Daily Papers of 2024-03-25

1. Can large language models explore in-context? 29 upvotes, #1 of 2024-03-25
2. LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement 20 upvotes, #2 of 2024-03-25
3. InternVideo2: Scaling Video Foundation Models for Multimodal Video Understanding 14 upvotes, #3 of 2024-03-25
4. Champ: Controllable and Consistent Human Image Animation with 3D Parametric Guidance 13 upvotes, #4 of 2024-03-25
5. ThemeStation: Generating Theme-Aware 3D Assets from Few Exemplars 11 upvotes, #5 of 2024-03-25
6. SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time series 10 upvotes, #6 of 2024-03-25
7. VidLA: Video-Language Alignment at Scale 9 upvotes, #7 of 2024-03-25
8. DragAPart: Learning a Part-Level Motion Prior for Articulated Objects 9 upvotes, #7 of 2024-03-25
9. StreamingT2V: Consistent, Dynamic, and Extendable Long Video Generation from Text 8 upvotes, #9 of 2024-03-25
10. FollowIR: Evaluating and Teaching Information Retrieval Models to Follow Instructions 8 upvotes, #9 of 2024-03-25
11. AllHands: Ask Me Anything on Large-scale Verbatim Feedback via Large Language Models 6 upvotes, #11 of 2024-03-25
12. LATTE3D: Large-scale Amortized Text-To-Enhanced3D Synthesis 5 upvotes, #12 of 2024-03-25
13. Compiler generated feedback for Large Language Models 4 upvotes, #13 of 2024-03-25

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.