??Top ML Papers of the Week

The top ML Papers of the Week (Mar 20 - Mar 26):

1). Sparks of AGI?- a comprehensive investigation of an early version of GPT-4 when it was still in active development by OpenAI. (paper | tweet )

2). Reflexion?- proposes an agent with dynamic memory and self-reflection capabilities to enhance its existing reasoning trace and task-specific action choice abilities. (paper | tweet )

3). GPT-4 for Medical Challenge Problems?- shows that GPT-4 exceeds the passing score on USMLE by over 20 points and outperforms GPT-3.5 as well as models specifically fine-tuned on medical knowledge (Med-PaLM, a prompt-tuned version of Flan-PaLM 540B). (paper | tweet )

4). GPTs are GPTs?- investigates the potential implications of GPT models and related systems on the US labor market. (paper | tweet )

5). CoLT5?- a long-input Transformer model that employs conditional computation, devoting more resources to important tokens in both feedforward and attention layers. (paper | tweet )

6). Artificial muses?- compares human-generated ideas with those generated by generative AI chatbots like ChatGPT and YouChat; reports that 9.4% of humans were more creative than GPT-4 and that GAIs are valuable assistants in the creative process. (paper | tweet )

7). Analysis of GPT-3 and GPT-3.5?- a comprehensive capability analysis of GPT series models; evaluates performance on 9 natural language understanding tasks using 21 datasets. (paper | tweet )

8). Context-faithful Prompting for LLMs?- presents a prompting technique that aims to improve LLMs' faithfulness using strategies such as opinion-based prompts and counterfactual demonstrations. (paper | tweet )

9). Text2Room?- a method for extracting room-scale textured 3D meshes from 2D text-to-image models. (paper | tweet )

10). PanGu-Σ?- a trillion parameter language model with sparse heterogeneous computing. (paper | tweet )