{"ID":2827657,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2512.16975","arxiv_id":"2512.16975","title":"InfoTok: Adaptive Discrete Video Tokenizer via Information-Theoretic Compression","abstract":"Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redundancy or information loss. Drawing inspiration from Shannon's information theory, this paper introduces InfoTok, a principled framework for adaptive video tokenization. We rigorously prove that existing data-agnostic training methods are suboptimal in representation length, and present a novel evidence lower bound (ELBO)-based algorithm that approaches theoretical optimality. Leveraging this framework, we develop a transformer-based adaptive compressor that enables adaptive tokenization. Empirical results demonstrate state-of-the-art compression performance, saving 20% tokens without influence on performance, and achieving 2.3x compression rates while still outperforming prior heuristic adaptive approaches. By allocating tokens according to informational richness, InfoTok enables a more compressed yet accurate tokenization for video representation, offering valuable insights for future research.","short_abstract":"Accurate and efficient discrete video tokenization is essential for long video sequences processing. Yet, the inherent complexity and variable information density of videos present a significant bottleneck for current tokenizers, which rigidly compress all content at a fixed rate, leading to redundancy or information l...","url_abs":"https://arxiv.org/abs/2512.16975","url_pdf":"https://arxiv.org/pdf/2512.16975v3","authors":"[\"Haotian Ye\",\"Qiyuan He\",\"Jiaqi Han\",\"Puheng Li\",\"Jiaojiao Fan\",\"Zekun Hao\",\"Fitsum Reda\",\"Yogesh Balaji\",\"Huayu Chen\",\"Sheng Liu\",\"Angela Yao\",\"James Zou\",\"Stefano Ermon\",\"Haoxiang Wang\",\"Ming-Yu Liu\"]","published":"2025-12-18T17:13:59Z","proceeding":"cs.CV","tasks":"[\"cs.CV\",\"cs.AI\"]","methods":"[\"Transformer\"]","has_code":false}