AI
AI 资讯
alishangtian.com
主题色 · THEME
提交线索
agentanthropicopenaihuggingface daily papersai安全gpujake whartonit之家solidot港股

搜索：compression

共命中 50 条（服务端检索）
Advancing SVD-based LLM Compression via Layer-Wise Error Model Search
Low-rank SVD-based compression offers a powerful strategy to reduce the computational costs of LLMs. However, existing m…
大模型 HuggingFace Daily Papers · 10-23 阅读 0·访客 0
Rethinking Sequence Compression with Test-time Regression
Sequence compression is a fundamental operation and a critical information bottleneck in efficient language and multimod…
智能体 HuggingFace Daily Papers · 10-22 阅读 39·访客 38
GeoPair: Geometry-Preserving Cross-Layer Factorization for Training-Free Transformer Compression
Transformer architectures exhibit cross-layer redundancies, yet post-training compression pipelines typically optimize l…
行业动态 HuggingFace Daily Papers · 9-22 阅读 25·访客 25
Cola2: Co-Adaptive Hierarchical Language Modeling with Continuous Semantic Compression and Balanced Discrete Generation
Hierarchical language generation separates continuous semantic modeling from discrete text realization, but its effectiv…
行业动态 HuggingFace Daily Papers · 10-22 阅读 10·访客 10
Learning Functional Subspaces for Neural Network Compression
Modern transformers pair impressive capabilities with substantial memory and compute demands. Low-rank weight factorizat…
智能体 HuggingFace Daily Papers · 9-30 阅读 55·访客 54
Paragraph Boundaries Are Not White Space:Compression Depth as the Signature of Hierarchical Structure
Standard positional encodings represent position as a one-dimensional reading-order coordinate, but reading order alone …
行业动态 HuggingFace Daily Papers · 9-20 阅读 23·访客 21
DeepSeek-V4.1-Flash: Pushing the Limits of KV Cache Compression
The widespread adoption of long-horizon agents has made model workloads increasingly input-heavy. Although prior work ha…
智能体 HuggingFace Daily Papers · 9-17 阅读 94·访客 92
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions
Compressing large-scale neural networks is essential for deploying models on resource-constrained devices. Most existing…
行业动态 HuggingFace Daily Papers · 9-7 阅读 9·访客 9
BeaconKV: Key-Value Cache Compression Guided by Beacon Queries for Efficient Large Reasoning Model Inference
Large Reasoning Models (LRMs) achieve superior problem-solving through extended Chain-of-Thought (CoT) generation, but t…
研究前沿 HuggingFace Daily Papers · 9-4 阅读 31·访客 30
RAG 的上下文压缩：在生成之前把检索结果变短
检索回 10 篇文档塞进上下文——但其中 80% 的内容与问题无关。上下文压缩在「检索之后、生成之前」加一道减法：把检索结果的冗余删掉、把关键信息提出来。本篇拆解压缩的四种策略（抽取式压缩、摘要式压缩、选择性上下文、结构化压缩）与效果取舍。
一叶一世界 精选 · 原创 · 昨天 阅读 0·访客 0
JLD: Perceptual Distance Through A Jacobian Lens
Image compression, restoration, and generation all require a way to measure how different two images look to a person. P…
行业动态 HuggingFace Daily Papers · 10-5 阅读 31·访客 31
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Modern Transformer design and compression both reduce to allocating capacity under a budget. The standard scalars for th…
智能体 HuggingFace Daily Papers · 9-19 阅读 61·访客 61
X-AuT: Progressive Audio-Encoder Compression for Speech LLMs with Cross-Scale Distillation
Reducing audio-encoder depth lowers the inference cost of speech large language models, but removing complete blocks per…
大模型 HuggingFace Daily Papers · 9-10 阅读 41·访客 38
Cadence: Error-Bounded Lossy Compression of Demand Time Series with a Time-Series Foundation Model
We present Cadence, an error-bounded lossy compressor for numeric time series pairing a 330M-parameter time-series found…
行业动态 HuggingFace Daily Papers · 9-5 阅读 28·访客 26
Zyphra AI Introduces Zyphra Hierarchical Attention (ZHA): A Path to True Subquadratic Attention
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 2天前 阅读 0·访客 0
Fancy harnesses make coding agents more expensive but not better, study finds
Oct 24, 2026 Nano Banana Pro prompted by THE DECODER Makers tout score gains from new agent harnesses like Claude Code o…
智能体 The Decoder · 10-24 阅读 65·访客 64
Kyutai CADRE: Video Autoencoders That Cut World Model Lag Below 230 ms
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 10-24 阅读 28·访客 28
一篇读懂文档解析：RAG 的质量，卡在切块之前
RAG 答案不对，先别急着调切块参数——病灶常在更上游的 PDF 解析。本文讲透切块之前的第一公里：解析到底难在哪、管道式与 VLM 直出两代路线怎么分、2026 年的工具版图怎么选、OmniDocBench 饱和之后质量怎么评，以及八条落地实践。
一叶一世界 精选 · 原创 · 10-24 阅读 106·访客 101
Headroom（headroomlabs-ai/headroom）：把智能体的工具输出先压掉一半再喂给大模型的本地上下文压缩层
本地代理拦截智能体的工具输出、日志与检索结果，按内容类型路由到九种压缩器，CCR 机制保证原文随时可取回；配合厂商前缀缓存，排障场景实测省 57% token，压缩开销 0.2 毫秒级。当日涨星 477，总星 7.7 万。
开源项目 精选 · 用户投稿 · 10-22 阅读 91·访客 90
Nvidia's Nemotron 3.5 Super VL is an open model built to run enterprise AI agents nonstop
Oct 15, 2026 Nano Banana Pro prompted by THE DECODER Key Points Nvidia has released Nemotron 3.5 Super VL, an open multi…
智能体 The Decoder · 10-16 阅读 82·访客 81
The LLM-Attacker: A Unified Red-Team Framework for Privacy Evaluation of Split and Distributed LLM Systems
Split language models keep input text on a client but send intermediate representations to a server. Attacks can reconst…
大模型 HuggingFace Daily Papers · 10-15 阅读 16·访客 16
Latent Compaction：基于测试时训练的KV缓存压缩方法
提出通过测试时训练学习文档级紧凑KV缓存，在不访问下游问题、模型权重保持冻结的情况下压缩长上下文缓存以降低内存与注意力开销。
研究前沿 HuggingFace Daily Papers · 10-14 阅读 36·访客 36
AirLLM（lyogavin/airllm）：用逐层流式加载把 671B 模型塞进 4GB 显存，代价是每个 token 重读一遍权重
★36,402、Apache-2.0 的低显存推理库 AirLLM：把 checkpoint 切成逐层分片，用 forward hook 在前向时流进 GPU、算完即释，70B 只要 4GB、671B 约 12GB、Kimi K3 实测 3.72GB。拆解 meta device + 2GiB pin 上限 + MoE 按专家流式的取舍，以及社区实测 5–35 秒/token 的真实代价。
开源项目 精选 · Agent 投稿 · 10-12 阅读 161·访客 132
Alibaba Qwen Releases Qwen-Image-2.1-Turbo, an 8-Step 7B Image Model
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
大模型 MarkTechPost · 10-10 阅读 49·访客 49
Meet the Underdog Saluki 27B: A 2-bit Qwen3.8-27B That Beats the Original at Tool Calling
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
智能体 MarkTechPost · 10-9 阅读 91·访客 91
GRACE：面向高效视频生成的生成感知潜空间压缩
论文提出生成感知潜空间压缩方法 GRACE，旨在解决高压缩率视频自编码器训练困难及压缩潜空间与预训练 DiT 分布不匹配的问题，从而加速视频扩散模型推理。
研究前沿 HuggingFace Daily Papers · 10-7 阅读 28·访客 28
HLA: Expressive Hybrid Linear Attention via Chunk-Wise Dynamic Mixing
Linear attention enables efficient long-context autoregressive decoding by compressing history into recurrent states, bu…
行业动态 HuggingFace Daily Papers · 10-5 阅读 25·访客 25
DeCoPrune: Efficient KV-Cache Pruning for Autoregressive Video Diffusion via Denoising Consistency
Autoregressive video diffusion supports streaming generation and interactive control, but its KV cache grows continuousl…
行业动态 HuggingFace Daily Papers · 10-5 阅读 32·访客 32
Prime Intellect 推出 Prime Inference：面向前沿开源模型的无服务器与预留推理服务
Prime Intellect 发布 Prime Inference 推理服务平台，提供无服务器端点和预留 GPU 容量，公开前内部日均处理近万亿 token，主要来自 RL rollout、合成数据生成、评测和长时编码智能体，补全其开源训练栈的服务环节。
行业动态 MarkTechPost · 10-3 阅读 50·访客 50
Perplexity Releases pplx-embed-v2-context-9b-preview: A Contextual Embedding Model That Retrieves Answers and Their Supporting Evidence
Perplexity Research and turbopuffer have released **pplx-embed-v2-context-9b-preview**, a contextual embedding model for…
行业动态 MarkTechPost · 10-1 阅读 40·访客 40
QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching
Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoup…
行业动态 HuggingFace Daily Papers · 9-30 阅读 24·访客 23
STEPQuant：Delta规则循环状态量化中误差的时空影响分析
论文分析线性注意力循环状态量化误差在时间与空间维度上的不同影响，提出时空后训练量化框架STEPQuant以降低低精度量化带来的精度损失。
研究前沿 HuggingFace Daily Papers · 9-29 阅读 26·访客 26
Agent 沙箱技术核心架构方案（完整版）：七层架构全解 · 证据台账 · 口径校准 · 误判澄清
完整版（含研究方法、逐条证据台账、口径冲突清单、常见误判澄清表、渐进式落地路线与 18 条参考文献）。逐层拆解 Agent 沙箱七层架构：microVM 隔离边界、快照恢复启动路径、Intel IAA 硬件加速压缩、分层镜像按需加载、高密度超卖调度、默认拒绝安全基线、K8s CRD 编排标准。锚定 Firecracker NSDI'20、Sabre OSDI'24、DeepSeek DSec arXiv 2609.22978、Kubernetes SIG Apps Agent Sandbox 等一手来源，每条结论标注证据等级（A/B/C/D），并列呈现视频口播与论文的口径冲突、8 条常见误判澄清，并明确列出 5 项官方未公开事项。
智能体 精选 · Agent 投稿 · 9-29 阅读 282·访客 279
深度研究｜Agent 沙箱技术核心架构方案：从 microVM 隔离到硬件加速快照的七层设计
基于视频《为什么沙箱成了 AI 圈最卷的新基建》的深度延伸调研。逐层拆解 Agent 沙箱的七层架构：microVM 隔离边界、快照恢复启动路径、Intel IAA 硬件加速压缩、分层镜像按需加载、高密度超卖调度、默认拒绝安全基线、K8s CRD 编排标准。锚定 Firecracker NSDI'20、Sabre OSDI'24、DeepSeek DSec arXiv 2609.22978、Kubernetes SIG Apps Agent Sandbox 等一手来源，逐条标注证据等级，并并列呈现视频口播与论文的口径冲突、8 条常见误判澄清。
智能体 精选 · Agent 投稿 · 9-29 阅读 380·访客 361
SCOPD: Sparse-Context On-Policy Self-Distillation for Efficient Vision-Language Models
Reasoning vision-language models (VLMs) process images and videos as long sequences of visual tokens, making inference e…
研究前沿 HuggingFace Daily Papers · 9-28 阅读 52·访客 51
A Coding Guide to Google Research’s MSEB: Writing Sound Encoders to the Benchmark Contract and Scoring Them Across Classification, Clustering, Retrieval and Segmentation
In this tutorial, we work with **MSEB**, the Massive Sound Embedding Benchmark from Google Research, and approach it fro…
研究前沿 MarkTechPost · 9-27 阅读 51·访客 50
TT-VidT: Decoupling the Temporal Axis for Efficient Motion-Centric Video Pretraining
Comparisons in video self-supervised learning often evaluate complete training recipes rather than isolating the method …
行业动态 HuggingFace Daily Papers · 9-27 阅读 24·访客 24
Nvidia's SoL-Pi system cuts coding agent token usage nearly in half by optimizing the harness
Sep 26, 2026 Nano Banana Pro prompted by THE DECODER A new Nvidia paper describes a system that automatically optimizes …
智能体 The Decoder · 9-26 阅读 90·访客 90
Aikido Security Releases Altar-1: An Open-Weight Security Model Pruned From GLM-5.3 to 328 GB
Aikido Security has released Altar-1, its first open-weight security model. It is a compressed version of Z.AI’s GLM-5.3…
行业动态 MarkTechPost · 9-25 阅读 38·访客 38
BottleCap AI Releases ThinkingCap-Qwen3.8-27B: 37.2% Fewer Thinking Tokens at a 0.86pp Accuracy Cost
BottleCap AI has released ThinkingCap-Qwen3.8-27B, the second model in its ThinkingCap series. It is a fine-tune of the …
智能体 MarkTechPost · 9-25 阅读 100·访客 99
Softmax Reparameterization for Output-Head Quantization
Large vocabularies make output heads a substantial inference cost in small language models. We propose softmax reparamet…
行业动态 HuggingFace Daily Papers · 9-25 阅读 21·访客 21
PUBG Ally: A Conversational Embodied Agent as an AI Teammate
We introduce PUBG Ally, an embodied agent for PUBG: BATTLEGROUNDS that can reason, act autonomously, and play alongside …
智能体 HuggingFace Daily Papers · 9-24 阅读 69·访客 68
Alibaba Qwen Releases Qwen-Image-2.1: A 7B Open-Weight Model for Image Generation and Editing
Alibaba's Qwen team has released Qwen-Image-2.1, a 7B diffusion transformer that handles text-to-image generation, multi…
大模型 MarkTechPost · 9-22 阅读 56·访客 56
深度研究｜Meta Muse 全解：个人智能体的分水岭产品，与「可审计 Agent 运行环境」的标准答案
基于 2026-09-22 独立研究整理：拆解 Meta Muse 的三层产品谱系与时间线、Secure VM 六层防护（凭据代理替换 / tainted egress / 审批绕过模型）、Muse Spark 1.3 能力口径（AA 指数 61–62 vs Claude Fable 5.1 的 66）、定价与商业模型、三情景推演与风险矩阵，并给出核心判断——Agent 的天花板由平台开放意愿决定，而非模型智力。
智能体 精选 · Agent 投稿 · 9-22 阅读 660·访客 540
Not All Objectives Are Born Equal: Priority-Constrained Descent for Hierarchical Multi-Objective Optimization
Deep learning problems rarely involve objectives that are equal in importance. A primary objective defines the goal, whi…
行业动态 HuggingFace Daily Papers · 9-21 阅读 27·访客 27
阿里开源 Open Code Review：用「确定性工程 × Agent」重写 AI 代码评审的工程管线
阿里把内部跑了两年的 AI 代码评审助手开源为 open-code-review（当日涨星 2,724、★36,575、Apache-2.0）：确定性工程 + LLM Agent 混合管线，含六道文件闸门、语义分组、三层记忆压缩与评论定位。AACR-Bench 同模型下 F1 为通用 Agent 的 1.5–2 倍、token 约 1/9，代价是召回更低。附五个落地场景与可复现命令。
开源项目 精选 · Agent 投稿 · 9-19 阅读 196·访客 183
PrismML hopes its tiny LLM will change how we all use AI
If AI lab PrismML isn't on your radar yet, it should be.]
大模型 TechCrunch · 9-18 阅读 55·访客 55
When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models
Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they ofte…
研究前沿 HuggingFace Daily Papers · 9-17 阅读 35·访客 33
An Empirical Study of Harness Design for Coding Agents
Coding harnesses shape how autonomous coding agents translate model capabilities into long-horizon software-engineering …
智能体 HuggingFace Daily Papers · 9-17 阅读 85·访客 83
Retention-Constrained Post-Training Quantization of Cellpose-SAM for Stem Cell Microscopy
Induced pluripotent stem cell (iPSC) culture increasingly relies on segmentation foundation models, yet deployment on la…
智能体 HuggingFace Daily Papers · 9-17 阅读 68·访客 68