5 papers
TRACE: A Framework for Analyzing and Enhancing Stepwise Reasoning in Vision-Language Models
Shima Imani, Seungwhan Moon, Lambert Mathias +2
Reliable mathematical and scientific reasoning remains an open challenge for large vision-language models. Standard final-answer evaluation often masks reasoning errors, allowing s…
SymPyBench: A Dynamic Benchmark for Scientific Reasoning with Executable Python Code
Shima Imani, Seungwhan Moon, Adel Ahmadyan +3
We introduce, a large-scale synthetic benchmark of 15,045 university-level physics problems (90/10% train/test split). Each problem is fully parameterized, supporting an effectivel…
PRiSM: An Agentic Multimodal Benchmark for Scientific Reasoning via Python-Grounded Evaluation
Shima Imani, Seungwhan Moon, Adel Ahmadyan +3
Evaluating vision-language models (VLMs) in scientific domains like mathematics and physics poses unique challenges that go far beyond predicting final answers. These domains deman…
Diffusion-Augmented Coreset Expansion for Scalable Dataset Distillation
Ali Abbasi, Shima Imani, Chenyang An +6
With the rapid scaling of neural networks, data storage and communication demands have intensified. Dataset distillation has emerged as a promising solution, condensing information…
Next-Token Prediction Task Assumes Optimal Data Ordering for LLM Training in Proof Generation
Chenyang An, Shima Imani, Feng Yao +8
In the field of large language model (LLM)-based proof generation, despite extensive training on large datasets such as ArXiv, LLMs still exhibit only modest performance on proving…