用离散余弦变换压缩视觉思考，实现轻量级多模态推理
Spectral-Progressive Thought Flow for Lightweight Multimodal Reasoning
- 将视觉中间状态映射到固定大小的离散余弦空间，减少计算开销
- 在保持布局结构前提下，仅在需要时引入高频细节，提升精度
- 适合长序列推理任务，尤其对内存和延迟敏感的场景
多模态空间推理常依赖大量中间文本与视觉思考，导致计算和内存开销巨大。为此，我们提出谱渐进思维流（SpecFlow），一种轻量级多模态空间推理框架，将中间视觉思考表示在固定尺寸的离散余弦空间中。通过利用强能量压缩特性，SpecFlow 在保留全局布局与关系结构的同时，仅在需要更高空间精度时引入高频细节。为使视觉状态演化与语言意图对齐，采用无分类器引导，让自回归文本思考驱动基于流的视觉工作区更新，无需扩展上下文。结果，SpecFlow 维持有界视觉工作区，其更新仅依赖当前视觉状态与累积文本轨迹，实现长时推理下的稳定延迟与独立于推理深度的内存使用。实证表明，SpecFlow 在推理性能上达到或超越基线，同时将计算量和键值缓存成本降低最多达2.1倍。
原文摘要 · Abstract (English)
Multimodal spatial reasoning often relies on long chains of intermediate textual and visual thoughts, where accumulating visual tokens and dense cross-modal attention incur substantial computation and memory overhead. To address this challenge, we propose Spectral-Progressive Thought Flow (SpecFlow), a novel lightweight multimodal spatial reasoning framework that represents intermediate visual thoughts in a fixed-size discrete cosine space. By exploiting strong energy compaction, SpecFlow preserves global layout and relational structure while introducing high-frequency details only when increased spatial precision is required. To align visual state evolution with linguistic intent, classifier-free guidance enables autoregressive textual thoughts to steer flow-based updates of the visual workspace/state without expanding the context. As a result, SpecFlow maintains a bounded visual workspace whose updates depend only on the current visual state and accumulated textual trace, enabling long-horizon inference with stable latency and memory usage independent of reasoning depth. Empirical results show that SpecFlow achieves competitive or superior reasoning performance while reducing computation and KV cache costs by up to 2.1 times.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。