Daily Papers of 2024-09-11

  1. LLaMA-Omni: Seamless Speech Interaction with Large Language Models 49 upvotes, #1 of 2024-09-11
  2. GroUSE: A Benchmark to Evaluate Evaluators in Grounded Question Answering 37 upvotes, #2 of 2024-09-11
  3. INTRA: Interaction Relationship-aware Weakly Supervised Affordance Grounding 24 upvotes, #3 of 2024-09-11
  4. SongCreator: Lyrics-based Universal Song Generation 19 upvotes, #4 of 2024-09-11
  5. Draw an Audio: Leveraging Multi-Instruction for Video-to-Audio Synthesis 14 upvotes, #5 of 2024-09-11
  6. SaRA: High-Efficient Diffusion Model Fine-tuning with Progressive Sparse Low-Rank Adaptation 14 upvotes, #5 of 2024-09-11
  7. LEIA: Latent View-invariant Embeddings for Implicit 3D Articulation 2 upvotes, #7 of 2024-09-11

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.