新研究揭示量化大语言模型的可靠性缩放定律，为部署经济高效且可信赖的AI模型提供理论依据。
arXiv:2607.10855v1 Announce Type: new Abstract: Quantization is a powerful strategy to build capable and resource-efficient large language models (LLM…
一篇探索生成式AI放大效应预测的前沿论文，从理论框架到实验验证均有突破性贡献。
arXiv:2509.08048v4 Announce Type: replace-cross Abstract: Generative networks are perfect tools to enhance the speed and precision of LHC simulations.…
用模糊推理动态调整私有区块链验证节点数量，解决资源浪费和性能瓶颈。
arXiv:2607.07901v1 Announce Type: cross Abstract: Private blockchain networks run with fixed node configurations that cannot adapt to changing workloa…
探讨LLM缩放能否提升社会模拟的保真度，揭示当前范式的局限与挑战
arXiv:2607.02464v1 Announce Type: new Abstract: Large Language Model (LLM) social simulations are a promising research method, but they are not yet fa…
捏合缩放代替逐层点击，树形导航的全新交互原型值得一试
I got this idea recently when I had to browse files more than usual and felt the pain: why do I need to click through every level when I want to drill…
视觉语言模型在测试时也能通过缩放计算量提升性能，这篇论文揭示了新的缩放规律。
arXiv:2606.28864v1 Announce Type: new Abstract: Test-time scaling is a paradigm where large models use additional compute at inference to achieve bett…
揭秘LLM训练中学习率缩放的非线性规律，为优化大模型训练过程提供全新理论视角。
arXiv:2606.29158v1 Announce Type: new Abstract: Learning-rate transfer can reduce the cost of training large language models: instead of sweeping lear…
揭示大模型优势源于约束引导推理，而非单纯规模扩大，颠覆传统认知。
arXiv:2606.26108v1 Announce Type: new Abstract: Larger language models consistently outperform smaller ones on reasoning benchmarks, yet the reasoning…
捏合手指即可压缩长文为摘要，扩开恢复细节，像操作照片一样阅读文字，体验新奇！
Photos have pinch-to-zoom; text doesn’t. This is a proof of concept where pinching out compresses prose into a skimmable summary and pinching in expan…
提出ReM-MoA机制，用推理记忆解决混合代理规模化难题，提升多智能体协作效率。
arXiv:2606.24437v1 Announce Type: new Abstract: Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents…
研究大模型在特定任务蒸馏中缩放定律，揭示蒸馏效率与模型规模、数据量的关系
arXiv:2606.24747v1 Announce Type: new Abstract: Large Language Models (LLMs) achieve strong performance across a growing range of domains, yet their s…
新方法REVES通过修订与验证增强训练，破解LLM测试时缩放与多步推理的错位难题。
arXiv:2606.18910v1 Announce Type: new Abstract: Test-time scaling via sequential revision has emerged as a powerful paradigm for enhancing Large Langu…
LLM置信度评分尺度（0-100）并非中性设计，新研究揭示其对元认知表现的显著影响。
arXiv:2603.09309v2 Announce Type: replace Abstract: Verbalized confidence, in which LLMs report a numerical certainty score, is widely used to estimat…
揭秘Transformer缩放定律背后的学习动力学与泛化机制，87页长文深度统一理论框架。
arXiv:2512.22088v3 Announce Type: replace-cross Abstract: The scaling law, a cornerstone of Large Language Model (LLM) development, predicts improveme…
提出可训练的平滑旋转变换与学习通道缩放，为LLM量化精度提升提供新思路
arXiv:2606.09927v1 Announce Type: cross Abstract: Post-training quantization (PTQ) is one of the most practical ways to reduce the serving cost of Lar…
揭秘数据混合对模型缩放的影响规律，为AI训练中的最优数据配比提供理论解释。
arXiv:2606.08167v1 Announce Type: new Abstract: Recent research has established empirical scaling laws to predict model performance on multi-domain da…
跨语言大模型代理中收益缩放如何塑造合作行为，揭示博弈论新视角
arXiv:2601.19082v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents that negotiate, …
用SVD低秩分解加学习缩放矩阵，实现高效LLM压缩，精准降维保性能。
arXiv:2606.07098v1 Announce Type: cross Abstract: We present SigmaScale, a method for learning auxiliary scaling matrices $S$ to aid truncated Singula…
LLM继续预训练中，超参数配置可预测的缩放规律，告别启发式搜索与高昂成本
arXiv:2606.05610v1 Announce Type: new Abstract: The efficacy of continued pre-training for Large Language Models (LLMs) hinges upon hyperparameter con…
用潜变量模型解释大模型缩放定律，为架构与基准激增提供理论框架。
arXiv:2512.06553v2 Announce Type: replace-cross Abstract: We propose a statistical framework built on latent variable modeling for scaling laws of lar…