phenomenon · first seen 4 Oct 2026
multimodal large language model physics reasoning
Also: LMMs, MLLM, multimodal LLM, multimodal language models, multimodal large language model, multimodal large language model vision encoder, multimodal large language model concept proposal
Evaluating whether multimodal models can infer governing physical laws and parameters from visual observations.
The label pairs multimodal large language models with physics reasoning, but the sources don't support that pairing. None of the sampled papers or repositories deal with inferring physical laws or parameters from visual observations. They are general MLLM work: visual token pruning and compression, hallucination detection in aerial captioning, remote sensing classification, RGB-thermal fusion, visual search psychophysics, vision-language navigation, a robot-painting benchmark and layer-connection schemes. The cluster looks like the umbrella term "MLLM" merged with one narrower sub-topic. MLLMs themselves are a broad, long-mainstream research area, and the falling growth figures fit ordinary background publication volume rather than a specific rising idea.
Physics-law inference from video by multimodal models could become a distinct benchmark topic, but these sources give no evidence for it. As extracted, the cluster only reflects the general MLLM literature.
Analyst note (not a concept), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Human-Like Attention? A Psychophysical Comparison of Visual Search in Humans and MLLMsPapers · 4 Oct 2026 · Renchi Zhang, Joost C. F. de Winter, Dimitra Dodou, Harleigh C. Seyffert, Yke Ba…
- From Transformation to Target State: Rethinking Query Representation for Zero-Shot Composed Image RetrievalPapers · 5 Oct 2026 · Yihe Zhao, Songhe Feng
- DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language ModelsPapers · 6 Oct 2026 · Shuo Yang, Changbai Li, Linlin Yang, Huobin Tan, Rongyu Chen, Tongfei Chen, Tian…
- RSJEV: Discriminative Remote Sensing Scene Classification with Multimodal Large Language ModelsPapers · 6 Oct 2026 · Dongchen Si, Di Wang, Mingzhen Xu, Jing Zhang, Bo Du, Liangpei Zhang
- From Pixel to Coding: Evaluating the Figure Reproduction Capabilities of MLLMsPapers · 7 Oct 2026 · Zijian Chen, Zhengyu Chen, Bohan Liang, Lirong Deng, Yushuo Zheng, Yanwei Jiang,…
- Open-MMUnlearning: Unifying Methods and Evaluation for MLLM UnlearningPapers · 7 Oct 2026 · Junkai Chen, Yuhao He, Qianshan Wei, Junxiang You, Jingwen Shao, Junkai Lin, Zho…
Latest sources
- Out of Sight, Into Memory: Compact Visual Latents Retain Local Evidence in Ultra-High-Resolution Remote SensingPapers · 16 Nov 2026 · Meng Tang, Siyuan Du, Yuxin Liu, Shuaishuai Cao, Di Wang, Haonan Guo
- Visual Marking as a Native Reasoning Capability for Multimodal LLMsPapers · 15 Nov 2026 · Jiazhen Liu, Yanghao Wang, Chaolei Tan, Long Chen
- Glance, then Select: Evidence-Tempered Visual Token Selection for Extremely Compressed Multimodal LLMsPapers · 15 Nov 2026 · Yuxuan Wang, Guangxiang Zhao, Yuxuan Tian, Yahui Han, Xinyu Tan, Feiyu Wang, Zon…
- TIVS: Mapping the Sensitivity Landscape of Visual Token Transformations in MLLMsPapers · 15 Nov 2026 · Yikang Qiao, Jianye Zeng, Duan Huang, Ziying Song
- Beyond Paired Inputs: Learning to Leverage RGB-T Cross-Modal Relations in Multimodal Large Language ModelsPapers · 14 Nov 2026 · Tianyi Zhao, Qihao Xu, Jiawen Xi, Duanni Meng, Bo Zhao, Maoxun Yuan, Xingxing We…
- Fine-Grained Generative Hallucination Detection and Correction for Aerial Image CaptioningPapers · 11 Nov 2026 · Debolena Basak, Somsubhra De, Maunendra Sankar Desarkar
- Reading the Unreadable: Text-Aware Image Super-Resolution Needs ReasoningPapers · 11 Nov 2026 · Jaeseong Lee, Jinwoo Kim, Jinho Jeong, Seon Joo Kim
- Semantic Consistency of Vision Tokens: A Vision-Centric Perspective on Multimodal Large Language ModelsPapers · 11 Nov 2026 · Nikola Đukić, Tim Lebailly, Tinne Tuytelaars
- Layer Roles Matter: Mitigating Modality Imbalance in Multimodal Emotion Reasoning via Adaptive Layer ProfilingPapers · 9 Nov 2026 · Pengyu Huang, Peipei Song, Beier Zhu, Zhiyuan Han, Jinpeng Hu, Xun Yang
- Tiny Evidence Region Localization with Selective Contrastive On-Policy Self-DistillationPapers · 7 Nov 2026 · Yujuan Pang, Wenhao Xu, Yinglei Teng
- Seeing Isn't Enough: Unlocking Visual Reasoning by Bridging the Reasoning-Access Gap with TIGERPapers · 7 Nov 2026 · Gregory Kang Ruey Lau, Minh Huynh Nguyen, Bryan Kian Hsiang Low
- Measurement-Aware Multimodal LLM for No-Reference Low-Dose CT Quality AssessmentPapers · 5 Nov 2026 · Kerem Basim, Tolga Demiroglu, Mehmet Ozan Unal, Metin Ertas, Isa Yildirim