Papers, modelos e datasets em alta no Hugging Face, além do blog oficial — com leitura editorial em português.
Dataset com 100 mil – 1 milhão de exemplos — 4.7 mil downloads no Hugging Face. Open-SWE-Traces: Advancing Distillation for Software Engineering Agents Data Overview Open-SWE-Traces is an agentic instruction tuning dataset designe…
S-Agent is a spatial reasoning framework that enhances visual language models with temporal memory and hierarchical spatial tools to enable continuous 3D world understanding from m…
A unified controllable video world model generates videos from a single image while preserving scene structure and transferring to target weather states through specialized paramet…
LLM agents frequently select higher-privilege tools unnecessarily, and while safety alignment doesn't ensure least-privilege choices, a post-training defense can reduce excessive p…
DO-ALL is a test-time adaptation framework that uses dataset distillation to create synthetic anchors for stable long-term model performance without retaining source data.
A fast, training-free framework generates text-driven 3D visual illusions by decoupling generation into cross-space dual-branch denoising and view-conditioned texture synthesis for…
Multi-LCB addresses the limitation of LiveCodeBench by providing a multi-language benchmark for evaluating LLMs across twelve programming languages while maintaining contamination…
Reinforcement learning approaches for improving LLM reasoning capabilities are enhanced by a Bayesian Manifold Curriculum framework that structures problem sampling based on task m…
Uniform 4-bit training with RHT-based quantization outperforms E2M1-based methods by eliminating shrinkage bias and improving training stability across large language model archite…
Egocentric human video can effectively replace teleoperated robot trajectories for embodied model pretraining, achieving better performance with reduced data collection costs.