大模型评估常浪费采样算力，这项研究用贝叶斯最优停止动态决定何时收手，兼顾精度与成本，是做评测必读的思路。
arXiv:2608.14425v1 Announce Type: new Abstract: LLM evaluations often use fixed sampling budgets, testing every item the same number of times even aft…
采样多样性如何左右大模型推理扩展的缩放规律？这项研究给出了新视角。
arXiv:2502.11027v5 Announce Type: replace Abstract: Large language model (LLM) scaling inference is key to unlocking greater performance, and leveragi…
用大模型先验给冷启动推荐装上导航，汤普森采样不再盲猜，评论推荐效率起飞。
arXiv:2608.03382v1 Announce Type: cross Abstract: Multi-armed bandit algorithms, especially Thompson sampling, are widely used in online recommendatio…
大模型做智能体时竟无法可靠随机采样？这份研究揭示隐性缺陷，值得每个Agent开发者警惕。
arXiv:2604.06543v2 Announce Type: replace-cross Abstract: In this work, we demonstrate that reliable stochastic sampling is a fundamental yet unfulfil…
解析采样温度在LLM强化学习训练中的实际作用，控制实验揭示关键机制。
Article URL: https://medium.com/@shizhanszh34/what-sampling-temperature-actually-does-in-llm-rl-training-a-controlled-study-of-temperature-a1f710e32a3…
汇顶发布柔性OLED触控芯片GT9926，支持4000Hz瞬时采样率，下半年旗舰手机大规模商用
IT之家 7 月 20 日消息，汇顶科技今日宣布，全新柔性 OLED 触控芯片 GT9926 将于下半年发布的旗舰和游戏手机上大规模商用。 据官方介绍，全新芯片架构带来行业优异的 480Hz 多指采样率和 4000Hz 瞬时采样率 ，点击响应更快，开镜射击更跟手；全新的硬件降噪，让信噪比较上代提升了…
专为LLM代理打造的列式存储可观测性方案，无采样全量追踪，每百万仅需10美元，有效应对非确定性调试痛点。
Hi HN, we're Kiran and Vijay! Over the past two years, we have built a columnar storage engine for observability: logs, metrics, and traces. Today, it…
无需训练的LLM推理新方法：深度熵引导采样，提升推理效率与质量。
arXiv:2607.09693v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become the dominant paradigm for improving the reasoning capabilitie…
用张量列低秩分解攻克扩散模型高维采样难题，带来理论与计算效率双重飞跃。
arXiv:2607.06841v1 Announce Type: cross Abstract: Diffusion models offer a powerful framework for sampling from complex probability densities by learn…
用动态偏好调优扩散采样器，D2PO在ECCV 2026提出创新方案，让AI绘画更高效精准。
arXiv:2607.06609v1 Announce Type: cross Abstract: We propose D2PO (Dynamic Direct Preference Optimization), a principled framework for optimizing diff…
单次采样异步优化刷新智能体强化学习效率，直击多步决策计算瓶颈，值得算法研究者细读。
arXiv:2607.07508v1 Announce Type: cross Abstract: Reinforcement learning (RL) is becoming increasingly important for post-training large language mode…
用张量训练联合建模突破离散扩散采样瓶颈，少步生成也能保持高质量，值得关注的前沿技术。
arXiv:2607.03788v1 Announce Type: new Abstract: Discrete diffusion promises orders-of-magnitude faster generation than autoregressive (AR) models for …
大模型模拟受访者出新招，跨调查迁移能否突破个体预测瓶颈？评估缺陷被直指，值得一读。
arXiv:2607.03091v1 Announce Type: new Abstract: Silicon sampling-using large language models (LLMs) to simulate human survey respondents-has emerged a…
反问题求解新方案，测量感知一致性采样，兼顾速度与精度，值得关注。
arXiv:2510.02208v3 Announce Type: replace-cross Abstract: Diffusion models have emerged as powerful generative priors for solving inverse imaging prob…
离散扩散模型采样提速新突破，并行时间采样让生成效率大幅跃升。
arXiv:2607.00773v1 Announce Type: new Abstract: Discrete diffusion models are widely used for learning and generating discrete distributions. As the g…
用LLM聚类实现实时难负样本采样，直击双塔检索训练瓶颈，规模越大收益越明显。
arXiv:2607.00448v1 Announce Type: cross Abstract: The two-tower model has been widely used for large-scale recommendation systems, particularly in the…
自洽性推理如何选样本更高效？新研究给出最优策略，大幅降低计算成本。
arXiv:2511.12309v2 Announce Type: replace-cross Abstract: Self-consistency (SC) is a widely used test-time inference technique for improving performan…
提出多范围视觉重采样方法，显著提升多模态大语言模型的效率与性能。
arXiv:2606.31383v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) typically employ resampling-based projectors to transform den…
为流模型注入即插即用的动量引导，无需重新训练即可提升生成质量，让采样更精准可控。
arXiv:2602.20360v2 Announce Type: replace Abstract: Flow-based generative methods offer a simple and effective framework for high-fidelity generation,…
把大模型反馈当“文本梯度”，用采样动量解决提示词优化的扩展与稳定性问题，方法新颖且直击痛点。
arXiv:2506.00400v4 Announce Type: replace Abstract: LLM-based prompt optimization, which uses LLM-provided ``textual gradients'' (feedback) to refine …