8 papers · 1 filter
OneDrive: Unified Multi-Paradigm Driving with Vision-Language-Action Models
Yiwei Zhang, Xuesong Chen, Jin Gao +5
Vision-Language Models(VLMs) excel at autoregressive text generation, yet end-to-end autonomous driving requires multi-task learning with structured outputs and heterogeneous decod…
NTIRE 2026 The 3rd Restore Any Image Model (RAIM) Challenge: Professional Image Quality Assessment (Track 1)
Guanyi Qin, Jie Liang, Bingbing Zhang +50
In this paper, we present an overview of the NTIRE 2026 challenge on the 3rd Restore Any Image Model in the Wild, specifically focusing on Track 1: Professional Image Quality Asses…
SEATrack: Simple, Efficient, and Adaptive Multimodal Tracker
Junbin Su, Ziteng Xue, Shihui Zhang +3
Parameter-efficient fine-tuning (PEFT) in multimodal tracking reveals a concerning trend where recent performance gains are often achieved at the cost of inflated parameter budgets…
Low-Data Supervised Adaptation Outperforms Prompting for Cloud Segmentation Under Domain Shift
Harshith Kethavath, Weiming Hu
Adapting vision-language models to remote sensing imagery presents a fundamental challenge: both the visual and linguistic distributions of satellite data lie far outside natural i…
Making MLLMs Blind: Adversarial Smuggling Attacks in MLLM Content Moderation
Zhiheng Li, Zongyang Ma, Yuntong Pan +8
Multimodal Large Language Models (MLLMs) are increasingly being deployed as automated content moderators. Within this landscape, we uncover a critical threat: Adversarial Smuggling…
Beyond Semantic Search: Towards Referential Anchoring in Composed Image Retrieval
Yuxin Yang, Yinan Zhou, Yuxin Chen +6
Composed Image Retrieval (CIR) has demonstrated significant potential by enabling flexible multimodal queries that combine a reference image and modification text. However, CIR inh…
Beyond Dataset Distillation: Lossless Dataset Concentration via Diffusion-Assisted Distribution Alignment
Tongfei Liu, Yufan Liu, Bing Li +1
The high cost and accessibility problem associated with large datasets hinder the development of large-scale visual recognition systems. Dataset Distillation addresses these proble…
Arbitrary Ratio Feature Compression via Next Token Prediction
Yufan Liu, Daoyuan Ren, Zhipeng Zhang +4
Feature compression is increasingly important for improving the efficiency of downstream tasks, especially in applications involving large-scale or multi-modal data. While existing…