2 papers
cs.IT2026
Video TokenCom: Textual Intent-Guided Multi-Rate Video Token Communications with UEP-Based Adaptive Source-Channel Coding
Jingxuan Men, Mahdi Boloursaz Mashhadi, Ning Wang +3
Token Communication (TokenCom) is a new paradigm, motivated by the recent success of Large AI Models (LAMs) and Multimodal Large Language Models (MLLMs), where tokens serve as unif…
cs.CV2025
Investigating and Enhancing the Robustness of Large Multimodal Models Against Temporal Inconsistency
Jiafeng Liang, Shixin Jiang, Xuan Dong +7
Large Multimodal Models (LMMs) have recently demonstrated impressive performance on general video comprehension benchmarks. Nevertheless, for broader applications, the robustness o…