Yunzhi Yao

Yunzhi Yao on Hugging Face Daily Papers: 15 papers, 1 in the top 3 of their day, 354 upvotes.

  1. From Data to Behavior: Predicting Unintended Model Behaviors Before Training 15 upvotes, #25 of 2026-02-05
  2. Why Steering Works: Toward a Unified View of Language Model Parameter Dynamics 13 upvotes, #32 of 2026-02-03
  3. Aligning Agentic World Models via Knowledgeable Experience Learning 15 upvotes, #15 of 2026-01-21
  4. How Do Large Language Models Learn Concepts During Continual Pre-Training? 3 upvotes, #21 of 2026-01-13
  5. Illusions of Confidence? Diagnosing LLM Truthfulness via Neighborhood Consistency 18 upvotes, #12 of 2026-01-12
  6. LightMem: Lightweight and Efficient Memory-Augmented Generation 105 upvotes, #2 of 2025-10-22
  7. ReCode: Updating Code API Knowledge with Reinforcement Learning 7 upvotes, #12 of 2025-06-26
  8. Two Experts Are All You Need for Steering Thinking: Reinforcing Cognitive Effort in MoE Reasoning Models Without Additional Training 9 upvotes, #23 of 2025-05-21
  9. EasyEdit2: An Easy-to-use Steering Framework for Editing Large Language Models 21 upvotes, #12 of 2025-04-22
  10. CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners 15 upvotes, #18 of 2025-03-21
  11. How Do LLMs Acquire New Knowledge? A Knowledge Circuits Perspective on Continual Pre-Training 21 upvotes, #6 of 2025-02-18
  12. Exploring Model Kinship for Merging Large Language Models 19 upvotes, #6 of 2024-10-17
  13. Benchmarking Chinese Knowledge Rectification in Large Language Models 13 upvotes, #7 of 2024-09-10
  14. Knowledge Mechanisms in Large Language Models: A Survey and Perspective 31 upvotes, #4 of 2024-07-23
  15. A Comprehensive Study of Knowledge Editing for Large Language Models 19 upvotes, #6 of 2024-01-03

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.