Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Arbor enables explicit 3D spatial control in text-conditioned latent generation through constraint meshes that define occupancy, avoidance, and contact regions, maintaining object…
ReNIO enhances on-policy distillation for language models by reweighting negative trajectories based on token-level probability ratios, improving reasoning performance in mathemati…
ChartWalker presents a novel framework for cross-chart retrieval-augmented generation with hierarchical knowledge graph construction and structure-aware sampling for challenging mu…
A novel RL training approach for terminal agents achieves superior performance using a simplified recipe and expanded dataset, enabling effective training with fewer parameters tha…
Language models should assist causal discovery workflows by providing contextual support and explanations rather than generating causal conclusions, as demonstrated through a platf…
A failure detection framework for long-horizon robotic tasks uses action-conditioned world models and functional conformal prediction to monitor manipulation trajectories with only…
A bi-modal construction domain dataset combining stereo RGB and LiDAR data under challenging environmental conditions is introduced for autonomous system perception research.
AOHP presents an Android-based operating system framework that treats AI agents as first-class entities, enhancing task completion rates and reducing execution costs through specia…
PhoneBuddy combines real and mock app environments to improve training of open models for phone use, demonstrating enhanced task success rates through mixed reinforcement learning…
UniverSat introduces a Universal Patch Encoder for Vision Transformers that enables robust, sensor-agnostic spatial feature extraction across diverse Earth Observation data types.
Computer-use agents can execute software tasks through either graphical interfaces or programmatic command interfaces, but existing evaluations confound interaction modality with d…
Standard LLM agents rely on plan content remaining in context rather than maintaining it as persistent state, with evidence shown through replay pairing diagnostics and compression…