Daily Papers of 2024-10-30

  1. CLEAR: Character Unlearning in Textual and Visual Modalities 196 upvotes, #1 of 2024-10-30
  2. AutoKaggle: A Multi-Agent Framework for Autonomous Data Science Competitions 36 upvotes, #2 of 2024-10-30
  3. SocialGPT: Prompting LLMs for Social Relation Reasoning via Greedy Segment Optimization 19 upvotes, #3 of 2024-10-30
  4. OpenWebVoyager: Building Multimodal Web Agents via Iterative Real-World Exploration, Feedback and Optimization 14 upvotes, #4 of 2024-10-30
  5. Flow-DPO: Improving LLM Mathematical Reasoning through Online Multi-Agent Learning 14 upvotes, #4 of 2024-10-30
  6. Can Language Models Replace Programmers? REPOCOD Says 'Not Yet' 11 upvotes, #6 of 2024-10-30
  7. Task Vectors are Cross-Modal 10 upvotes, #7 of 2024-10-30
  8. Mind Your Step (by Step): Chain-of-Thought can Reduce Performance on Tasks where Thinking Makes Humans Worse 9 upvotes, #8 of 2024-10-30
  9. ShadowKV: KV Cache in Shadows for High-Throughput Long-Context LLM Inference 9 upvotes, #8 of 2024-10-30
  10. Precise and Dexterous Robotic Manipulation via Human-in-the-Loop Reinforcement Learning 9 upvotes, #8 of 2024-10-30
  11. Robots Pre-train Robots: Manipulation-Centric Robotic Representation from Large-Scale Robot Dataset 9 upvotes, #8 of 2024-10-30
  12. Zero-Shot Dense Retrieval with Embeddings from Relevance Feedback 6 upvotes, #12 of 2024-10-30
  13. RARe: Retrieval Augmented Retrieval with In-Context Examples 5 upvotes, #13 of 2024-10-30
  14. Accelerating Direct Preference Optimization with Prefix Sharing 5 upvotes, #13 of 2024-10-30
  15. Measuring memorization through probabilistic discoverable extraction 4 upvotes, #15 of 2024-10-30

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.