New Paradigm: AI Research Summaries
Activity Overview
Episode publication activity over the past year
Episodes
A Summary of Microsoft's 'Make Your LLM Fully Utilize the Context'
28 Apr 2024
Contributed by Lukas
A Summary of Microsoft, Jiaotong University & Peking University's 'Make Your LLM Fully Utilize the Context' Available at: https://arxiv.org/abs/...
A Summary of Microsoft Research's 'Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone'
23 Apr 2024
Contributed by Lukas
A Summary of Microsoft Research's 'Phi-3 Technical Report: A Highly Capable Language Model Locally on Your Phone' Available at: https://arxiv.org/ab...
A Summary of Google's 'Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention'
23 Apr 2024
Contributed by Lukas
A Summary of Google's 'Leave No Context Behind: Efficient Infinite Context Transformers with Infini-attention' Available at: https://arxiv.org/abs/2...
A Summary of Tencent AI Lab's 'Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing'
22 Apr 2024
Contributed by Lukas
A Summary of Tencent AI Lab's 'Toward Self-Improvement of LLMs via Imagination, Searching, and Criticizing' Available at: https://arxiv.org/abs/2404...
A Summary of Microsoft Research's 'VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time'
22 Apr 2024
Contributed by Lukas
A Summary of Microsoft Research's 'VASA-1: Lifelike Audio-Driven Talking Faces Generated in Real Time' Available at: https://arxiv.org/abs/2404.1066...
A Summary of MIT & Harvard's 'Automated Social Science: Language Models as Scientist and Subjects'
21 Apr 2024
Contributed by Lukas
A Summary of MIT & Harvard's 'Automated Social Science: Language Models as Scientist and Subjects' Available at: https://arxiv.org/abs/2404.1179...
A Summary of Microsoft Research's 'The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits'
20 Apr 2024
Contributed by Lukas
This is a summary of the AI research paper: The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits Available at: https://arxiv.org/abs/2402...
A Summary of 'Long-form factuality in large language models' by Google Deepmind and Stanford University
28 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: Long-form factuality in large language models Available at: https://arxiv.org/pdf/2403.18802.pdf And is ...
A Summary of MIT & Sequoia Capital's 'The Unreasonable Ineffectiveness of the Deeper Layers'
27 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: The Unreasonable Ineffectiveness of the Deeper Layers Available at: https://arxiv.org/pdf/2403.17887.pdf T...
A Summary of Microsoft Research and Carnegie Mellon's 'Can large language models explore in-context?'
27 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: Can large language models explore in-context? Available at: https://arxiv.org/pdf/2403.15371.pdf This su...
A Summary of Salesforce AI Research 'AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System'
26 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: AgentLite: A Lightweight Library for Building and Advancing Task-Oriented LLM Agent System Available at: ...
A Summary of 'LLM Agent Operating System'
26 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: LLM Agent Operating System Available at: https://arxiv.org/abs/2403.16971 This summary is AI generated, ...
A Summary of 'Is Cosine-Similarity of Embeddings Really About Similarity?'
23 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: Is Cosine-Similarity of Embeddings Really About Similarity? Available at: https://arxiv.org/pdf/2403.0544...
A Summary of 'Arcee’s MergeKit: A Toolkit for Merging Large Language Models'
23 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: Arcee’s MergeKit: A Toolkit for Merging Large Language Models Available at: https://arxiv.org/pdf/2403.1...
A Summary of 'MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training'
22 Mar 2024
Contributed by Lukas
This is a summary of the AI research paper: MM1: Methods, Analysis & Insights from Multimodal LLM Pre-training Available at: https://arxiv.org/a...