作者位次 #3/6ACL 2026Poster· Natural Language Processing
Look Less, Reason More: Rollout-Guided Adaptive Pixel-Space Reasoning
Xuchen Li · Xuzhao Li · Jiahui Gao · Renjie Pi · Shiyu Hu · Wentao Zhang
摘要
Vision-Language Models (VLMs) excel at many multimodal tasks, yet they frequently struggle with tasks requiring precise understanding and handling of fine-grained visual elements. This is mainly due to information loss during image encoding or insufficient attention to critical regions. Recent wo...