Investigating Answerability of LLMs for Long-Form Question AnsweringDownload PDF#Large Language Models#QA#Paper#Salesforce·arxiv.org·Sep 25, 2023Investigating Answerability of LLMs for Long-Form Question Answering
100x Efficiency: MIT’s Machine-Learning System Based on Light Could Yield More Powerful Large Language ModelsDOI: 10.1038/s41566-023-01233-w#Machine Learning#Paper#Photonics·scitechdaily.com·Sep 25, 2023100x Efficiency: MIT’s Machine-Learning System Based on Light Could Yield More Powerful Large Language Models
End-to-end Autonomous Driving: Challenges and Frontiers#Paper#AVs·arxiv.org·Sep 23, 2023End-to-end Autonomous Driving: Challenges and Frontiers
Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual TasksPDF#Large Language Models#Performance#Paper#PDF·arxiv.org·Jul 31, 2023Reasoning or Reciting? Exploring the Capabilities and Limitations of Language Models Through Counterfactual Tasks
Llama 2: Open Foundation and Fine-Tuned Chat ModelsPDF#LLaMa#Large Language Models#Meta#Paper#PDF·arxiv.org·Jul 28, 2023Llama 2: Open Foundation and Fine-Tuned Chat Models
How is ChatGPT's behavior changing over time?#ChatGPT#Paper#PDF·arxiv.org·Jul 25, 2023How is ChatGPT's behavior changing over time?
Language models and linguistic theories beyond words#Linguistics#Paper#PDF#Large Language Models·nature.com·Jul 24, 2023Language models and linguistic theories beyond words
Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning | Meta AI ResearchDownload the Paper#Meta#Multimodal#Paper#PDF·ai.meta.com·Jul 14, 2023Scaling Autoregressive Multi-Modal Models: Pretraining and Instruction Tuning | Meta AI Research
Large language models encode clinical knowledge#Large Language Models#Medical#Google#Paper#PDF·nature.com·Jul 14, 2023Large language models encode clinical knowledge
A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT#Prompt Engineering#ChatGPT#Paper#PDF·arxiv.org·Jul 13, 2023A Prompt Pattern Catalog to Enhance Prompt Engineering with ChatGPT
The Jiminy Advisor: Moral Agreements among Stakeholders Based on Norms and Argumentation | Journal of Artificial Intelligence Research#Preferences#Reasoning#Stakeholders#Paper#PDF·jair.org·Jul 12, 2023The Jiminy Advisor: Moral Agreements among Stakeholders Based on Norms and Argumentation | Journal of Artificial Intelligence Research
OpenELM/OpenELM_Paper.pdf at paper · CarperAI/OpenELM · GitHub#Large Language Models#Algorithms#Feedback#Paper#PDF·github.com·Jul 11, 2023OpenELM/OpenELM_Paper.pdf at paper · CarperAI/OpenELM · GitHub
Phase transition in Random Circuit SamplingPDF#Quantum Computing#Google#Paper#PDF·arxiv.org·Jul 5, 2023Phase transition in Random Circuit Sampling
Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis#Text-to-Image#Benchmark#Preferences#Prompt Engineering#Paper#PDF·arxiv.org·Jul 5, 2023Human Preference Score v2: A Solid Benchmark for Evaluating Human Preferences of Text-to-Image Synthesis
ChatGPT is not all you need. A State of the Art Review of large Generative AI models#Text-to-Image#Paper#PDF#Generative Models#Taxonomy·arxiv.org·Jul 5, 2023ChatGPT is not all you need. A State of the Art Review of large Generative AI models
Perceptions and Realities of Text-to-Image Generation#Text-to-Image#Paper#PDF#Survey·arxiv.org·Jul 5, 2023Perceptions and Realities of Text-to-Image Generation
Large-scale Text-to-Image Generation Models for Visual Artists' Creative WorksPDF#Text-to-Image#Large Language Models#Generative Models#Paper#PDF·arxiv.org·Jul 5, 2023Large-scale Text-to-Image Generation Models for Visual Artists' Creative Works
Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias#Large Language Models#Training#Machine Learning#Paper#PDF·arxiv.org·Jul 4, 2023Large Language Model as Attributed Training Data Generator: A Tale of Diversity and Bias
Pushing the Limits of Machine Design: Automated CPU Design with AI#Design#Automation#Paper#PDF·arxiv.org·Jul 1, 2023Pushing the Limits of Machine Design: Automated CPU Design with AI
Towards Measuring the Representation of Subjective Global Opinions in Language Models#Large Language Models#Machine Learning#Opinion#Paper#PDF·arxiv.org·Jun 30, 2023Towards Measuring the Representation of Subjective Global Opinions in Language Models
Wef presidio recommendations on responsible generative ai 2023#Generative Models#Responsible AI#Recommendations#World Economic Forum#Paper#PDF#Standard·www3.weforum.org·Jun 22, 2023Wef presidio recommendations on responsible generative ai 2023
Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations#Large Language Models#Diffusion#GPU#Paper#PDF·arxiv.org·Jun 22, 2023Speed Is All You Need: On-Device Acceleration of Large Diffusion Models via GPU-Aware Optimizations
Opportunities and Risks of LLMs for Scalable Deliberation with Polis#Large Language Models#Democracy#Paper#PDF·arxiv.org·Jun 22, 2023Opportunities and Risks of LLMs for Scalable Deliberation with Polis
ZeRO++: Extremely Efficient Collective Communication for Giant Model Training - Microsoft Research#Large Language Models#Training#Microsoft#Paper#PDF·microsoft.com·Jun 22, 2023ZeRO++: Extremely Efficient Collective Communication for Giant Model Training - Microsoft Research
MIME: Human-Aware 3D Scene Generation#Computer Vision#3D#Paper#PDF·arxiv.org·Jun 22, 2023MIME: Human-Aware 3D Scene Generation
Quantum neural network cost function concentration dependency on the parametrization expressivity#Quantum Computing#Machine Learning#Paper#PDF#Neural Networks·nature.com·Jun 22, 2023Quantum neural network cost function concentration dependency on the parametrization expressivity
ChemCrow: Augmenting large-language models with chemistry tools#Large Language Models#Chemistry#Paper#PDF·arxiv.org·Jun 22, 2023ChemCrow: Augmenting large-language models with chemistry tools
Microsoft at CVPR 2023: Pushing the boundaries of computer vision - Microsoft Research#Computer Vision#Microsoft#Paper#Conference·microsoft.com·Jun 21, 2023Microsoft at CVPR 2023: Pushing the boundaries of computer vision - Microsoft Research