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 …
用Kronecker分解海森矩阵，高效提升LLM量化精度，突破后训练量化瓶颈。
arXiv:2607.07964v1 Announce Type: new Abstract: Post-training quantization (PTQ) is a widely adopted technique for compressing large language models (…
突破传统一刀切剪枝，PALS按每层百分位自适应稀疏度，精准提升大模型压缩效率。
arXiv:2607.07557v1 Announce Type: cross Abstract: One-shot pruning methods like Wanda and SparseGPT apply the same sparsity ratio to every layer of a …
70多位作者联合发布Nemotron混合MoE大模型压缩方案，大幅降低推理成本且保持性能。
arXiv:2607.04371v1 Announce Type: new Abstract: We present Nemotron-Labs-3-Puzzle-75B-A9B, a compressed variant of Nemotron-3-Super optimized for inte…
新方法Fair-GPTQ实现大模型量化时兼顾效率与公平性，减少偏差
arXiv:2509.15206v3 Announce Type: replace Abstract: The high memory demands of generative language models have drawn attention to quantization, which …
针对多模态大语言模型压缩难题，提出Token级响应-视觉注意力引导，提升蒸馏效果
arXiv:2607.02593v1 Announce Type: cross Abstract: While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging su…
将知识蒸馏引入混合xLSTM架构，探索高效模型压缩新方向
arXiv:2603.15590v2 Announce Type: replace Abstract: There have been numerous attempts to distill quadratic attention-based large language models (LLMs…
将信任区域优化引入策略蒸馏，解决模型压缩中的策略漂移问题。
arXiv:2607.04751v1 Announce Type: cross Abstract: Big goals are hard to achieve all at once; breaking them into small steps is wiser. We present Trust…
突破性KV缓存量化方案，实现sub-1-bit压缩，大幅降低推理内存开销却不损精度。
arXiv:2607.01065v1 Announce Type: new Abstract: The deployment of Large Language Models (LLMs) with extended context windows is increasingly constrain…
扩散变换器虽强但计算开销大，后训练剪枝技术如何高效优化？这篇论文给出新方案。
arXiv:2607.00927v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) have demonstrated impressive performance in image generation but suffe…
提出一种压缩模型大小与类别数双重带宽瓶颈的联邦蒸馏方法，大幅提升通信效率。
arXiv:2607.00173v1 Announce Type: new Abstract: Federated learning is bandwidth-bound on two orthogonal axes: model size, which limits how often param…
量化大模型时公平性与安全性易受损，本文通过保护关键权重巧妙解决，让轻量化模型也能坚守底线。
arXiv:2601.12033v2 Announce Type: replace Abstract: Quantization is widely adopted to reduce the computational cost of large language models (LLMs); h…
语音大模型解码器层存在多少冗余？这篇论文提出测量方法，为模型压缩提供新视角
arXiv:2603.05121v2 Announce Type: replace-cross Abstract: Speech Large Language Models route speech encoder representations into an LLM decoder that t…
将激活稀疏性与FP4量化巧妙结合，大幅提升LLM推理效率，硬核优化方案来袭！
arXiv:2606.26587v1 Announce Type: cross Abstract: Low-bit floating-point formats and semi-structured sparsity are increasingly supported by modern acc…
大型视觉语言模型重校准后生成更小模型，提升效率和精度，新技术论文。
arXiv:2506.15681v4 Announce Type: replace Abstract: Recent advancements in vision-language models (VLMs) have leveraged large language models (LLMs) t…
On-policy蒸馏中旧数据的容忍度如何？这篇论文挑战了传统认知，给出定量分析框架。
arXiv:2606.24143v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts guided by teacher feedback and is be…
提出上下文感知的蒸馏与消融方法，精准提升Text2DSL生成质量与效率，是自然语言到领域特定语言转化的新突破。
arXiv:2606.22578v1 Announce Type: cross Abstract: We extend our prior work on Text2DSL automatic generation of domain-specific language (DSL) code fro…
华为Ascend NPU上OpenPangu量化的实证研究，揭秘国产芯片AI模型部署关键优化。
arXiv:2606.21257v1 Announce Type: cross Abstract: OpenPangu models are attractive targets for private and domestic large-language-model deployment, ye…
提出统一秩分配方法，突破低秩分解压缩LLM的瓶颈，兼顾效率与性能。
arXiv:2606.21847v1 Announce Type: cross Abstract: Low-rank decomposition serves as a promising compression paradigm for large language models, however…
这篇新论文提出强化学习感知的知识蒸馏，让教师模型“教”学生时更关注推理过程，突破传统蒸馏只传答案的局限。
arXiv:2602.22495v3 Announce Type: replace-cross Abstract: Reinforcement learning (RL) post-training has recently driven major gains in long chain-of-t…