Daily Papers of 2024-09-17

  1. Seed-Music: A Unified Framework for High Quality and Controlled Music Generation 43 upvotes, #1 of 2024-09-17
  2. Kolmogorov-Arnold Transformer 34 upvotes, #2 of 2024-09-17
  3. RetrievalAttention: Accelerating Long-Context LLM Inference via Vector Retrieval 28 upvotes, #3 of 2024-09-17
  4. One missing piece in Vision and Language: A Survey on Comics Understanding 23 upvotes, #4 of 2024-09-17
  5. jina-embeddings-v3: Multilingual Embeddings With Task LoRA 19 upvotes, #5 of 2024-09-17
  6. Ferret: Federated Full-Parameter Tuning at Scale for Large Language Models 14 upvotes, #6 of 2024-09-17
  7. ReCLAP: Improving Zero Shot Audio Classification by Describing Sounds 10 upvotes, #7 of 2024-09-17
  8. On the Diagram of Thought 9 upvotes, #8 of 2024-09-17
  9. Guiding Vision-Language Model Selection for Visual Question-Answering Across Tasks, Domains, and Knowledge Types 7 upvotes, #9 of 2024-09-17
  10. Policy Filtration in RLHF to Fine-Tune LLM for Code Generation 5 upvotes, #10 of 2024-09-17
  11. AudioBERT: Audio Knowledge Augmented Language Model 4 upvotes, #11 of 2024-09-17
  12. Breaking reCAPTCHAv2 4 upvotes, #11 of 2024-09-17
  13. Towards Predicting Temporal Changes in a Patient's Chest X-ray Images based on Electronic Health Records 3 upvotes, #13 of 2024-09-17
  14. LLM-Powered Grapheme-to-Phoneme Conversion: Benchmark and Case Study 3 upvotes, #13 of 2024-09-17
  15. beeFormer: Bridging the Gap Between Semantic and Interaction Similarity in Recommender Systems 2 upvotes, #15 of 2024-09-17

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.