1
诺和诺德与 Anthropic 达成合作，用 Claude 大模型加速新药研发
IT之家 9 月 16 日消息，诺和诺德（Novo Nordisk）宣布已与 Anthropic 达成合作，计划运用这家 AI 企业的 Claude 大模型，加快新药的发现与研发进程。 这家丹麦制药企业表示，项目初期，诺和诺德会先在自身研发工作流程当中测试 Anthropic 的各类模型以及 Cla…
2
NIRVANA: Structured Pruning Reimagined for Large Language Model Compression
一种重新构想的结构化剪枝方法，无需昂贵重训练即可高效压缩大模型
arXiv:2509.14230v2 Announce Type: replace Abstract: While structured pruning presents a highly effective pathway for accelerating Large Language Model…
3
ERA: Entropy-Guided Visual Token Pruning with Rectified Attention for Efficient MLLMs
熵引导视觉token剪枝，修正注意力机制，让多模态大模型推理更快更省。
arXiv:2606.31982v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) incur prohibitive inference costs due to long visual token se…
4
LLM Optimization
手把手拆解大模型优化全流程，从推理加速到显存调优的实战指南，适合想深挖LLM性能的开发者。
Article URL: https://www.youtube.com/watch?v=9tvJ_GYJA-o Comments URL: https://news.ycombinator.com/item?id=48713470 Points: 1 # Comments: 0
5
SelfJudge: Faster Speculative Decoding via Self-Supervised Judge Verification
自监督验证机制让大模型推测解码无需额外训练，实现2-3倍推理速度提升，架构简洁高效。
arXiv:2510.02329v2 Announce Type: replace-cross Abstract: Speculative decoding accelerates LLM inference by verifying candidate tokens from a draft mo…
6
Dr.LLM: Dynamic Layer Routing in LLMs
提出动态层路由机制，让LLM推理时跳过无关层，显著提升效率与精度。
arXiv:2510.12773v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) process every token through all layers of a transformer stack, …