Demystifying GPT Self-Repair for Code Generation
Test Information Space
LLM-Blender: Ensembling Large Language Models with Pairwise Ranking and Generative Fusion
PDF
AI and the transformation of social science research
Evaluating the Social Impact of Generative AI Systems in Systems and Society
Tanaka, H., Gallo, G., Gluyas, J., Kamoshida, O., Lo Presti, D., Shimizu, T., ... & Yokota, Y. First Navigation With Wireless Muometric Navigation System (MuWNS) in Indoor and Underground Environments. Available at SSRN 4180806.
FinGPT: Open-Source Financial Large Language Models
Distinguishing academic science writing from humans or ChatGPT with over 99% accuracy using off-the-shelf machine learning tools
The Curse of Recursion: Training on Generated Data Makes Models Forget
A transformer-based representation-learning model with unified processing of multimodal input for clinical diagnostics
LLaVA-Med: Training a Large Language-and-Vision Assistant for Biomedicine in One Day
FrugalGPT: How to Use Large Language Models While Reducing Cost and Improving Performance
DNA-GPT: Divergent N-Gram Analysis for Training-Free Detection of GPT-Generated Text
Trends in AI — June 2023 // With Apple's Vision Pro, AI Doomers, Optimists and AI Regulation, TII's.
Recognize Anything: A Strong Image Tagging Model
🥇Top ML Papers of the Week
Gong, Y., Rouditchenko, A., Liu, A. H., Harwath, D., Karlinsky, L., Kuehne, H., & Glass, J. (2022). Contrastive audio-visual masked autoencoder. arXiv preprint arXiv:2210.07839.
Advances in apparent conceptual physics reasoning in GPT-4
Cross-Lingual Supervision improves Large Language Models Pre-training
Deliberate then Generate: Enhanced Prompting Framework for Text Generation
Developing a platform for linear mechanical quantum computing
Simple and Controllable Music Generation
Entailment as Robust Self-Learner
Imagen Editor and EditBench: Advancing and evaluating text-guided image inpainting
Moral Machine or Tyranny of the Majority?
PDF
Researchers unveil first Chat-GPT-designed robot
Distinguishing academic science writing from humans or ChatGPT with over 99% accuracy using off-the-shelf machine learning tools
LEACE: Perfect linear concept erasure in closed form
Explainable Goal-driven Agents and Robots - A Comprehensive Review | ACM Computing Surveys
CAPE: Camera View Position Embedding for Multi-View 3D Object Detection
governance/keras_api_design_guidelines.md at master · keras-team/governance · GitHub