Daily Papers of 2024-04-26

1. Layer Skip: Enabling Early Exit Inference and Self-Speculative Decoding 47 upvotes, #1 of 2024-04-26
2. How Far Are We to GPT-4V? Closing the Gap to Commercial Multimodal Models with Open-Source Suites 47 upvotes, #1 of 2024-04-26
3. Make Your LLM Fully Utilize the Context 45 upvotes, #3 of 2024-04-26
4. Interactive3D: Create What You Want by Interactive 3D Generation 17 upvotes, #4 of 2024-04-26
5. Tele-FLM Technical Report 17 upvotes, #4 of 2024-04-26
6. ConsistentID: Portrait Generation with Multimodal Fine-Grained Identity Preserving 16 upvotes, #6 of 2024-04-26
7. Revisiting Text-to-Image Evaluation with Gecko: On Metrics, Prompts, and Human Ratings 15 upvotes, #7 of 2024-04-26
8. List Items One by One: A New Data Source and Learning Paradigm for Multimodal LLMs 14 upvotes, #8 of 2024-04-26
9. NeRF-XL: Scaling NeRFs with Multiple GPUs 11 upvotes, #9 of 2024-04-26
10. SEED-Bench-2-Plus: Benchmarking Multimodal Large Language Models with Text-Rich Visual Comprehension 7 upvotes, #10 of 2024-04-26

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.