Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866908384368787456 |
|---|---|
| author | Man, Yunze Huang, De-An Liu, Guilin Sheng, Shiwei Liu, Shilong Gui, Liang-Yan Kautz, Jan Wang, Yu-Xiong Yu, Zhiding |
| author_facet | Man, Yunze Huang, De-An Liu, Guilin Sheng, Shiwei Liu, Shilong Gui, Liang-Yan Kautz, Jan Wang, Yu-Xiong Yu, Zhiding |
| contents | Recent advances in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks, yet they often struggle with vision-centric scenarios where precise visual focus is needed for accurate reasoning. In this paper, we introduce Argus to address these limitations with a new visual attention grounding mechanism. Our approach employs object-centric grounding as visual chain-of-thought signals, enabling more effective goal-conditioned visual attention during multimodal reasoning tasks. Evaluations on diverse benchmarks demonstrate that Argus excels in both multimodal reasoning tasks and referring object grounding tasks. Extensive analysis further validates various design choices of Argus, and reveals the effectiveness of explicit language-guided visual region-of-interest engagement in MLLMs, highlighting the importance of advancing multimodal intelligence from a visual-centric perspective. Project page: https://yunzeman.github.io/argus/ |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_23766 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought Man, Yunze Huang, De-An Liu, Guilin Sheng, Shiwei Liu, Shilong Gui, Liang-Yan Kautz, Jan Wang, Yu-Xiong Yu, Zhiding Computer Vision and Pattern Recognition Recent advances in multimodal large language models (MLLMs) have demonstrated remarkable capabilities in vision-language tasks, yet they often struggle with vision-centric scenarios where precise visual focus is needed for accurate reasoning. In this paper, we introduce Argus to address these limitations with a new visual attention grounding mechanism. Our approach employs object-centric grounding as visual chain-of-thought signals, enabling more effective goal-conditioned visual attention during multimodal reasoning tasks. Evaluations on diverse benchmarks demonstrate that Argus excels in both multimodal reasoning tasks and referring object grounding tasks. Extensive analysis further validates various design choices of Argus, and reveals the effectiveness of explicit language-guided visual region-of-interest engagement in MLLMs, highlighting the importance of advancing multimodal intelligence from a visual-centric perspective. Project page: https://yunzeman.github.io/argus/ |
| title | Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2505.23766 |