3 months agoHugging Face Daily PapersPoseLess: Depth-Free Vision-to-Joint Control via Direct Image Mapping with VLM
3 months agoHugging Face Daily PapersQuantizing Large Language Models for Code Generation: A Differentiated Replication
3 months agoHugging Face Daily PapersAn Empirical Study on Eliciting and Improving R1-like Reasoning Models
3 months agoHugging Face Daily PapersDistiLLM-2: A Contrastive Approach Boosts the Distillation of LLMs
3 months agoHugging Face Daily PapersVideoPainter: Any-length Video Inpainting and Editing with Plug-and-Play Context Control
3 months agoAI News CN (Telegram)智元机器人发布首个通用具身基座大模型 3月10日，智元正式发布首个通用具身基座模型智元启元大模型 (Genie Operator-1)。该模型提出了 Vision-Language-Latent-A...
3 months agoHugging Face Daily PapersEasyControl: Adding Efficient and Flexible Control for Diffusion Transformer
3 months agoHugging Face Daily PapersAnyAnomaly: Zero-Shot Customizable Video Anomaly Detection with LVLM
3 months agoHugging Face Daily PapersTaking Notes Brings Focus? Towards Multi-Turn Multimodal Dialogue Learning
3 months agoHugging Face Daily PapersPLADIS: Pushing the Limits of Attention in Diffusion Models at Inference Time by Leveraging Sparsity
3 months agoAI News CN (Telegram)🖼 🚀 Crusoe“星际之门”项目：34亿美元打造AI数据中心，引领美国偏远地区经济复兴 Crusoe公司正在美国得克萨斯州阿比林市郊外建设一个价值34亿美元的数据...
3 months agoAI News CN (Telegram)🖼 💰 AI模型“蒸馏”技术降低成本，挑战大模型厂商 人工智能模型的开发成本正在迅速下降，这主要归功于“模型蒸馏”技术。该技术允许小型“学生”模型模仿...
3 months agoHugging Face Daily PapersTrajectoryCrafter: Redirecting Camera Trajectory for Monocular Videos via Diffusion Models
3 months agoHugging Face Daily PapersA Data-Centric Revisit of Pre-Trained Vision Models for Robot Learning
3 months agoHugging Face Daily PapersCineBrain: A Large-Scale Multi-Modal Brain Dataset During Naturalistic Audiovisual Narrative Processing