Safe Few-Step Generation via Velocity Editing
VESFlow is a training-free safety method for flow matching-based text-to-image generation that edits velocity fields to ensure safe output while maintaining prompt integrity.
Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
VESFlow is a training-free safety method for flow matching-based text-to-image generation that edits velocity fields to ensure safe output while maintaining prompt integrity.
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…
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…
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…
True artificial agency requires internalized structures for goals, identity, decision-making, self-regulation, and learning, distinguishing autonomous systems from task-specific on…