Daily Papers of 2024-12-18

  1. Are Your LLMs Capable of Stable Reasoning? 87 upvotes, #1 of 2024-12-18
  2. Multi-Dimensional Insights: Benchmarking Real-World Personalization in Large Multimodal Models 41 upvotes, #2 of 2024-12-18
  3. OmniEval: An Omnidirectional and Automatic RAG Evaluation Benchmark in Financial Domain 40 upvotes, #3 of 2024-12-18
  4. Compressed Chain of Thought: Efficient Reasoning Through Dense Representations 30 upvotes, #4 of 2024-12-18
  5. Emergence of Abstractions: Concept Encoding and Decoding Mechanism for In-Context Learning in Transformers 15 upvotes, #5 of 2024-12-18
  6. VisDoM: Multi-Document QA with Visually Rich Elements Using Multimodal Retrieval-Augmented Generation 14 upvotes, #6 of 2024-12-18
  7. Feather the Throttle: Revisiting Visual Token Pruning for Vision-Language Model Acceleration 12 upvotes, #7 of 2024-12-18
  8. Proposer-Agent-Evaluator(PAE): Autonomous Skill Discovery For Foundation Model Internet Agents 12 upvotes, #7 of 2024-12-18
  9. Marigold-DC: Zero-Shot Monocular Depth Completion with Guided Diffusion 6 upvotes, #9 of 2024-12-18
  10. SUGAR: Subject-Driven Video Customization in a Zero-Shot Manner 5 upvotes, #10 of 2024-12-18
  11. When to Speak, When to Abstain: Contrastive Decoding with Abstention 4 upvotes, #11 of 2024-12-18
  12. MIVE: New Design and Benchmark for Multi-Instance Video Editing 4 upvotes, #11 of 2024-12-18
  13. Seeker: Towards Exception Safety Code Generation with Intermediate Language Agents Framework 3 upvotes, #13 of 2024-12-18

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.