潜在思维调整：通过潜在令牌中的融合信息连接上下文与推理
Latent Thoughts Tuning: Bridging Context and Reasoning with Fused Information in Latent Tokens
AI总结：
研究提出潜在思维调整（LT-Tuning）框架，通过重新定义潜在思维构建与部署方式，引入上下文预测融合机制，结合三阶段课程学习，实现潜在与显式思维模式动态切换，优于现有潜在推理基线，有效缓解特征崩溃并提升推理精度。
摘要：
虽然显式思维链（CoT）赋予大语言模型（LLMs）强大的推理能力，但它将模型的思维限制在离散的词汇空间中。最近，在连续潜在空间中的推理成为一种有前途的替代方案，但当前范式存在问题。我们提出潜在思维调整（LT-Tuning），一个重新定义潜在思维构建和部署方式的训练后框架。它引入上下文预测融合机制，结合渐进式三阶段课程学习管道，能在潜在和显式思维模式间动态切换。实验表明该方法优于现有潜在推理基线，有效缓解特征崩溃并实现稳健推理精度。
英文摘要：
While explicit Chain-of-Thought (CoT) equips Large Language Models (LLMs) with strong reasoning capabilities, it constrains the model's thoughts to a discrete vocabulary space. Recently, reasoning in continuous latent space has emerged as a promising alternative, but current paradigms suffer from feature collapse and instability due to distribution mismatch when recurrently reusing hidden states, or alignment issues when relying on assistant models. To address this, we propose Latent Thoughts Tuning (LT-Tuning), a post-training framework that redefines how latent thoughts are constructed and deployed. Instead of relying solely on raw hidden states, our method introduces a Context-Prediction-Fusion mechanism that jointly leverages contextual hidden states and predictive semantic guidance from the vocabulary embedding space. Combined with a progressive three-stage curriculum learning pipeline, LT-Tuning also enables dynamic switching between latent and explicit thinking modes. Experiments demonstrate that our method outperforms existing latent reasoning baselines, effectively mitigating feature collapse and achieving robust reasoning accuracy.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
