Daily Papers of 2023-09-12
- Textbooks Are All You Need II: phi-1.5 technical report 92 upvotes, #1 of 2023-09-12
- NExT-GPT: Any-to-Any Multimodal LLM 79 upvotes, #2 of 2023-09-12
- MADLAD-400: A Multilingual And Document-Level Large Audited Dataset 26 upvotes, #3 of 2023-09-12
- Neurons in Large Language Models: Dead, N-gram, Positional 18 upvotes, #4 of 2023-09-12
- When Less is More: Investigating Data Pruning for Pretraining LLMs at Scale 17 upvotes, #5 of 2023-09-12
- Optimize Weight Rounding via Signed Gradient Descent for the Quantization of LLMs 16 upvotes, #6 of 2023-09-12
- Dynamic Mesh-Aware Radiance Fields 7 upvotes, #7 of 2023-09-12
- FIAT: Fusing learning paradigms with Instruction-Accelerated Tuning 6 upvotes, #8 of 2023-09-12
Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.