{"ID":5551958,"CreatedAt":"2026-07-02T01:54:51.863792489Z","UpdatedAt":"2026-07-08T07:18:47.304504717Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.00461","arxiv_id":"2607.00461","title":"Multimodal Continuous Reasoning via Asymmetric Mutual Variational Learning","abstract":"Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous latent reasoning, where the goal is to discover implicit reasoning pathways that bridge the multimodal query and the final answer. However, this introduces a severe train-inference mismatch: a training-time posterior, conditioned on the ground-truth answer, can exploit answer-dependent shortcuts. Standard variational training then forces the inference-time prior to mimic a posterior that has access to information unavailable at test time, leading to poor performance. To address this, we propose Asymmetric Mutual Variational Learning (AMVL), a framework that resolves this mismatch via a bidirectional calibration objective. A forward KL divergence trains the target-agnostic prior to match the posterior, while a novel reverse KL divergence simultaneously regularizes the posterior, preventing it from collapsing into inference-incompatible regions and mitigating this ``answer leakage''. We provide theoretical analysis formalizing this leakage as prior contamination and prove that our dual-KL objective reduces it. We instantiate AMVL in a latent-integrated MLLM and show that it consistently outperforms strong discrete and latent-reasoning baselines, improving the average score on the complex BLINK benchmark by +10.83 and achieving gains of up to +32.00 on individual reasoning tasks, with analyses confirming improved latent-space stability.","short_abstract":"Multimodal Large Language Models (MLLMs) are often constrained by a language-space bottleneck, forcing complex visual reasoning into discrete tokens which can lose perceptual nuance. A promising alternative is continuous latent reasoning, where the goal is to discover implicit reasoning pathways that bridge the multimo...","url_abs":"https://arxiv.org/abs/2607.00461","url_pdf":"https://arxiv.org/pdf/2607.00461v1","authors":"[\"Shijie Li\",\"Yilin Gao\",\"Siyuan Yang\",\"Tieyuan Chen\",\"Chaofan Gan\",\"Zhihao He\",\"Zicheng Zhao\",\"Yuyu Guo\",\"Weiyao Lin\",\"Hang Yu\"]","published":"2026-07-01T05:29:02Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[\"Large Language Model\",\"Language Model\"]","has_code":false}