Daily Papers of 2024-10-24

1. MIA-DPO: Multi-Image Augmented Direct Preference Optimization For Large Vision-Language Models 34 upvotes, #1 of 2024-10-24
2. LongVU: Spatiotemporal Adaptive Compression for Long Video-Language Understanding 18 upvotes, #2 of 2024-10-24
3. WorldSimBench: Towards Video Generation Models as World Simulators 16 upvotes, #3 of 2024-10-24
4. Scalable Ranked Preference Optimization for Text-to-Image Generation 14 upvotes, #4 of 2024-10-24
5. Scaling Diffusion Language Models via Adaptation from Autoregressive Models 13 upvotes, #5 of 2024-10-24
6. DynamicCity: Large-Scale LiDAR Generation from Dynamic Scenes 12 upvotes, #6 of 2024-10-24
7. M-RewardBench: Evaluating Reward Models in Multilingual Settings 10 upvotes, #7 of 2024-10-24
8. Lightweight Neural App Control 8 upvotes, #8 of 2024-10-24
9. MedINST: Meta Dataset of Biomedical Instructions 6 upvotes, #9 of 2024-10-24
10. ARKit LabelMaker: A New Scale for Indoor 3D Scene Understanding 6 upvotes, #9 of 2024-10-24
11. TP-Eval: Tap Multimodal LLMs' Potential in Evaluation by Customizing Prompts 6 upvotes, #9 of 2024-10-24
12. Steering Your Generalists: Improving Robotic Foundation Models via Value Guidance 1 upvotes, #12 of 2024-10-24
13. LVSM: A Large View Synthesis Model with Minimal 3D Inductive Bias 1 upvotes, #12 of 2024-10-24

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.