Prépublication
· 2026 arXiv
EN
Vision-language-action (VLA) models have shown promise in robotic manipulation, but imitation learning (IL) alone often struggles to master complex long-horizon skills. Reinforcement learning (RL) offers an effective avenue for further improving VLA policies....
Likui Zhang, Zhe Zhu et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Parallel AI agents can produce useful local edits yet degrade a shared solution when their edits are combined. We model this coordination problem as discrete block optimization with an exactly evaluable objective and a known dependency graph. Independent sets...
Hanmin Li, Yury Demidovich et al.
#cs.MA
Document numérisé
· 1620 Gallica (BnF)
FR
Document numérisé par la Bibliothèque nationale de France, publié en 1620. Thème : mathématiques. Consultable en ligne sur Gallica.
Bibliothèque nationale de France
#Mathématiques
Prépublication
· 2026 arXiv
EN
Attribution of observed historical climate evolution to externally forced change and internal variability is fundamental to understanding climate change and evaluating climate models. Yet such attribution remains challenging because the forced response is inte...
Parvathi Kooloth, Wenyu Zhou et al.
#physics.ao-ph
Prépublication
· 2026 arXiv
EN
Video generation models can now depict remarkably realistic motion. Yet it is unclear how to use this motion beyond pixels: to animate a specific 3D asset and replay the animation in its 3D scene. For instance, a video model can show a monkey jumping over a cr...
Noam Rotstein, Yoad Tewel et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
Agentic artificial intelligence (AI) systems hold immense potential for automating complex workflows in materials discovery and design, but extending them to domain-intensive mechanistic investigations remains challenging. Here, we present GBClaw, an agentic A...
Yazhuo Liu, Kunqing Ding et al.
#cond-mat.mtrl-sci
Prépublication
· 2026 arXiv
EN
Motivated by the human ability to integrate experience across language, perception, and action, we introduce UniWALM, a unified world-action-language model that learns video, action, and language in a single shared representation, where each modality is both a...
Rahul Sajnani, Diego Romeres et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Warehouse robot fleets continuously observe operational conditions, but preserving these observations as reusable semantic memory incurs substantial computation, communication, and storage costs. For example, explaining recurring aisle blockages can require re...
Jad Yammine, Malek Wahidi et al.
#cs.RO
Prépublication
· 2026 arXiv
EN
Spatial intelligence has recently been assessed through generative tasks such as spatially grounded image editing, yet language-guided generation of spatially consistent views from partial multi-view observations remains underexplored. We introduce MindView, a...
Yanbo Wang, Siqi Luo et al.
#cs.CV
Prépublication
· 2026 arXiv
EN
Multi-token prediction (MTP) can accelerate language-model decoding by drafting several tokens and verifying them in a single target-model pass. However, the best speculation horizon changes with context: longer drafts offer greater amortization when reliable,...
Emile Anand, Mohammed Rehan Parwani et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Modern distributed microservice deployments generate massive volumes of heterogeneous, multi-format observability logs across physically and logically partitioned infrastructure. Isolating root causes during cascading failures remains an arduous task for Site...
Jitendra Solanki, Anand Todkar et al.
#cs.AI
Prépublication
· 2026 arXiv
EN
Mathematical reasoning remains underexplored for low-resource languages, including Dialectal Arabic. To bridge this gap, we introduce the DAR-MGSM (Dialectal Arabic Multilingual Grade School Math) Benchmark, the first manually curated benchmark for evaluating...
Noor Abo Mokh, Teresa Lynn et al.
#cs.CL