揭示LLM验证中不确定性信号的结构异质性，指出资源分配优化增益存在上限。
arXiv:2606.15841v1 Announce Type: new Abstract: Large language model (LLM) systems increasingly use uncertainty signals to allocate limited computatio…
提出Predict-then-Diffuse框架，根据计算预算自适应调整响应长度，显著提升扩散LLM推理效率与吞吐量。
arXiv:2605.04215v2 Announce Type: replace-cross Abstract: Diffusion-based Large Language Models (D-LLMs) represent a promising frontier in generative …
将推理预算设定问题重构为风险控制问题，在限制错误率的同时最小化计算量，用分布自由的方法自适应控制推理何时停下，既省Token又保精准。
arXiv:2602.03814v2 Announce Type: replace Abstract: Reasoning Large Language Models (LLMs) enable test-time scaling, with dataset-level accuracy impro…