Showing cs.CVShow all
2 papers · 1 filter
cs.CV2026
Context Tokens are Anchors: Understanding the Repetition Curse in dMLLMs from an Information Flow Perspective
Qiyan Zhao, Xiaofeng Zhang, Shuochen Chang +7
Recent diffusion-based Multimodal Large Language Models (dMLLMs) suffer from high inference latency and therefore rely on caching techniques to accelerate decoding. However, the ap…
cs.CV2025
Affordance-First Decomposition for Continual Learning in Video-Language Understanding
Mengzhu Xu, Hanzhi Liu, Ningkang Peng +2
Continual learning for video--language understanding is increasingly important as models face non-stationary data, domains, and query styles, yet prevailing solutions blur what sho…