视觉语言模型如何轻量化？这项研究提出免重训练的任务无关剪枝方案，一次剪枝即可适配下游任务。
arXiv:2608.06901v1 Announce Type: cross Abstract: Vision-language models (VLMs) have achieved remarkable generalization across diverse multimodal task…
Fisher重加权剪枝，让大模型压缩更省能耗，部署更可持续。
arXiv:2608.00481v1 Announce Type: new Abstract: One-shot post-training pruning is the most energy-frugal compression strategy for largelanguage models…
提出统一静态与动态剪枝的框架，显著提升大模型推理速度与资源效率。
arXiv:2607.21985v1 Announce Type: cross Abstract: The increasing deployment of large language models (LLMs) has magnified the computational and memory…
MoE编码模型太大跑不动？这篇论文提出一次性剪掉一半专家，编码能力几乎不变。
arXiv:2607.16721v1 Announce Type: new Abstract: The strongest open-weight coding models are mixture-of-experts (MoE) networks: most of their size come…
视觉Transformer压缩新方案，多粒度随机自动剪枝兼顾精度与效率，模型轻量化研究值得一看。
arXiv:2603.12222v2 Announce Type: replace-cross Abstract: Vision Transformers require significant computational resources and memory bandwidth, severe…
剪枝扩散模型实现高效真实图像超分，推理更快内存更省，兼顾画质与实时性。
arXiv:2508.17434v3 Announce Type: replace Abstract: Real-world image super-resolution (Real-ISR) focuses on recovering high-quality images from low-re…
面向工业物联网的端侧大模型推理，级联多粒度剪枝兼顾精度与效率，落地价值突出。
arXiv:2606.26861v1 Announce Type: new Abstract: Deploying large language models (LLMs) on Industrial Internet of Things (IIoT) edge devices demands ex…
LLM压缩新突破：将块删除问题转化为约束二元优化，物理模型Ising玻璃降低下游性能损失
arXiv:2602.00161v2 Announce Type: replace Abstract: In this paper, we formulate the compression of large language models (LLMs) by optimally deleting …
剪枝后的大模型在多项选择基准测试中表现优异，却在开放回答任务中“原形毕露”，揭示评测陷阱。
arXiv:2606.17609v1 Announce Type: new Abstract: Compressing large language models reduces memory use and inference cost, but it can also create failur…
大模型剪枝新突破：CRePE用卷积感知相对重要性实现高效后训练剪枝，大幅降低部署开销
arXiv:2606.01544v1 Announce Type: new Abstract: Deploying Large Language Models (LLMs) in practice incurs substantial memory and computational costs. …
在MacBook上也能轻松剪枝MoE专家模型了，Cerebras REAP方法完美移植到MLX。
Article URL: https://github.com/egesabanci/reap-mlx Comments URL: https://news.ycombinator.com/item?id=48364457 Points: 2 # Comments: 0
重新定义替换式LLM压缩的粒度，从层到子模块，为模型轻量化提供新视角。
arXiv:2606.02559v1 Announce Type: cross Abstract: Post-training compression of Large Language Models (LLMs) removes entire architectural components, e…
用激进剪枝法从LLM中提取轻量翻译专家，模型压缩与翻译能力兼得。
arXiv:2605.28042v1 Announce Type: cross Abstract: Modern large language models (LLMs) achieve state-of-the-art machine translation performance, but th…
提出Diet-LLM方法，通过融合任务特定重要性分数实现维度级全局剪枝，在保持性能的同时显著压缩大模型规模。
arXiv:2603.23985v3 Announce Type: replace Abstract: Large language models (LLMs) have demonstrated remarkable capabilities, but their massive scale po…