2 papers
cs.AI2025
Hallucination as a Computational Boundary: A Hierarchy of Inevitability and the Oracle Escape
Wang Xi, Quan Shi, Zenghui Ding +2
The illusion phenomenon of large language models (LLMs) is the core obstacle to their reliable deployment. This article formalizes the large language model as a probabilistic Turin…
cs.CV2025
Beyond Training: Dynamic Token Merging for Zero-Shot Video Understanding
Yiming Zhang, Zhuokai Zhao, Zhaorun Chen +3
Recent advancements in multimodal large language models (MLLMs) have opened new avenues for video understanding. However, achieving high fidelity in zero-shot video tasks remains c…