Daily Papers of 2024-09-30

1. Emu3: Next-Token Prediction is All You Need 75 upvotes, #1 of 2024-09-30
2. MIO: A Foundation Model on Multimodal Tokens 46 upvotes, #2 of 2024-09-30
3. A Survey on the Honesty of Large Language Models 28 upvotes, #3 of 2024-09-30
4. VPTQ: Extreme Low-bit Vector Post-Training Quantization for Large Language Models 22 upvotes, #4 of 2024-09-30
5. MinerU: An Open-Source Solution for Precise Document Content Extraction 22 upvotes, #4 of 2024-09-30
6. PhysGen: Rigid-Body Physics-Grounded Image-to-Video Generation 21 upvotes, #6 of 2024-09-30
7. Modulated Intervention Preference Optimization (MIPO): Keep the Easy, Refine the Difficult 16 upvotes, #7 of 2024-09-30
8. HDFlow: Enhancing LLM Complex Problem-Solving with Hybrid Thinking and Dynamic Workflows 8 upvotes, #8 of 2024-09-30
9. LML: Language Model Learning a Dataset for Data-Augmented Prediction 8 upvotes, #8 of 2024-09-30
10. MSI-Agent: Incorporating Multi-Scale Insight into Embodied Agents for Superior Planning and Decision-Making 7 upvotes, #10 of 2024-09-30

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.