SlimPer提出让个性化模型精简且智能的新方法，兼顾性能与效率，值得关注。
arXiv:2607.12281v1 Announce Type: cross Abstract: Transformer-style architectures are increasingly adopted for industrial recommendation systems, yet …
消息传递方法实现高效推理，揭秘AI全新思维范式
arXiv:2607.01077v1 Announce Type: cross Abstract: While inference-time scaling has improved the reasoning abilities of large language models (LLMs), t…
百度开源端到端OCR模型，总参30亿仅激活5亿，有效解决文档解析越生成越慢问题
IT之家 6 月 25 日消息，百度于 6 月 22 日开源推出 Unlimited OCR 模型，总参数量 30 亿，推理时仅激活 5 亿参数 ，目标解决在解析长文档时，端到端 OCR 模型越生成越慢的问题。 IT之家注：端到端 OCR 模型是统一神经网络架构系统，融合检测图像中的文本和字符识别，…
BitNet二值化网络实现高效文本嵌入，为资源受限场景提供轻量级NLP新方案。
arXiv:2606.25674v1 Announce Type: new Abstract: LLM-based text embedders have substantially improved retrieval and semantic representation quality, bu…
音视频多模态大模型token减少新方法，巧妙抑制混叠问题。
arXiv:2512.10324v2 Announce Type: replace Abstract: Audio-Visual Large Language Models (AV-LLMs) face prohibitive computational costs of processing ma…
残差感知新方法让大模型二值化训练更准更高效，已被ICML 2026接收。
arXiv:2602.05367v3 Announce Type: replace Abstract: Efficient deployment of large language models (LLMs) requires extreme quantization, forcing a crit…
加法码本搭配多比特宽度量化方案，为LLM推理加速与压缩提供新思路。
arXiv:2606.12876v1 Announce Type: cross Abstract: As large language models (LLMs) are increasingly deployed across heterogeneous hardware with varying…
稀疏MoE大模型部署新突破：引入联盟感知策略的专家剪枝方法
arXiv:2606.09886v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token comp…
只需整数运算的视觉Transformer，快速语义分割无需浮点，部署更高效。
arXiv:2509.10334v2 Announce Type: replace-cross Abstract: Vision Transformers (ViTs) have recently achieved strong results in semantic segmentation, y…
轻量级世界动作模型Light-WAM，通过状态融合动作解码实现高效推理，为具身智能与机器人学习带来新突破。
arXiv:2606.08242v1 Announce Type: new Abstract: World Action Models (WAMs) extend robot policy learning by incorporating future prediction as an addit…
NVIDIA推出的高性能推理加速器，专为长时间运行AI代理设计，速度更快、效率更高。
Powers faster, efficient reasoning for long-running agents Discussion | Link
边缘设备高效推理新突破，兼顾性能与资源约束，适合部署场景研究者
arXiv:2603.16867v2 Announce Type: replace-cross Abstract: Large language models (LLMs) with chain-of-thought reasoning achieve state-of-the-art perfor…
异构边缘/雾环境中大模型高效服务的新方案，解决部署延迟与资源优化难题。
arXiv:2606.03770v1 Announce Type: cross Abstract: Large Language Models (LLMs) have become integral to modern applications, yet their deployment remai…
无需额外训练，即可让预训练ViT弹性适配不同计算约束，实现高效推理与精度平衡的创新方法。
arXiv:2510.17700v2 Announce Type: replace Abstract: Vision foundation models achieve remarkable performance but are only available in a limited set of…
新方法ReSpinQuant通过子空间残差旋转近似，显著提升大模型逐层量化效率与精度。
arXiv:2604.11080v2 Announce Type: replace-cross Abstract: Rotation-based Post-Training Quantization (PTQ) has emerged as a promising solution for miti…
首个将混合专家模型高效部署到移动设备上的架构，实现低延迟与资源友好的AI推理。
arXiv:2605.27358v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) has become the de facto architecture for hundred-billion-parameter language…
通过引入“自发性”机制，显著提升大语言模型激活稀疏性的鲁棒性，为高效推理提供新思路。
arXiv:2512.12744v4 Announce Type: replace Abstract: Activation sparsity offers a compelling route to accelerate large language model (LLM) inference b…
无需手动筛选视觉令牌，LRCP利用低秩可压缩性自动剪枝，大幅提升LVLMs推理效率，尤其适合高分辨率图像与长视频场景。
arXiv:2605.15621v1 Announce Type: new Abstract: Large vision-language models (LVLMs) achieve strong multimodal understanding, but their inference cost…