从粗到细监督实现高效高分辨率视觉表示，SigLIP-HD在处理多模态大模型时兼顾计算效率与细粒度特征。
arXiv:2607.09488v1 Announce Type: new Abstract: High-quality visual representation is a long-standing pursuit in computer vision. In the context of mu…
HBM之父一语道破：AI计算的真正瓶颈不在GPU，而在内存，多数时间GPU都在“等待”。
IT之家 7 月 6 日消息，被誉为“HBM 之父”的韩国科学技术院（KAIST）电气系教授金正浩近日接受《东亚日报》采访时表示，AI 的核心竞争力正在从 GPU 转向内存。 金正浩认为 AI 的本质是内存，GPU 在 AI 推理中的利用率远低于理论水平。AI 每次输出结果，都必须先从 HBM 读取…
新AI优化框架Arbor在相同计算预算下比Claude Code和Codex性能提升2.5倍，为AI编码工具树立新标杆。
Imagine your engineering team just deployed an AI agent to search through internal company documents and answer employee questions. It works perfectly…
挑战扩散模型主流地位，快速U-Net实现配对医学图像翻译，兼顾速度与质量。
arXiv:2606.17675v1 Announce Type: new Abstract: Magnetic resonance imaging-signal fat fraction (MRI-SFF) quantifies tissue fat and serves as an establ…
DLLM解码计算并行化存在严重低效，只有少数token可解码，此文精准定位瓶颈并提出优化方向。
arXiv:2601.23278v2 Announce Type: replace Abstract: Diffusion Large Language Models (DLLMs) offer a compelling alternative to Auto-Regressive models, …
将低秩最优传输问题转化为黎曼流形上的优化，显著提升计算效率与可扩展性，理论突破值得关注。
arXiv:2606.12120v1 Announce Type: new Abstract: Low-rank optimal transport (OT) mitigates the quadratic scaling of classical solvers, yet existing app…
从数据、内存、计算三方面统一梳理LLM训练效率优化策略，系统总结前沿方法
arXiv:2606.10706v1 Announce Type: cross Abstract: Resource constraints increasingly determine what can be trained, fine-tuned, and deployed in large l…
挑战LLM推理中的混合批处理惯例，全新阈值独占批处理策略或改写效率规则。
arXiv:2606.00516v1 Announce Type: new Abstract: Mixed batching (MB)--interleaving prefill and decode in a single batch--has become the standard schedu…
无需昂贵训练与冗长思维链，探索视频推理的高效新路径。
arXiv:2510.17045v2 Announce Type: replace-cross Abstract: Video reasoning using Large Multimodal Models (LMMs) relies on costly reinforcement learning…
无需训练的轻量级视觉推理方法LookWise，让多模态大模型更高效地“细看”图像细节
arXiv:2603.00171v3 Announce Type: replace-cross Abstract: Multimodal Large Language Models (MLLMs) are shifting towards "Thinking with Images" by acti…
MoBiQuant通过混合位数量化实现token自适应任意精度，大幅降低大模型内存与计算开销，推理更高效。
arXiv:2602.20191v2 Announce Type: replace-cross Abstract: Dynamic runtime latency and memory constraints necessitate flexible large language model (LL…
轻量可插拔框架ChunkLLM，通过块选择与压缩突破Transformer自注意力二次复杂度瓶颈，显著加速大模型推理
arXiv:2510.02361v2 Announce Type: replace-cross Abstract: Transformer-based large models excel in natural language processing and computer vision, but…
用认知嵌入高效筛选评估子集，大幅降低大模型评测成本，保持预测准确性。
arXiv:2510.26384v2 Announce Type: replace-cross Abstract: The prohibitive cost of evaluating large language models (LLMs) on comprehensive benchmarks …
提出PaAno方法，用补丁表示学习实现高效时间序列异常检测，兼顾性能与计算资源
arXiv:2602.01359v2 Announce Type: replace-cross Abstract: Although recent studies on time-series anomaly detection have increasingly adopted ever-larg…
将摊销思想引入能量基贝叶斯推断，用传输方法一键解决非线性反问题，告别逐次MCMC的昂贵计算。
arXiv:2605.15407v1 Announce Type: cross Abstract: We consider amortized Bayesian inference for nonlinear inverse problems in settings where only sampl…