| Compositional languages emerge in a neural iterated learning model Y Ren, S Guo, M Labeau, SB Cohen, S Kirby ICLR2020, 2020 | 135* | 2020 |
| Learning Dynamics of LLM Finetuning Y Ren, DJ Sutherland ICLR 2025 (Oral, Outstanding Paper Award), 2025 | 89 | 2025 |
| The Emergence of Compositional Languages for Numeric Concepts Through Iterated Learning in Neural Agents S Guo, Y Ren, S Havrylov, S Frank, I Titov, K Smith Workshop: EmeCom@NeurIPS, 2019 | 41 | 2019 |
| Better Supervisory Signals by Observing Learning Paths Y Ren, S Guo, DJ Sutherland ICLR2022, 2022 | 34 | 2022 |
| Economics arena for large language models S Guo, H Bu, H Wang, Y Ren, D Sui, Y Shang, S Lu Workshop: Language Gamification@NeurIPS2024, 2024 | 33 | 2024 |
| How to prepare your task head for finetuning Y Ren, S Guo, W Bae, DJ Sutherland ICLR2023, 2023 | 26 | 2023 |
| Improving Compositional Generalization Using Iterated Learning and Simplicial Embeddings Y Ren, S Lavoie, M Galkin, DJ Sutherland, A Courville NeurIPS 2023, 2023 | 19 | 2023 |
| Expressivity of Emergent Language is a Trade-off between Contextual Complexity and Unpredictability S Guo, Y Ren, K Mathewson, S Kirby, SV Albrecht, K Smith ICLR2022, 2021 | 15 | 2021 |
| Bias Amplification in Language Model Evolution: An Iterated Learning Perspective Y Ren, S Guo, L Qiu, B Wang, DJ Sutherland NeurIPS 2024, 2024 | 13* | 2024 |
| On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization W Deng, Y Ren, M Li, DJ Sutherland, X Li, C Thrampoulidis NeurIPS 2025, 2025 | 12 | 2025 |
| Inductive bias and language expressivity in emergent communication S Guo, Y Ren, A Słowik, K Mathewson Workshop: EmeCom@NeurIPS, 2020 | 9 | 2020 |
| AdaFlood: Adaptive Flood Regularization W Bae, Y Ren, MO Ahmed, F Tung, DJ Sutherland, GL Oliveira TMLR, 2024 | 5 | 2024 |
| lpNTK: Better Generalisation with Less Data via Sample Interaction During Learning S Guo, Y Ren, SV Albrecht, K Smith ICLR 2024, 2024 | 5 | 2024 |
| SimKO: Simple Pass@ K Policy Optimization R *Peng, Y *Ren, Z Yu, W Liu, Y Wen arXiv preprint arXiv:2510.14807, 2025 | 4 | 2025 |
| Token Hidden Reward: Steering Exploration-Exploitation in GRPO Training W Deng, Y Ren, DJ Sutherland, C Thrampoulidis, X Li 2nd AI for Math Workshop@ ICML 2025 (Best Paper Award), 2025 | 3* | 2025 |
| Understanding Simplicity Bias towards Compositional Mappings via Learning Dynamics Y Ren, DJ Sutherland Workshop: Compositional Learning@NeurIPS 2024, 2024 | 3 | 2024 |
| On GRPO Collapse in Search-R1: The Lazy Likelihood-Displacement Death Spiral W Deng, Y Li, B Gong, Y Ren, C Thrampoulidis, X Li arXiv preprint arXiv:2512.04220, 2025 | 2 | 2025 |
| Learning Dynamics of Deep Learning--Force Analysis of Deep Neural Networks Y Ren arXiv preprint arXiv:2509.19554, 2025 | 2 | 2025 |
Shangmin GuoUniversity of EdinburghVerified email at ed.ac.uk
