2 citations · 2 across the 6 of their papers we have counts for
7 papers
Splicing Hints into Reasoning Traces: Learning from Demonstrator Failures
Hamed Mahdavi, Pouria Mahdavinia, Majid Farhadi +1
Reinforcement learning with verifiable rewards improves mathematical reasoning when a final answer can be checked, but a correct answer does not certify the derivation behind it, a…
CombiGraph-Vis: A Curated Multimodal Olympiad Benchmark for Discrete Mathematical Reasoning
Hamed Mahdavi, Pouria Mahdavinia, Alireza Farhadi +7
State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 o…
RefGrader: Automated Grading of Mathematical Competition Proofs using Agentic Workflows
Hamed Mahdavi, Pouria Mahdavinia, Samira Malek +7
State-of-the-art (SOTA) LLMs have progressed from struggling on proof-based Olympiad problems to solving most of the IMO 2025 problems, with leading systems reportedly handling 5 o…
Harnessing Optimization Dynamics for Curvature-Informed Model Merging
Pouria Mahdavinia, Hamed Mahdavi, Niloofar Mireshghallah +1
Model merging is an effective post-training strategy for composing capabilities in large language models without joint retraining. We study this in the supervised fine-tuning (SFT)…
Low-rank Momentum Factorization for Memory Efficient Training
Pouria Mahdavinia, Mehrdad Mahdavi
Fine-tuning large foundation models presents significant memory challenges due to stateful optimizers like AdamW, often requiring several times more GPU memory than inference. Whil…
Distributed Personalized Empirical Risk Minimization
Yuyang Deng, Mohammad Mahdi Kamani, Pouria Mahdavinia +1
This paper advocates a new paradigm Personalized Empirical Risk Minimization (PERM) to facilitate learning from heterogeneous data sources without imposing stringent constraints on…
Tight Analysis of Extra-gradient and Optimistic Gradient Methods For Nonconvex Minimax Problems
Pouria Mahdavinia, Yuyang Deng, Haochuan Li +1
Despite the established convergence theory of Optimistic Gradient Descent Ascent (OGDA) and Extragradient (EG) methods for the convex-concave minimax problems, little is known abou…