首页 > 开发 > Hugging Face Hugging Face 共 5344 条资讯 Joint and Cross-Modal Video-Audio Generation and Editing: A Unified Formulation and Design Taxonomy Explore Broadly, Reason Sharply: Push Small Models toward the Frontier via Sampling Devils in Question Relay: Source-Conditioned Relay Steering to Mitigate Hallucinations in Audio-visual Large Language Models Controlled Decoding Attacks on Black-Box LLMs Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs Pretrain Once, Route Anywhere: Towards a Foundation Model for LLM Routing FlexRouter: Learning Complementary Model Sets for Flexible LLM Routing Memorizon: Training World Models Beyond Their Context Window DexPolicy: Scheduled Exploration for Trajectory-Guided Dexterous Manipulation Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces PixelDense: Dense Prediction as Representation Alignment for Pixel Diffusion Benchmarking and Enhancing Skill-Level Memory for Partially Observable Robotic Manipulation Align Then Reason: A Multimodal Lip-Sync Judge for Dubbing Better Supervision Is Nearby: Neighborhood On-Policy Self-Distillation Smaller Models, Better Rejects: Preference Distillation Scaling Personalized Image Generation with Reasoning and Reflection Pay for the Fault, Not the Flow: Label-Free In-Flow Multi-Agent Workflow Optimization OmniSeek: Native Tool Integration for Multi-turn Audio-Visual Reasoning World Observer: Joint Actor-Observer Generation for Persistent World Modeling « 上一页12345…268下一页 » 相关分类 Hugging Face 51CTO ADGuider Android Police Android Weekly Update Android开发技术周报 Blow Studio Blur Studio CSDN CSDN博客 CSDN资讯 CSS-Tricks DEV Community