3 papers
cs.CV2026
TimeBlind: A Spatio-Temporal Compositionality Benchmark for Video LLMs
Baiqi Li, Kangyi Zhao, Ce Zhang +3
Fine-grained spatio-temporal understanding is essential for video reasoning and embodied AI. Yet, while Multimodal Large Language Models (MLLMs) master static semantics, their gras…
cs.CV2025
Towards Reason-Informed Video Editing in Unified Models with Self-Reflective Learning
Xinyu Liu, Hangjie Yuan, Yujie Wei +9
Unified video models exhibit strong capabilities in understanding and generation, yet they struggle with reason-informed visual editing even when equipped with powerful internal vi…
cs.LG2025
Can LLMs Alleviate Catastrophic Forgetting in Graph Continual Learning? A Systematic Study
Ziyang Cheng, Zhixun Li, Yuhan Li +6
Nowadays, real-world data, including graph-structure data, often arrives in a streaming manner, which means that learning systems need to continuously acquire new knowledge without…