Zonglin Yang's picture

Zonglin Yang

ZonglinY

·

https://zongliny.github.io/

AI & ML interests

LLMs for Automated Scientific Hypothesis Discovery; Reasoning & LLMs; Pretraining

Recent Activity

upvoted a paper 19 days ago

Error-Free Linear Attention is a Free Lunch: Exact Solution from Continuous-Time Dynamics

upvoted a paper about 1 month ago

LongVT: Incentivizing "Thinking with Long Videos" via Native Tool Calling

upvoted a paper about 1 month ago

OpenMMReasoner: Pushing the Frontiers for Multimodal Reasoning with an Open and General Recipe

View all activity

Organizations

commented 3 papers 7 months ago

Harnessing Large Language Models for Scientific Novelty Detection

Paper • 2505.24615 • Published May 30, 2025 • 5 •

MOOSE-Chem2: Exploring LLM Limits in Fine-Grained Scientific Hypothesis Discovery via Hierarchical Search

Paper • 2505.19209 • Published May 25, 2025 • 23 •

MOOSE-Chem3: Toward Experiment-Guided Hypothesis Ranking via Simulated Experimental Feedback

Paper • 2505.17873 • Published May 23, 2025 • 30 •

commented a paper 9 months ago

ResearchBench: Benchmarking LLMs in Scientific Discovery via Inspiration-Based Task Decomposition

Paper • 2503.21248 • Published Mar 27, 2025 • 21 •

commented a paper 12 months ago

LLM4SR: A Survey on Large Language Models for Scientific Research

Paper • 2501.04306 • Published Jan 8, 2025 • 35 •