2 papers
cs.CV2026
Images in Sentences: Scaling Interleaved Instructions for Unified Visual Generation
Yabo Zhang, Kunchang Li, Dewei Zhou +2
While recent advancements in multimodal language models have enabled image generation from expressive multi-image instructions, existing methods struggle to maintain performance un…
cs.CV2026
High-Resolution Visual Reasoning via Multi-Turn Grounding-Based Reinforcement Learning
Xinyu Huang, Yuhao Dong, Weiwei Tian +3
State-of-the-art large multi-modal models (LMMs) face challenges when processing high-resolution images, as these inputs are converted into enormous visual tokens, many of which ar…