Daily Papers of 2024-07-25

  1. OpenDevin: An Open Platform for AI Software Developers as Generalist Agents 62 upvotes, #1 of 2024-07-25
  2. VILA^2: VILA Augmented VILA 36 upvotes, #2 of 2024-07-25
  3. HumanVid: Demystifying Training Data for Camera-controllable Human Image Animation 21 upvotes, #3 of 2024-07-25
  4. DDK: Distilling Domain Knowledge for Efficient Large Language Models 18 upvotes, #4 of 2024-07-25
  5. PERSONA: A Reproducible Testbed for Pluralistic Alignment 16 upvotes, #5 of 2024-07-25
  6. Longhorn: State Space Models are Amortized Online Learners 14 upvotes, #6 of 2024-07-25
  7. SV4D: Dynamic 3D Content Generation with Multi-Frame and Multi-View Consistency 13 upvotes, #7 of 2024-07-25
  8. Learning to Manipulate Anywhere: A Visual Generalizable Framework For Reinforcement Learning 11 upvotes, #8 of 2024-07-25
  9. MOMAland: A Set of Benchmarks for Multi-Objective Multi-Agent Reinforcement Learning 10 upvotes, #9 of 2024-07-25
  10. ViPer: Visual Personalization of Generative Models via Individual Preference Learning 10 upvotes, #9 of 2024-07-25
  11. Scalify: scale propagation for efficient low-precision LLM training 9 upvotes, #11 of 2024-07-25
  12. DistilDIRE: A Small, Fast, Cheap and Lightweight Diffusion Synthesized Deepfake Detection 8 upvotes, #12 of 2024-07-25
  13. DreamCar: Leveraging Car-specific Prior for in-the-wild 3D Car Reconstruction 6 upvotes, #13 of 2024-07-25

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.