8 papers · 1 filter
Test-Time Registers as Global Priors for Tokenized Image Generation
Cheng-Yao Hong, Yifan Wang, Yuewei Lin +1
Attention-based models often develop attention sinks, where a small number of tokens repeatedly attract attention and accumulate unusually large activations. In vision transformers…
HorizonForge: Driving Scene Editing with Any Trajectories and Any Vehicles
Yifan Wang, Francesco Pittaluga, Zaid Tasneem +3
Controllable driving scene generation is critical for realistic and scalable autonomous driving simulation, yet existing approaches struggle to jointly achieve photorealism and pre…
Supervise Less, See More: Training-free Nuclear Instance Segmentation with Prototype-Guided Prompting
Wen Zhang, Qin Ren, Wenjing Liu +2
Accurate nuclear instance segmentation is a pivotal task in computational pathology, supporting data-driven clinical insights and facilitating downstream translational applications…
Scale Where It Matters: Training-Free Localized Scaling for Diffusion Models
Qin Ren, Yufei Wang, Lanqing Guo +3
Diffusion models have become the dominant paradigm in text-to-image generation, and test-time scaling (TTS) improves sample quality by allocating additional computation at inferenc…
Together, Then Apart: Balancing Alignment and Distinctiveness for Multimodal Survival Analysis
Wenjing Liu, Qin Ren, Wen Zhang +2
Multimodal survival analysis aims to improve cancer prognosis using heterogeneous biomedical data, such as histopathology images and genomic profiles. A common strategy is to align…
VisReason: A Large-Scale Dataset for Visual Chain-of-Thought Reasoning
Lingxiao Li, Yifan Wang, Xinyan Gao +3
Chain-of-Thought (CoT) prompting has proven remarkably effective for eliciting complex reasoning in large language models (LLMs). Yet, its potential in multimodal large language mo…