Daily Papers of 2024-11-01

  1. Unpacking SDXL Turbo: Interpreting Text-to-Image Models with Sparse Autoencoders 71 upvotes, #1 of 2024-11-01
  2. What Happened in LLMs Layers when Trained for Fast vs. Slow Thinking: A Gradient Perspective 57 upvotes, #2 of 2024-11-01
  3. A Pointer Network-based Approach for Joint Extraction and Detection of Multi-Label Multi-Class Intents 24 upvotes, #3 of 2024-11-01
  4. SelfCodeAlign: Self-Alignment for Code Generation 20 upvotes, #4 of 2024-11-01
  5. BitStack: Fine-Grained Size Control for Compressed Large Language Models in Variable Memory Environments 17 upvotes, #5 of 2024-11-01
  6. Language Models can Self-Lengthen to Generate Long Texts 15 upvotes, #6 of 2024-11-01
  7. Constraint Back-translation Improves Complex Instruction Following of Large Language Models 15 upvotes, #6 of 2024-11-01
  8. NeuZip: Memory-Efficient Training and Inference with Dynamic Compression of Neural Networks 14 upvotes, #8 of 2024-11-01
  9. Learning Video Representations without Natural Videos 14 upvotes, #8 of 2024-11-01
  10. AAAR-1.0: Assessing AI's Potential to Assist Research 13 upvotes, #10 of 2024-11-01
  11. BenchX: A Unified Benchmark Framework for Medical Vision-Language Pretraining on Chest X-Rays 8 upvotes, #11 of 2024-11-01
  12. Navigating the Unknown: A Chat-Based Collaborative Interface for Personalized Exploratory Tasks 8 upvotes, #11 of 2024-11-01
  13. DELTA: Dense Efficient Long-range 3D Tracking for any video 8 upvotes, #11 of 2024-11-01
  14. Minimum Entropy Coupling with Bottleneck 4 upvotes, #14 of 2024-11-01
  15. Teaching Embodied Reinforcement Learning Agents: Informativeness and Diversity of Language Use 4 upvotes, #14 of 2024-11-01
  16. GlotCC: An Open Broad-Coverage CommonCrawl Corpus and Pipeline for Minority Languages 3 upvotes, #16 of 2024-11-01

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.