Daily Papers of 2024-07-03

  1. Summary of a Haystack: A Challenge to Long-Context LLMs and RAG Systems 73 upvotes, #1 of 2024-07-03
  2. OpenVid-1M: A Large-Scale High-Quality Dataset for Text-to-video Generation 43 upvotes, #2 of 2024-07-03
  3. Agentless: Demystifying LLM-based Software Engineering Agents 37 upvotes, #3 of 2024-07-03
  4. MInference 1.0: Accelerating Pre-filling for Long-Context LLMs via Dynamic Sparse Attention 22 upvotes, #4 of 2024-07-03
  5. Understanding Alignment in Multimodal LLMs: A Comprehensive Study 18 upvotes, #5 of 2024-07-03
  6. Magic Insert: Style-Aware Drag-and-Drop 16 upvotes, #6 of 2024-07-03
  7. Consistency Flow Matching: Defining Straight Flows with Velocity Consistency 14 upvotes, #7 of 2024-07-03
  8. Revealing Fine-Grained Values and Opinions in Large Language Models 13 upvotes, #8 of 2024-07-03
  9. What Matters in Detecting AI-Generated Videos like Sora? 13 upvotes, #8 of 2024-07-03
  10. To Forget or Not? Towards Practical Knowledge Unlearning for Large Language Models 13 upvotes, #8 of 2024-07-03
  11. FoleyCrafter: Bring Silent Videos to Life with Lifelike and Synchronized Sounds 10 upvotes, #11 of 2024-07-03
  12. μ-Bench: A Vision-Language Benchmark for Microscopy Understanding 5 upvotes, #12 of 2024-07-03

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.