introduce a novel method for verifying Lean formalizations that goes beyond LLM-judged faithfulness. Unlike most verification methods, which rely on LLMs or trained models, our method combines LLM-based semantic review with mechanical numerical and vacuity...
Anna Mei, Michael R. Douglas
#cs.LO
Prépublication
· 2026 arXiv
EN
On-policy distillation (OPD) trains a student model on its own rollouts with token-level supervision from a teacher, assuming that the teacher can reach a correct answer from any prefix the student writes. We call this property the recoverability of the teache...
Kaixiang Zhao, Tianrun Yu et al.
#cs.LG