Daily Papers of 2024-06-06

1. Parrot: Multilingual Visual Instruction Tuning 30 upvotes, #1 of 2024-06-06
2. Block Transformer: Global-to-Local Language Modeling for Fast Inference 30 upvotes, #1 of 2024-06-06
3. Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration 26 upvotes, #3 of 2024-06-06
4. Ouroboros3D: Image-to-3D Generation via 3D-aware Recursive Diffusion 15 upvotes, #4 of 2024-06-06
5. Audio Mamba: Bidirectional State Space Model for Audio Representation Learning 12 upvotes, #5 of 2024-06-06
6. PosterLLaVa: Constructing a Unified Multi-modal Layout Generator with LLM 11 upvotes, #6 of 2024-06-06
7. LiveSpeech: Low-Latency Zero-shot Text-to-Speech via Autoregressive Modeling of Audio Discrete Codes 11 upvotes, #6 of 2024-06-06
8. Scaling Laws for Reward Model Overoptimization in Direct Alignment Algorithms 9 upvotes, #8 of 2024-06-06
9. Searching Priors Makes Text-to-Video Synthesis Better 9 upvotes, #8 of 2024-06-06
10. Item-Language Model for Conversational Recommendation 6 upvotes, #10 of 2024-06-06
11. Xmodel-LM Technical Report 6 upvotes, #10 of 2024-06-06
12. PLaD: Preference-based Large Language Model Distillation with Pseudo-Preference Pairs 4 upvotes, #12 of 2024-06-06

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.