paper-with-me

Papers

Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge

2025-09-07 · Hao Liang, Ruitao Wu, Bohan Zeng, Junbo Niu, Wentao Zhang, Bin Dong arxiv

Multimodal reasoning remains a fundamental challenge in artificial intelligence. Despite substantial advances in text-based reasoning, even state-of-the-art models such as GPT-o3 struggle to maintain strong performance in multimodal scenarios. To address this gap, we introduce a caption-assisted reasoning framework that effectively bridges visual and textual modalities. Our approach achieved 1st place in the ICML 2025 AI for Math Workshop \& Challenge 2: SeePhys, highlighting its effectiveness and robustness. Furthermore, we validate its generalization on the MathVerse benchmark for geometric reasoning, demonstrating the versatility of our method. Our code is publicly available at https://github.com/OpenDCAI/SciReasoner.

📄 PDF Abstract BibTeX arXiv:2509.06079

Code (0)

등록된 구현이 없습니다.

Tasks

Multimodal Reasoning

Similar Papers 제목 키워드 기반

MLLM-Assisted Audio VOS: A 3rd Place Report for the MeViS-Audio Track, 8th LSVOS Challenge

2026-08-24 · Liangtao Shi, Jinxia Xie, Xiantao Hu, Ting Liu arxiv

In this technical report, we present a training-free framework for audio-guided video object segmentation, which integrates Multimodal Large Language Models (MLLMs) with SAM-based segmentation models. We decompose the ta…

Video Object SegmentationMultimodal ReasoningVideo Segmentation

Memory Bear AI Memory Science Engine for Multimodal Affective Intelligence: A Technical Report

2026-03-18 · Deliang Wen, Ke Sun, Yu Wang arxiv

Affective judgment in real interaction is rarely a purely local prediction problem. Emotional meaning often depends on prior trajectory, accumulated context, and multimodal evidence that may be weak, noisy, or incomplete…

Multimodal Emotion Recognition

1$^{st}$ Place Solution of WWW 2025 EReL@MIR Workshop Multimodal CTR Prediction Challenge

2025-05-06 · Junwei Xu, Zehao Zhao, Xiaoyu Hu, Zhenjie Song

The WWW 2025 EReL@MIR Workshop Multimodal CTR Prediction Challenge focuses on effectively applying multimodal embedding features to improve click-through rate (CTR) prediction in recommender systems. This technical repor…

Click-Through Rate PredictionRecommendation SystemsTask 2

MARS: Technical Report for the CASTLE Challenge at EgoVis 2026

2026-05-18 · Haoyu Zhang, Qiaohui Chu, Yisen Feng, Meng Liu 외 arxiv

This report presents MARS, short for Multimodal Agentic Reasoning with Source selection, our system for the CASTLE Challenge at EgoVis 2026. Participants must answer 185 closed-form questions over the CASTLE 2024 dataset…

Can Multimodal LLMs See Science Instruction? Benchmarking Pedagogical Reasoning in K-12 Classroom Videos

2026-02-08 · Yixuan Shen, Peng He, Honglu Liu, Jinxuan Fan 외 arxiv

K-12 science classrooms are rich sites of inquiry where students coordinate phenomena, evidence, and explanatory models through discourse; yet, the multimodal complexity of these interactions has made automated analysis …