transformer layers

5 papers

• Memory-Efficient Visual Autoregressive Modeling with Scale-Aware KV Cache Compression
• RadZero: Similarity-Based Cross-Attention for Explainable Vision-Language Alignment in Chest X-ray with Zero-Shot Multi-Task Capability
• System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
• Visual Thoughts: A Unified Perspective of Understanding Multimodal Chain-of-Thought
• When Semantics Mislead Vision: Mitigating Large Multimodal Models Hallucinations in Scene Text Spotting and Understanding