Forwarded from AI DeepMind (Farzad 🦅)
در هفته گذشته چه مقالات و مدلهای متن بازی در #هوش_مصنوعی و #یادگیری_ماشین منتشر شد:
◾️DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
◾️ Imagen 3
◾️ The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
◾️Diffusion Guided Language Modeling
◾️Layerwise Recurrent Router for Mixture-of-Experts
◾️LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
◾️Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
◾️ BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
◾️ Gemma Scope
◾️Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
◾️Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
◾️I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm
◾️Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
RAG
◾️HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction
◾️OpenResearcher: Unleashing AI for Accelerated Scientific Research
MLLM
◾️VITA: Towards Open-Source Interactive Omni Multimodal LLM
◾️mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
VLM
◾️Mitigating Object Hallucination via Data Augmented Contrastive Tuning
◾️Towards flexible perception with visual memory
◾️VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
AI Gen
◾️VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
◾️ Generative Photomontage
◾️Heavy Labels Out! Dataset Distillation with Label Space Lightening
◾️ 3D Gaussian Editing with A Single Image
◾️ CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
◾️ ControlNeXt: Powerful and Efficient Control for Image and Video Generation
Others
◾️ Body Transformer: Leveraging Robot Embodiment for Policy Learning
◾️ Machine Psychology
◾️ Med42-v2: A Suite of Clinical LLMs
#مقاله #ایده_جذاب #الگوریتمها #مدل_متن_باز
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
🔸 @AI_Person
◾️DeepSeek-Prover-V1.5: Harnessing Proof Assistant Feedback for Reinforcement Learning and Monte-Carlo Tree Search
◾️ Imagen 3
◾️ The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery
◾️Diffusion Guided Language Modeling
◾️Layerwise Recurrent Router for Mixture-of-Experts
◾️LongWriter: Unleashing 10,000+ Word Generation from Long Context LLMs
◾️Training Language Models on the Knowledge Graph: Insights on Hallucinations and Their Detectability
◾️ BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts
◾️ Gemma Scope
◾️Diversity Empowers Intelligence: Integrating Expertise of Software Engineering Agents
◾️Mutual Reasoning Makes Smaller LLMs Stronger Problem-Solvers
◾️I-SHEEP: Self-Alignment of LLM from Scratch through an Iterative Self-Enhancement Paradigm
◾️Does Liking Yellow Imply Driving a School Bus? Semantic Leakage in Language Models
RAG
◾️HybridRAG: Integrating Knowledge Graphs and Vector Retrieval Augmented Generation for Efficient Information Extraction
◾️OpenResearcher: Unleashing AI for Accelerated Scientific Research
MLLM
◾️VITA: Towards Open-Source Interactive Omni Multimodal LLM
◾️mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models
VLM
◾️Mitigating Object Hallucination via Data Augmented Contrastive Tuning
◾️Towards flexible perception with visual memory
◾️VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
AI Gen
◾️VisualAgentBench: Towards Large Multimodal Models as Visual Foundation Agents
◾️ Generative Photomontage
◾️Heavy Labels Out! Dataset Distillation with Label Space Lightening
◾️ 3D Gaussian Editing with A Single Image
◾️ CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer
◾️ ControlNeXt: Powerful and Efficient Control for Image and Video Generation
Others
◾️ Body Transformer: Leveraging Robot Embodiment for Policy Learning
◾️ Machine Psychology
◾️ Med42-v2: A Suite of Clinical LLMs
#مقاله #ایده_جذاب #الگوریتمها #مدل_متن_باز
🔸 مطالب بیشتر 👇👇
✅ @AI_DeepMind
🔸 @AI_Person