基于非对称互变分学习的多模态连续推理

摘要

多模态大语言模型（MLLMs）常受限于语言空间瓶颈，被迫将复杂的视觉推理压缩为离散词元，从而丢失感知细节。一个颇具前景的替代方案是连续潜在推理，其目标是发现连接多模态查询与最终答案的隐式推理路径。然而，这引入了严重的训练-推理不匹配问题：训练时基于正确答案的后验可以依赖答案相关的捷径，而标准的变分训练迫使推理时的先验去模仿一个在测试时无法获取的信息后验，导致性能不佳。为此，我们提出非对称互变分学习（AMVL），该框架通过双向校准目标解决了这一不匹配问题。前向KL散度训练与答案无关的先验去匹配后验，而新颖的反向KL散度同时正则化后验，防止其坍缩至与推理不相容的区域，并缓解这种“答案泄露”。我们提供了理论分析，将这种泄露形式化为先验污染，并证明我们的双KL目标能减少该泄露。我们在一个集成潜在表示的MLLM中实例化AMVL，并展示其在强基准（包括离散与潜在推理方法）上的持续优势：在复杂BLINK基准上平均得分提升+10.83，在单个推理任务上提升高达+32.00，分析结果也证实了潜在空间稳定性的改善。

English

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.