2 papers
cs.CV2026
Data Organization Matters in Multimodal Instruction Tuning: A Controlled Study of Capability Trade-offs
Guowei Tang
Recent multimodal large language models (MLLMs) perform strongly on general visual understanding, diagram and chart reasoning, and document-centric perception. However, these abili…
cs.CV2026
StreamingEval: A Unified Evaluation Protocol towards Realistic Streaming Video Understanding
Guowei Tang, Tianwen Qian, Huanran Zheng +2
Real-time, continuous understanding of visual signals is essential for real-world interactive AI applications, and poses a fundamental system-level challenge. Existing research on…