2 papers
cs.CV2026
Contrastive Heliophysical Image Pretraining for Solar Dynamics Observatory Records
Shiyu Shen, Zhe Gao, Taifeng Chai +2
Deep learning has revolutionized solar image analysis, yet most approaches train task-specific encoders from scratch or rely on natural-image pretraining that ignores the unique ch…
cs.CV2026
VideoTIR: Accurate Understanding for Long Videos with Efficient Tool-Integrated Reasoning
Zhe Gao, Shiyu Shen, Taifeng Chai +7
Existing Multimodal Large Language Models (MLLMs) often suffer from hallucinations in long video understanding (LVU), primarily due to the imbalance between textual and visual toke…