ML + Vision Top-6 Agent Survey - ICCV 2025 - Page 6 of 6¶

Papers

AVAM: A Universal Training-Free Adaptive Visual Anchoring Embedded into Multimodal Large Language Model for Multi-Image Question Answering Paper

Authors: Kang Zeng, Guojin Zhong, Jintao Cheng, Jin Yuan, Zhiyong Li
Year: 2025
Venue: IEEE International Conference on Computer Vision
DOI: 10.1109/ICCV51701.2025.00221
Citations: 0
Relevance: 3 / 5
Why selected: Heuristic keyword/alias matches: vision-language models (matched: multimodal large language model).
Code: Not found.
Extraction: method/data pending

Abstract

Not stated in metadata.

Claim

Not stated in abstract.

ReCot: Reflective Self-Correction Training for Mitigating Confirmation Bias in Large Vision-Language Models Paper

Authors: Mengxue Qu, Yibo Hu, Kunyang Han, Yunchao Wei, Yao Zhao
Year: 2025
Venue: IEEE International Conference on Computer Vision
DOI: 10.1109/ICCV51701.2025.00855
Citations: 0
Relevance: 3 / 5
Why selected: Heuristic keyword/alias matches: vision-language models (matched: vision language models, large vision language models).
Code: Not found.
Extraction: method/data pending

Abstract

Not stated in metadata.

Claim

Not stated in abstract.

Fuzzy Contrastive Decoding to Alleviate Object Hallucination in Large Vision-Language Models Paper

Authors: Jieun Kim, Jinmyeong Kim, Yoon Kim, Sunghyun Cho
Year: 2025
Venue: IEEE International Conference on Computer Vision
DOI: 10.1109/ICCV51701.2025.01913
Citations: 0
Relevance: 3 / 5
Why selected: Heuristic keyword/alias matches: vision-language models (matched: vision language models, large vision language models).
Code: Not found.
Extraction: method/data pending

Abstract

Not stated in metadata.

Claim

Not stated in abstract.