Daily Papers of 2024-06-21

  1. nabla^2DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentials 96 upvotes, #1 of 2024-06-21
  2. Instruction Pre-Training: Language Models are Supervised Multitask Learners 74 upvotes, #2 of 2024-06-21
  3. The Devil is in the Details: StyleFeatureEditor for Detail-Rich StyleGAN Inversion and High Quality Image Editing 64 upvotes, #3 of 2024-06-21
  4. HARE: HumAn pRiors, a key to small language model Efficiency 37 upvotes, #4 of 2024-06-21
  5. Prism: A Framework for Decoupling and Assessing the Capabilities of VLMs 33 upvotes, #5 of 2024-06-21
  6. Model Merging and Safety Alignment: One Bad Model Spoils the Bunch 30 upvotes, #6 of 2024-06-21
  7. MMBench-Video: A Long-Form Multi-Shot Benchmark for Holistic Video Understanding 27 upvotes, #7 of 2024-06-21
  8. Whiteboard-of-Thought: Thinking Step-by-Step Across Modalities 26 upvotes, #8 of 2024-06-21
  9. Invertible Consistency Distillation for Text-Guided Image Editing in Around 7 Steps 24 upvotes, #9 of 2024-06-21
  10. PIN: A Knowledge-Intensive Dataset for Paired and Interleaved Multimodal Documents 20 upvotes, #10 of 2024-06-21
  11. DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning 17 upvotes, #11 of 2024-06-21
  12. GLiNER multi-task: Generalist Lightweight Model for Various Information Extraction Tasks 17 upvotes, #11 of 2024-06-21
  13. Self-play with Execution Feedback: Improving Instruction-following Capabilities of Large Language Models 14 upvotes, #13 of 2024-06-21
  14. Iterative Length-Regularized Direct Preference Optimization: A Case Study on Improving 7B Language Models to GPT-4 Level 13 upvotes, #14 of 2024-06-21
  15. Improving Visual Commonsense in Language Models via Multiple Image Generation 13 upvotes, #14 of 2024-06-21
  16. LiveMind: Low-latency Large Language Models with Simultaneous Inference 13 upvotes, #14 of 2024-06-21
  17. ExVideo: Extending Video Diffusion Models via Parameter-Efficient Post-Tuning 10 upvotes, #17 of 2024-06-21
  18. REPOEXEC: Evaluate Code Generation with a Repository-Level Executable Benchmark 8 upvotes, #18 of 2024-06-21
  19. Model Internals-based Answer Attribution for Trustworthy Retrieval-Augmented Generation 7 upvotes, #19 of 2024-06-21
  20. StableSemantics: A Synthetic Language-Vision Dataset of Semantic Representations in Naturalistic Images 5 upvotes, #20 of 2024-06-21
  21. A Systematic Survey of Text Summarization: From Statistical Methods to Large Language Models 4 upvotes, #21 of 2024-06-21
  22. τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains 4 upvotes, #21 of 2024-06-21
  23. From Insights to Actions: The Impact of Interpretability and Analysis Research on NLP 4 upvotes, #21 of 2024-06-21
  24. Sampling 3D Gaussian Scenes in Seconds with Latent Diffusion Models 4 upvotes, #21 of 2024-06-21

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.