Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
KaLM-Reranker-V1 is a fast reranker that decouples query and passage computation using encoder-decoder architecture with Matryoshka embedding pooling and cross-attention for effici…
EnterpriseClawBench presents a benchmark for enterprise agents based on real-world sessions with 852 reproducible tasks, emphasizing comprehensive evaluation metrics beyond single…
The book provides a comprehensive guide to building autonomous AI systems, covering foundational elements like transformer architecture and training methods, along with advanced to…
HeRA aligns individual attention heads in MLLMs to preserve local neighborhood relationships across modalities, improving vision-centric task performance and reducing visual halluc…
Unlimited OCR introduces Reference Sliding Window Attention to eliminate growing memory consumption during long-sequence OCR tasks, enabling efficient transcription of multiple pag…
Lift4D presents a test-time optimization framework that combines temporal consistency from single-view 3D reconstruction with deformable 3D Gaussian Splatting and view-conditioned…
FedOT is a novel framework that enables ownership verification and leakage tracing in federated latent diffusion models by introducing chunked watermarking and latent vector transf…
HAKARI-Bench provides a lightweight benchmark for comparing retrieval methods across multiple configurations and languages, enabling efficient model selection and performance analy…
SingGuard is a policy-adaptive multimodal guardrail system that evaluates safety in real-time conversations by dynamically applying natural-language rules through fast-to-slow reas…
SelfCompact is a scaffolding approach that enables models to autonomously determine optimal compaction timing and methods for managing long agent traces, achieving better performan…
Text-to-image models are enhanced with controlled diversity through semantic browsing capabilities that enable structured navigation of image variations based on meaningful semanti…