Daily Papers of 2024-10-22

  1. FrugalNeRF: Fast Convergence for Few-shot Novel View Synthesis without Learned Priors 79 upvotes, #1 of 2024-10-22
  2. SAM2Long: Enhancing SAM 2 for Long Video Segmentation with a Training-Free Memory Tree 61 upvotes, #2 of 2024-10-22
  3. CompassJudger-1: All-in-one Judge Model Helps Model Evaluation and Evolution 55 upvotes, #3 of 2024-10-22
  4. PUMA: Empowering Unified MLLM with Multi-granular Visual Generation 51 upvotes, #4 of 2024-10-22
  5. AutoTrain: No-code training for state-of-the-art models 48 upvotes, #5 of 2024-10-22
  6. Baichuan Alignment Technical Report 46 upvotes, #6 of 2024-10-22
  7. SemiEvol: Semi-supervised Fine-tuning for LLM Adaptation 45 upvotes, #7 of 2024-10-22
  8. Pangea: A Fully Open Multilingual Multimodal LLM for 39 Languages 41 upvotes, #8 of 2024-10-22
  9. RM-Bench: Benchmarking Reward Models of Language Models with Subtlety and Style 23 upvotes, #9 of 2024-10-22
  10. Meta-Chunking: Learning Efficient Text Segmentation via Logical Perception 20 upvotes, #10 of 2024-10-22
  11. Pre-training Distillation for Large Language Models: A Design Space Exploration 15 upvotes, #11 of 2024-10-22
  12. Alchemy: Amplifying Theorem-Proving Capability through Symbolic Mutation 11 upvotes, #12 of 2024-10-22
  13. Ichigo: Mixed-Modal Early-Fusion Realtime Voice Assistant 8 upvotes, #13 of 2024-10-22
  14. Zero-shot Model-based Reinforcement Learning using Large Language Models 7 upvotes, #14 of 2024-10-22
  15. Selecting Influential Samples for Long Context Alignment via Homologous Models' Guidance and Contextual Awareness Measurement 7 upvotes, #14 of 2024-10-22
  16. How Many Van Goghs Does It Take to Van Gogh? Finding the Imitation Threshold 6 upvotes, #16 of 2024-10-22
  17. CBT-Bench: Evaluating Large Language Models on Assisting Cognitive Behavior Therapy 4 upvotes, #17 of 2024-10-22
  18. Agent-to-Sim: Learning Interactive Behavior Models from Casual Longitudinal Videos 4 upvotes, #17 of 2024-10-22
  19. Router-Tuning: A Simple and Effective Approach for Enabling Dynamic-Depth in Transformers 2 upvotes, #19 of 2024-10-22
  20. In-context learning and Occam's razor 2 upvotes, #19 of 2024-10-22
  21. Cross-Lingual Auto Evaluation for Assessing Multilingual LLMs 1 upvotes, #21 of 2024-10-22
  22. DM-Codec: Distilling Multimodal Representations for Speech Tokenization 1 upvotes, #21 of 2024-10-22
  23. Hallucination Detox: Sensitive Neuron Dropout (SeND) for Large Language Model Training 1 upvotes, #21 of 2024-10-22

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.