Daily Papers of 2024-10-14

  1. Baichuan-Omni Technical Report 80 upvotes, #1 of 2024-10-14
  2. Meissonic: Revitalizing Masked Generative Transformers for Efficient High-Resolution Text-to-Image Synthesis 44 upvotes, #2 of 2024-10-14
  3. StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization 36 upvotes, #3 of 2024-10-14
  4. From Generalist to Specialist: Adapting Vision Language Models via Task-Specific Visual Instruction Tuning 34 upvotes, #4 of 2024-10-14
  5. EvolveDirector: Approaching Advanced Text-to-Image Generation with Large Vision-Language Models 18 upvotes, #5 of 2024-10-14
  6. Multi-Agent Collaborative Data Selection for Efficient LLM Pretraining 17 upvotes, #6 of 2024-10-14
  7. PositionID: LLMs can Control Lengths, Copy and Paste with Explicit Positional Awareness 16 upvotes, #7 of 2024-10-14
  8. Mechanistic Permutability: Match Features Across Layers 16 upvotes, #7 of 2024-10-14
  9. SuperCorrect: Supervising and Correcting Language Models with Error-Driven Insights 16 upvotes, #7 of 2024-10-14
  10. Semantic Score Distillation Sampling for Compositional Text-to-3D Generation 12 upvotes, #10 of 2024-10-14
  11. KV Prediction for Improved Time to First Token 11 upvotes, #11 of 2024-10-14
  12. Think While You Generate: Discrete Diffusion with Planned Denoising 8 upvotes, #12 of 2024-10-14
  13. ZeroComp: Zero-shot Object Compositing from Image Intrinsics via Diffusion 7 upvotes, #13 of 2024-10-14
  14. I-Max: Maximize the Resolution Potential of Pre-trained Rectified Flow Transformers with Projected Flow 5 upvotes, #14 of 2024-10-14
  15. DA-Code: Agent Data Science Code Generation Benchmark for Large Language Models 4 upvotes, #15 of 2024-10-14
  16. Mentor-KD: Making Small Language Models Better Multi-step Reasoners 4 upvotes, #15 of 2024-10-14
  17. SimpleStrat: Diversifying Language Model Generation with Stratification 4 upvotes, #15 of 2024-10-14
  18. MiRAGeNews: Multimodal Realistic AI-Generated News Detection 4 upvotes, #15 of 2024-10-14
  19. GenARM: Reward Guided Generation with Autoregressive Reward Model for Test-time Alignment 3 upvotes, #19 of 2024-10-14
  20. Synth-SONAR: Sonar Image Synthesis with Enhanced Diversity and Realism via Dual Diffusion Models and GPT Prompting 1 upvotes, #20 of 2024-10-14

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.