Daily Papers of 2023-07-07

1. Lost in the Middle: How Language Models Use Long Contexts 44 upvotes, #1 of 2023-07-07
2. A Survey on Evaluation of Large Language Models 43 upvotes, #2 of 2023-07-07
3. mPLUG-DocOwl: Modularized Multimodal Large Language Model for Document Understanding 16 upvotes, #3 of 2023-07-07
4. Training Models to Generate, Recognize, and Reframe Unhelpful Thoughts 15 upvotes, #4 of 2023-07-07
5. Focused Transformer: Contrastive Training for Context Scaling 12 upvotes, #5 of 2023-07-07
6. SkipDecode: Autoregressive Skip Decoding with Batching and Caching for Efficient LLM Inference 10 upvotes, #6 of 2023-07-07
7. Whisper-AT: Noise-Robust Automatic Speech Recognizers are Also Strong General Audio Event Taggers 10 upvotes, #6 of 2023-07-07
8. VideoGLUE: Video General Understanding Evaluation of Foundation Models 5 upvotes, #8 of 2023-07-07

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.