Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
An object-centric residual reinforcement learning framework improves real-world vision-language-action model robustness through simulation-trained corrective policies that transfer…
Current memory agents lack reliable shared institutional deployment due to challenges in balancing utility, access control, and forgetting across multiple principals with diverse a…
Trajectory-Augmented Policy Optimization (TAPO) enhances large language model reasoning by creating explicit corrective trajectories that preserve erroneous reasoning while incorpo…
FAPO optimizes LLM pipelines by combining prompt editing with structural changes, demonstrating superior performance across multiple benchmarks and security tasks.
PerceptionDLM enables efficient parallel region perception in multimodal diffusion language models through structured attention masking and efficient prompting, achieving faster in…
Data-centric approach using curated datasets and minimal GRPO setup significantly improves long-context reasoning in large language models, outperforming prior reinforcement learni…
OpenRath introduces a PyTorch-like programming model for multi-agent systems using Session as a central runtime abstraction that enables explicit fork, merge, and replay operations…
The Mahalanobis cosine similarity provides a theoretically grounded method for comparing linear probes that correlates strongly with out-of-distribution performance metrics.
ACIE, an agentic RAG system deployed in a clinical setting, demonstrates high accuracy in extracting medical information from complex patient contexts, achieving 96.
WorldLines benchmark evaluates long-term memory in embodied agents through household scenarios, while ObsMem framework addresses challenges in partial observability and memory tran…
NVIDIA XR AI is now available in public beta, giving developers a framework for building multimodal AI agents for AR glasses and XR devices.