Reyhane Askari-Hemmat — accepted AI-conference papers

2026

Inference-time Physics Alignment of Video Generative Models with Latent World Models

Jianhao Yuan, Xiaofeng Zhang, Felix Friedrich, Nicolas Beltran-Velez, Melissa Hall, Reyhane Askari-Hemmat +4

CVPR 2026

State-of-the-art video generative models produce promising visual content yet often violate basic physics principles, limiting their utility. While some attribute this deficiency to insufficient physics understanding from pre-training, we find that the shortfall in physics plausibility also stems fr

Cited by 0 Source ↗code ↗Scholar ↗

2026

Multimodal RewardBench 2: Evaluating Omni Reward Models for Interleaved Text and Image

Yushi Hu, Reyhane Askari-Hemmat, Melissa Hall, Emily Dinan, Luke Zettlemoyer, Marjan Ghazvininejad

CVPR 2026

Reward models (RMs) are essential for training large language models (LLMs), but remain underexplored for omni models that handle interleaved image and text sequences. We introduce Multimodal RewardBench 2 (MMRB2), the first comprehensive benchmark for reward models on multimodal understanding and (

Cited by 0 Source ↗code ↗Scholar ↗

2026

Why Less is More (Sometimes): A Theory of Data Curation

Elvis Dohmatob, Mohammad Pezeshki, Reyhane Askari-Hemmat

ICLR 2026poster

This paper introduces a theoretical framework to resolve a central paradox in modern machine learning: When is it better to use less data? This question has become critical as classical scaling laws suggesting ``more is more'' (Sun et al., 2025) are challenged by methods like LIMO (``less is more'')…

Cited by 0 Source ↗code ↗Scholar ↗

2025

Improving the Scaling Laws of Synthetic Data with Deliberate Practice

Reyhane Askari-Hemmat, Mohammad Pezeshki, Elvis Dohmatob, Florian Bordes, Pietro Astolfi, Melissa Hall +3

ICML 2025oral

Inspired by the principle of deliberate practice in human learning, we propose Deliberate Practice for Synthetic Data Generation (DP), a novel framework that improves sample efficiency through dynamic synthetic data generation. Prior work has shown that scaling synthetic data is inherently challengi…

Cited by 0 Source ↗PDF ↗Scholar ↗

2025

Increasing the Utility of Synthetic Images through Chamfer Guidance

Nicola Dall'Asen, Xiaofeng Zhang, Reyhane Askari-Hemmat, Melissa Hall, Jakob Verbeek, Adriana Romero-Soriano +1

NeurIPS 2025poster

Conditional image generative models hold considerable promise to produce infinite amounts of synthetic training data. Yet, recent progress in generation quality has come at the expense of generation diversity, limiting the utility of these models as a source of synthetic training data. Although gui…

Cited by 0 Source ↗Scholar ↗