Daily Papers of 2024-12-10

  1. Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation 70 upvotes, #1 of 2024-12-10
  2. ProcessBench: Identifying Process Errors in Mathematical Reasoning 61 upvotes, #2 of 2024-12-10
  3. Training Large Language Models to Reason in a Continuous Latent Space 54 upvotes, #3 of 2024-12-10
  4. Maya: An Instruction Finetuned Multilingual Multimodal Model 22 upvotes, #4 of 2024-12-10
  5. OmniDocBench: Benchmarking Diverse PDF Document Parsing with Comprehensive Annotations 19 upvotes, #5 of 2024-12-10
  6. Around the World in 80 Timesteps: A Generative Approach to Global Visual Geolocation 18 upvotes, #6 of 2024-12-10
  7. Divot: Diffusion Powers Video Tokenizer for Comprehension and Generation 13 upvotes, #7 of 2024-12-10
  8. Exploring Multi-Grained Concept Annotations for Multimodal Large Language Models 12 upvotes, #8 of 2024-12-10
  9. You See it, You Got it: Learning 3D Creation on Pose-Free Videos at Scale 11 upvotes, #9 of 2024-12-10
  10. Gated Delta Networks: Improving Mamba2 with Delta Rule 9 upvotes, #10 of 2024-12-10
  11. MotionShop: Zero-Shot Motion Transfer in Video Diffusion Models with Mixture of Score Guidance 7 upvotes, #11 of 2024-12-10
  12. Global and Dense Embeddings of Earth: Major TOM Floating in the Latent Space 6 upvotes, #12 of 2024-12-10
  13. MAtCha Gaussians: Atlas of Charts for High-Quality Geometry and Photorealism From Sparse Views 6 upvotes, #12 of 2024-12-10
  14. CARP: Visuomotor Policy Learning via Coarse-to-Fine Autoregressive Prediction 6 upvotes, #12 of 2024-12-10
  15. Robust Multi-bit Text Watermark with LLM-based Paraphrasers 5 upvotes, #15 of 2024-12-10
  16. If You Can't Use Them, Recycle Them: Optimizing Merging at Scale Mitigates Performance Tradeoffs 3 upvotes, #16 of 2024-12-10
  17. Turbo3D: Ultra-fast Text-to-3D Generation 3 upvotes, #16 of 2024-12-10

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.