Soft Injection of Task Embeddings Outperforms Prompt-Based In-Context Learning Paper • 2507.20906 • Published Jul 28, 2025 • 2
ReFlex: Text-Guided Editing of Real Images in Rectified Flow via Mid-Step Feature Extraction and Attention Adaptation Paper • 2507.01496 • Published Jul 2, 2025 • 4
An Image Grid Can Be Worth a Video: Zero-shot Video Question Answering Using a VLM Paper • 2403.18406 • Published Mar 27, 2024 • 2