Linyi Yang
7
Papers
111
Total Citations
Papers (7)
CycleResearcher: Improving Automated Research via Automated Review
ICLR 2025arXiv
62
citations
ReMA: Learning to Meta-Think for LLMs with Multi-agent Reinforcement Learning
NeurIPS 2025arXiv
35
citations
CofCA: A STEP-WISE Counterfactual Multi-hop QA benchmark
ICLR 2025arXiv
14
citations
ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
NeurIPS 2025arXiv
0
citations
MMQA: Evaluating LLMs with Multi-Table Multi-Hop Complex Questions
ICLR 2025
0
citations
Constrain Alignment with Sparse Autoencoders
ICML 2025arXiv
0
citations
USB: A Unified Semi-supervised Learning Benchmark for Classification
NeurIPS 2022arXiv
0
citations