Daily Papers of 2023-12-13

  1. FreeInit: Bridging Initialization Gap in Video Diffusion Models 26 upvotes, #1 of 2023-12-13
  2. DiffMorpher: Unleashing the Capability of Diffusion Models for Image Morphing 23 upvotes, #2 of 2023-12-13
  3. VILA: On Pre-training for Visual Language Models 21 upvotes, #3 of 2023-12-13
  4. FreeControl: Training-Free Spatial Control of Any Text-to-Image Diffusion Model with Any Condition 17 upvotes, #4 of 2023-12-13
  5. Alignment for Honesty 13 upvotes, #5 of 2023-12-13
  6. Rethinking Compression: Reduced Order Modelling of Latent Features in Large Language Models 13 upvotes, #5 of 2023-12-13
  7. Steering Llama 2 via Contrastive Activation Addition 12 upvotes, #7 of 2023-12-13
  8. Honeybee: Locality-enhanced Projector for Multimodal LLM 11 upvotes, #8 of 2023-12-13
  9. CCM: Adding Conditional Controls to Text-to-Image Consistency Models 11 upvotes, #8 of 2023-12-13
  10. COLMAP-Free 3D Gaussian Splatting 11 upvotes, #8 of 2023-12-13
  11. Interfacing Foundation Models' Embeddings 10 upvotes, #11 of 2023-12-13
  12. Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations 9 upvotes, #12 of 2023-12-13
  13. How Well Does GPT-4V(ision) Adapt to Distribution Shifts? A Preliminary Investigation 8 upvotes, #13 of 2023-12-13
  14. PEEKABOO: Interactive Video Generation via Masked-Diffusion 8 upvotes, #13 of 2023-12-13
  15. Fast Training of Diffusion Transformer with Extreme Masking for 3D Point Clouds Generation 7 upvotes, #15 of 2023-12-13
  16. "I Want It That Way": Enabling Interactive Decision Support Using Large Language Models and Constraint Programming 6 upvotes, #16 of 2023-12-13

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.