Sadegh Mahdavi

16 papers A* 3Misc 1Journal 12
YearRankTypeTitle / Venue / Authors
2026 J jnl
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients.
Trans. Mach. Learn. Res.
Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng
2026 J jnl
Learning Generative Selection for Best-of-N.
CoRR
Shubham Toshniwal, Aleksander Ficek, Siddhartha Jain, Wei Du, Vahid Noroozi, Sadegh Mahdavi, Somshubra Majumdar, Igor Gitman
2025 J jnl
Advantage Shaping as Surrogate Reward Maximization: Unifying Pass@K Policy Gradients.
CoRR
Christos Thrampoulidis, Sadegh Mahdavi, Wenlong Deng
2025 A* conf
Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation.
ICML
Sadegh Mahdavi, Muchen Li, Kaiwen Liu, Christos Thrampoulidis, Leonid Sigal, Renjie Liao
2025 J jnl
Leveraging Online Olympiad-Level Math Problems for LLMs Training and Contamination-Resistant Evaluation.
CoRR
Sadegh Mahdavi, Muchen Li, Kaiwen Liu, Christos Thrampoulidis, Leonid Sigal, Renjie Liao
2025 J jnl
Nemotron-Math: Efficient Long-Context Distillation of Mathematical Reasoning from Multi-Mode Supervision.
CoRR
Wei Du, Shubham Toshniwal, Branislav Kisacanin, Sadegh Mahdavi, Ivan Moshkov, George Armstrong, Stephen Ge, Edgar Minasyan, Feng Chen, Igor Gitman
2025 J jnl
Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection.
CoRR
Sadegh Mahdavi, Branislav Kisacanin, Shubham Toshniwal, Wei Du, Ivan Moshkov, George Armstrong, Renjie Liao, Christos Thrampoulidis, Igor Gitman
2025 J jnl
The Challenge of Teaching Reasoning to LLMs Without RL or Distillation.
CoRR
Wei Du, Branislav Kisacanin, George Armstrong, Shubham Toshniwal, Ivan Moshkov, Alexan Ayrapetyan, Sadegh Mahdavi, Dan Zhao, Shizhe Diao, Dragan Masulovic, Marius Stanean, Advaith Avadhanam, Max Wang, Ashmit Dutta, Shitij Govil, Sri Yanamandara, Mihir Tandon, Sriram Ananthakrishnan, Vedant Rathi, David Zhang, Joonseok Kang, Leon Luo, Titu Andreescu, Boris Ginsburg, Igor Gitman
2024 J jnl
From Graph Diffusion to Graph Classification.
CoRR
Jia Jun Cheng Xian, Sadegh Mahdavi, Renjie Liao, Oliver Schulte
2024 J jnl
Leveraging Environment Interaction for Automated PDDL Generation and Planning with Large Language Models.
CoRR
Sadegh Mahdavi, Raquel Aoki, Keyi Tang, Yanshuai Cao
2024 A* conf
Leveraging Environment Interaction for Automated PDDL Translation and Planning with Large Language Models.
NeurIPS
Sadegh Mahdavi, Raquel Aoki, Keyi Tang, Yanshuai Cao
2024 A* conf
Memorization Capacity of Multi-Head Attention in Transformers.
ICLR
Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis
2024 Misc conf
Revisiting the Equivalence of In-Context Learning and Gradient Descent: The Impact of Data Distribution.
ICASSP
Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis
2023 J jnl
Memorization Capacity of Multi-Head Attention in Transformers.
CoRR
Sadegh Mahdavi, Renjie Liao, Christos Thrampoulidis
2023 J jnl
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks.
Trans. Mach. Learn. Res.
Sadegh Mahdavi, Kevin Swersky, Thomas Kipf, Milad Hashemi, Christos Thrampoulidis, Renjie Liao
2022 J jnl
Towards Better Out-of-Distribution Generalization of Neural Algorithmic Reasoning Tasks.
CoRR
Sadegh Mahdavi, Kevin Swersky, Thomas Kipf, Milad Hashemi, Christos Thrampoulidis, Renjie Liao