Daily Papers of 2024-05-31

  1. Jina CLIP: Your CLIP Model Is Also Your Text Retriever 26 upvotes, #1 of 2024-05-31
  2. Similarity is Not All You Need: Endowing Retrieval Augmented Generation with Multi Layered Thoughts 22 upvotes, #2 of 2024-05-31
  3. Xwin-LM: Strong and Scalable Alignment Practice for LLMs 16 upvotes, #3 of 2024-05-31
  4. MotionLLM: Understanding Human Behaviors from Human Motions and Videos 16 upvotes, #3 of 2024-05-31
  5. MOFA-Video: Controllable Image Animation via Generative Motion Field Adaptions in Frozen Image-to-Video Diffusion Model 9 upvotes, #5 of 2024-05-31
  6. DITTO-2: Distilled Diffusion Inference-Time T-Optimization for Music Generation 8 upvotes, #6 of 2024-05-31
  7. GECO: Generative Image-to-3D within a SECOnd 7 upvotes, #7 of 2024-05-31
  8. DevEval: A Manually-Annotated Code Generation Benchmark Aligned with Real-World Code Repositories 6 upvotes, #8 of 2024-05-31
  9. PLA4D: Pixel-Level Alignments for Text-to-4D Gaussian Splatting 5 upvotes, #9 of 2024-05-31
  10. DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark 3 upvotes, #10 of 2024-05-31
  11. Parrot: Efficient Serving of LLM-based Applications with Semantic Variable 3 upvotes, #10 of 2024-05-31

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.