Related papers: Physics-R1: An Audited Olympiad Corpus and Recipe …

Existing benchmarks for evaluating foundation models mainly focus on single-document, text-only tasks. However, they often fail to fully capture the complexity of research workflows, which typically involve interpreting non-textual data and…

Developing 3D vision-language models with robust clinical reasoning remains a challenge due to the inherent complexity of volumetric medical imaging, the tendency of models to overfit superficial report patterns, and the lack of…

Visual mathematical reasoning, as a fundamental visual reasoning ability, has received widespread attention from the Large Multimodal Models (LMMs) community. Existing benchmarks, such as MathVista and MathVerse, focus more on the…

We present ThinknCheck, a 1B-parameter verifier for grounded claim verification that first produces a short, structured rationale and then a binary verdict. We construct LLMAggreFact-Think, a 24.1k reasoning-augmented training set derived…

Recent advancements in Large Multimodal Models (LMMs) have shown promising results in mathematical reasoning within visual contexts, with models approaching human-level performance on existing benchmarks such as MathVista. However, we…

Multimodal large language models (MLLMs) capable of processing both text and visual inputs are increasingly being explored for uses in physics education, such as tutoring, formative assessment, and grading. This study evaluates a range of…

Constructing scientific multimodal document reasoning datasets for foundation model training involves an inherent trade-off among scale, faithfulness, and realism. To address this challenge, we introduce the synthesize-and-reground…

Recent advancements in large reasoning models have fueled growing interest in extending such capabilities to multimodal domains. However, despite notable progress in visual reasoning, the lack of transparent and reproducible data curation…

We present NeuroQA, a large-scale benchmark for visual question answering in 3D brain magnetic resonance imaging (MRI), with 56,953 QA pairs from 12,977 subjects across 12 datasets. It spans ages 5-104 and five clinical domains:…

The success of DeepSeek-R1 demonstrates the immense potential of using reinforcement learning (RL) to enhance LLMs' reasoning capabilities. This paper introduces Retrv-R1, the first R1-style MLLM specifically designed for multimodal…

Multimodal Large Language Models (MLLM) are primarily pre-trained on the RGB modality, thereby limiting their performance on other modalities, such as infrared, depth, and event data, which are crucial for complex scenarios. To address…

Reinforcement learning (RL) is becoming an important direction for post-training vision-language models (VLMs), but public training methodologies for unified multimodal RL remain much less mature, especially for heterogeneous reasoning and…

Medical vision--language models (VLMs) are usually evaluated on intact image--question pairs, but trustworthy clinical use requires a stronger property: a model must recognise when the evidential basis for an answer has failed. We study…

Providing timely, rubric-aligned feedback on student-drawn diagrams is a persistent challenge in STEM education. While large multimodal models (LMMs) can jointly parse images and generate explanations, their tendency to hallucinate…

Visual Question Answering (VQA) is a challenging task of predicting the answer to a question about the content of an image. Prior works directly evaluate the answering models by simply calculating the accuracy of predicted answers. However,…

Physics education researchers are interested in using the tools of machine learning and natural language processing to make quantitative claims from natural language and text data, such as open-ended responses to survey questions. The…

Recent advances in Multi-Modal Large Language Models (MLLMs) have enabled unified processing of language, vision, and structured inputs, opening the door to complex tasks such as logical deduction, spatial reasoning, and scientific…

Chain-of-thought (CoT) distillation trains a smaller model to imitate a teacher's reasoning trace, but it is typically evaluated by final-answer metrics including accuracy. We ask whether gains in answer quality are accompanied by…

Multimodal large language models (MLLMs) have shown promising reasoning abilities, yet evaluating their performance in specialized domains remains challenging. STEM reasoning is a particularly valuable testbed because it provides highly…

We present Datarus-R1-14B, a 14 B-parameter open-weights language model fine-tuned from Qwen 2.5-14B-Instruct to act as a virtual data analyst and graduate-level problem solver. Datarus is trained not on isolated question-answer pairs but…