State-of-the-art vision-language models (VLMs) suffer from a critical failure in understanding negation, often referred to as affirmative bias. This limitation is particularly severe in described object detection (DOD) tasks. To address this, we propose two primary contributions: (1) a new dataset pipeline and (2) a novel, lightweight adaptation recipe. First, we introduce CoVAND, a dataset constructed with a systematic chain-of-thought (CoT) and VQA-based pipeline to generate high-quality, instance-grounded negation data. Second, we propose NegToMe, a novel text token merging module that directly tackles the architectural cause of affirmative bias. NegToMe fundamentally addresses the structural loss of negation cues in tokenization, grouping them with attributes into coherent semantic phrases. It maintains correct polarity at the input level, enabling robust negation understanding even with limited data. For instance, to prevent a model from treating the fragmented tokens "not" and "girl" as simply "girl", NegToMe binds them into a single token whose meaning is correctly distinguished from that of "girl" alone. This module is integrated with a parameter-efficient and strategic LoRA fine-tuning approach. Our method significantly improves performance on challenging negation benchmarks with a lowered false positive rate, boosting NMS-AP by up to +10.8 points on OVDEval and demonstrating generalization to SoTA VLMs. This work marks a crucial step forward in addressing negation understanding for real-world detection applications.
Negation-Aware Test-Time Adaptation for Vision-Language Models
Department of AI Computing, Pengcheng Laboratory（人工智能计算系，鹏城实验室）；School of Computer Science and Technology, Central South University（计算机科学与技术学院，中南大学）；Department of Computer Science and Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University（计算机科学与技术系，人工智能研究院，BNRist中心，THBI实验室，清华-博世联合人工智能中心，清华大学）
University of Arkansas（阿肯色大学）；University of Science, VNU-HCM（胡志明市国家大学科学大学）；Aalto University（阿尔托大学）；SpexAI GmbH（SpexAI有限公司）；University of California, San Diego（加利福尼亚大学圣迭戈分校）
Bi-MCQ: Reformulating Vision-Language Alignment for Negation Understanding
Department of Electrical and Computer Engineering, Inha University, Republic of Korea（电气与计算机工程系，印哈大学，大韩民国）；College of Medicine, Inha University, Republic of Korea（医学学院，印哈大学，大韩民国）
HANCLIP: A Family of Hyperbolic Angular Negation Vision Language Models
ADAPT Centre Dublin City University, Ireland（爱尔兰都柏林城市大学ADAPT中心）；University of East Anglia Norwich, UK（英国东英吉利大学）；Queen’s University Belfast Belfast, UK（英国贝尔法斯特女王大学）；University of Science Vietnam National University Ho Chi Minh City, Vietnam（越南胡志明市国家大学理科大学）
Investigating Cross-Modal Skill Injection: Scenarios, Methods, and Hyperparameters
State Key Laboratory for Multimedia Information Processing, School of Computer Science, Peking University（多媒体信息处理国家重点实验室，计算机科学学院，北京大学）；WeChat AI, Tencent Inc., China（腾讯公司，中国）；The University of Hong Kong（香港大学）
FRISM: Fine-Grained Reasoning Injection via Subspace-Level Model Merging for Vision-Language Models
College of Future Information Technology, Fudan University, Shanghai, China（复旦大学未来信息科技学院，中国）；Shanghai Innovation Institute, China（上海创新研究院，中国）；The Chinese University of Hong Kong, China（香港中文大学，中国）；Harbin Institute of Technology, China（哈尔滨工业大学，中国）；Shanghai Artificial Intelligence Laboratory, China（上海人工智能实验室，中国）；Sun Yat-Sen University, Shenzhen, China（暨南大学深圳校区，中国）
Scale Can't Overcome Pragmatics: The Impact of Reporting Bias on Vision-Language Reasoning
University of Washington（华盛顿大学）；University of California, Los Angeles（加州大学洛杉矶分校）；Samaya AI（Samaya人工智能）；Mistral AI（Mistral人工智能）；Allen Institute for AI（人工智能研究所）
Know "No" Better: A Data-Driven Approach for Enhancing Negation Awareness in CLIP
Department of Electrical and Computer Engineering, Seoul National University（首尔国立大学电子与计算机工程系）；Amazon（亚马逊）；Samsung Research（三星研究院）；School of Computer Science and Engineering, Soongsil University（顺天大学计算机科学与工程学院）；IPAI, AIIS, ASRI, INMC, and ISRC, Seoul National University（首尔国立大学IPAI、AIIS、ASRI、INMC和ISRC）
SEP: Self-Enhanced Prompt Tuning for Visual-Language Model
Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所）；Institute of Computing Technology, Chinese Academy of Sciences（中国科学院计算技术研究所）；Tianjin University of Technology（天津理工大学）；University of Science and Technology of China（中国科学技术大学）
