Daily Papers of 2024-04-01

1. Jamba: A Hybrid Transformer-Mamba Language Model 86 upvotes, #1 of 2024-04-01
2. Gecko: Versatile Text Embeddings Distilled from Large Language Models 38 upvotes, #2 of 2024-04-01
3. Transformer-Lite: High-efficiency Deployment of Large Language Models on Mobile Phone GPUs 33 upvotes, #3 of 2024-04-01
4. ReALM: Reference Resolution As Language Modeling 18 upvotes, #4 of 2024-04-01
5. InstantSplat: Unbounded Sparse-view Pose-free Gaussian Splatting in 40 Seconds 14 upvotes, #5 of 2024-04-01
6. Unsolvable Problem Detection: Evaluating Trustworthiness of Vision Language Models 14 upvotes, #5 of 2024-04-01
7. Localizing Paragraph Memorization in Language Models 13 upvotes, #7 of 2024-04-01
8. DiJiang: Efficient Large Language Models through Compact Kernelization 9 upvotes, #8 of 2024-04-01
9. MambaMixer: Efficient Selective State Space Models with Dual Token and Channel Selection 8 upvotes, #9 of 2024-04-01
10. Snap-it, Tap-it, Splat-it: Tactile-Informed 3D Gaussian Splatting for Reconstructing Challenging Surfaces 8 upvotes, #9 of 2024-04-01

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.