Daily Papers of 2025-12-15

  1. EgoX: Egocentric Video Generation from a Single Exocentric Video 106 upvotes, #1 of 2025-12-15
  2. DentalGPT: Incentivizing Multimodal Complex Reasoning in Dentistry 41 upvotes, #2 of 2025-12-15
  3. SVG-T2I: Scaling Up Text-to-Image Latent Diffusion Model Without Variational Autoencoder 35 upvotes, #3 of 2025-12-15
  4. V-RGBX: Video Editing with Accurate Controls over Intrinsic Properties 29 upvotes, #4 of 2025-12-15
  5. PersonaLive! Expressive Portrait Image Animation for Live Streaming 28 upvotes, #5 of 2025-12-15
  6. Sliding Window Attention Adaptation 17 upvotes, #6 of 2025-12-15
  7. Exploring MLLM-Diffusion Information Transfer with MetaCanvas 12 upvotes, #7 of 2025-12-15
  8. Sharp Monocular View Synthesis in Less Than a Second 11 upvotes, #8 of 2025-12-15
  9. MeshSplatting: Differentiable Rendering with Opaque Meshes 10 upvotes, #9 of 2025-12-15
  10. Structure From Tracking: Distilling Structure-Preserving Motion for Video Generation 9 upvotes, #10 of 2025-12-15
  11. LEO-RobotAgent: A General-purpose Robotic Agent for Language-driven Embodied Operator 6 upvotes, #11 of 2025-12-15
  12. Fairy2i: Training Complex LLMs from Real LLMs with All Parameters in {pm 1, pm i} 5 upvotes, #12 of 2025-12-15
  13. Scaling Behavior of Discrete Diffusion Language Models 5 upvotes, #12 of 2025-12-15
  14. Fast-FoundationStereo: Real-Time Zero-Shot Stereo Matching 4 upvotes, #14 of 2025-12-15
  15. Causal Judge Evaluation: Calibrated Surrogate Metrics for LLM Systems 4 upvotes, #14 of 2025-12-15
  16. Particulate: Feed-Forward 3D Object Articulation 4 upvotes, #14 of 2025-12-15
  17. Task adaptation of Vision-Language-Action model: 1st Place Solution for the 2025 BEHAVIOR Challenge 3 upvotes, #17 of 2025-12-15
  18. CLINIC: Evaluating Multilingual Trustworthiness in Language Models for Healthcare 3 upvotes, #17 of 2025-12-15
  19. Interpretable Embeddings with Sparse Autoencoders: A Data Analysis Toolkit 2 upvotes, #19 of 2025-12-15
  20. CheXmask-U: Quantifying uncertainty in landmark-based anatomical segmentation for X-ray images 2 upvotes, #19 of 2025-12-15
  21. The N-Body Problem: Parallel Execution from Single-Person Egocentric Video 2 upvotes, #19 of 2025-12-15

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.