Daily Papers of 2024-01-10

1. MagicVideo-V2: Multi-Stage High-Aesthetic Video Generation 49 upvotes, #1 of 2024-01-10
2. Masked Audio Generation using a Single Non-Autoregressive Transformer 44 upvotes, #2 of 2024-01-10
3. Lightning Attention-2: A Free Lunch for Handling Unlimited Sequence Lengths in Large Language Models 27 upvotes, #3 of 2024-01-10
4. Chain-of-Table: Evolving Tables in the Reasoning Chain for Table Understanding 25 upvotes, #4 of 2024-01-10
5. Jump Cut Smoothing for Talking Heads 20 upvotes, #5 of 2024-01-10
6. Let's Go Shopping (LGS) -- Web-Scale Image-Text Dataset for Visual Concept Understanding 18 upvotes, #6 of 2024-01-10
7. Narrowing the Knowledge Evaluation Gap: Open-Domain Question Answering with Multi-Granularity Answers 13 upvotes, #7 of 2024-01-10
8. FADI-AEC: Fast Score Based Diffusion Model Guided by Far-end Signal for Acoustic Echo Cancellation 8 upvotes, #8 of 2024-01-10

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.