Daily Papers of 2025-06-09

  1. Will It Still Be True Tomorrow? Multilingual Evergreen Question Classification to Improve Trustworthy QA 127 upvotes, #1 of 2025-06-09
  2. PartCrafter: Structured 3D Mesh Generation via Compositional Latent Diffusion Transformers 61 upvotes, #2 of 2025-06-09
  3. Truth in the Few: High-Value Data Selection for Efficient Multi-Modal Reasoning 36 upvotes, #3 of 2025-06-09
  4. Leveraging Self-Attention for Input-Dependent Soft Prompting in LLMs 33 upvotes, #4 of 2025-06-09
  5. MORSE-500: A Programmatically Controllable Video Benchmark to Stress-Test Multimodal Reasoning 32 upvotes, #5 of 2025-06-09
  6. FusionAudio-1.2M: Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion 29 upvotes, #6 of 2025-06-09
  7. Sentinel: SOTA model to protect against prompt injections 22 upvotes, #7 of 2025-06-09
  8. Is Extending Modality The Right Path Towards Omni-Modality? 21 upvotes, #8 of 2025-06-09
  9. STARFlow: Scaling Latent Normalizing Flows for High-resolution Image Synthesis 19 upvotes, #9 of 2025-06-09
  10. Medical World Model: Generative Simulation of Tumor Evolution for Treatment Planning 16 upvotes, #10 of 2025-06-09
  11. Audio-Aware Large Language Models as Judges for Speaking Styles 14 upvotes, #11 of 2025-06-09
  12. Peer-Ranked Precision: Creating a Foundational Dataset for Fine-Tuning Vision Models from DataSeeds' Annotated Imagery 9 upvotes, #12 of 2025-06-09
  13. CodeContests+: High-Quality Test Case Generation for Competitive Programming 8 upvotes, #13 of 2025-06-09
  14. MIRIAD: Augmenting LLMs with millions of medical query-response pairs 8 upvotes, #13 of 2025-06-09
  15. Bridging Perspectives: A Survey on Cross-view Collaborative Intelligence with Egocentric-Exocentric Vision 8 upvotes, #13 of 2025-06-09
  16. Splatting Physical Scenes: End-to-End Real-to-Sim from Imperfect Robot Data 7 upvotes, #16 of 2025-06-09
  17. AssetOpsBench: Benchmarking AI Agents for Task Automation in Industrial Asset Operations and Maintenance 5 upvotes, #17 of 2025-06-09
  18. HASHIRU: Hierarchical Agent System for Hybrid Intelligent Resource Utilization 5 upvotes, #17 of 2025-06-09
  19. 3DFlowAction: Learning Cross-Embodiment Manipulation from 3D Flow World Model 5 upvotes, #17 of 2025-06-09
  20. Prefix Grouper: Efficient GRPO Training through Shared-Prefix Forward 4 upvotes, #20 of 2025-06-09
  21. When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding 4 upvotes, #20 of 2025-06-09
  22. GuideX: Guided Synthetic Data Generation for Zero-Shot Information Extraction 3 upvotes, #22 of 2025-06-09
  23. When Models Know More Than They Can Explain: Quantifying Knowledge Transfer in Human-AI Collaboration 3 upvotes, #22 of 2025-06-09
  24. Sparsified State-Space Models are Efficient Highway Networks 2 upvotes, #24 of 2025-06-09

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.