Daily Papers of 2024-06-04

1. MMLU-Pro: A More Robust and Challenging Multi-Task Language Understanding Benchmark 35 upvotes, #1 of 2024-06-04
2. Show, Don't Tell: Aligning Language Models with Demonstrated Feedback 22 upvotes, #2 of 2024-06-04
3. Learning Temporally Consistent Video Depth from Video Diffusion Priors 14 upvotes, #3 of 2024-06-04
4. Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning 11 upvotes, #4 of 2024-06-04
5. ZeroSmooth: Training-free Diffuser Adaptation for High Frame Rate Video Generation 9 upvotes, #5 of 2024-06-04
6. μLO: Compute-Efficient Meta-Generalization of Learned Optimizers 8 upvotes, #6 of 2024-06-04

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.