搜索:Few-shot

共命中 50 条(服务端检索)
ALPINE: Adaptive Localization for Parameter- and Sample-Efficient Few-Shot Learning
Few-shot learning research is predominantly evaluated on accuracy alone, with limited attention to the parameter and tra…
行业动态 HuggingFace Daily Papers · 9-16 阅读 31·访客 31
提示工程方法论 2026:什么还有效、什么可以省、什么已经易主
推理模型改写了提示词的规则——OpenAI 官方文档明确写着「避免思维链提示」「通常不需要 few-shot 示例」;Anthropic 则把叙事重心移交给了「上下文工程」。提示工程死了吗?没有,它收缩了:从话术技巧收缩成「先建评估、再写规格、管好上下文」的工程实践。本文以三家官方文档为一手依据,对照出仍然有效的技巧清单、官方明确说可以省掉的技巧,以及实证研究给出的边界。
大模型 精选 · 原创 · 10-8 💬 1 阅读 1,350·访客 1,263
Encore: Few-Shot Agentic Discovery of Manipulation Strategies
Coding agents can now write, run, and debug programs with little human help. Robot tasks, however, are usually specified…
智能体 HuggingFace Daily Papers · 9-29 阅读 96·访客 96
eDMD: Endpoint Distribution Matching for Few-Step Diffusion Distillation
Distribution matching distillation (DMD) has emerged as a leading paradigm for distilling diffusion models into few-step…
行业动态 HuggingFace Daily Papers · 11-12 阅读 8·访客 8
一篇读懂上下文学习:示例没改一个参数,模型怎么就「学会」了
在提示里放几个输入-输出示例,模型一次前向传播就把新任务干得像模像样——没有梯度更新,没有训练循环,这就是上下文学习(ICL)。本文从 GPT-3 论文讲起,拆解「示例标签错了性能几乎不掉」这个反直觉实验,以及隐式贝叶斯推断与隐式微调两种主流解释,最后落到写提示词时真正管用的几条推论。
一叶一世界 精选 · 原创 · 10-8 阅读 715·访客 715
论文精读:GPT-3 与上下文学习的发现——不训练参数,只给例子
《Language Models are Few-Shot Learners》(Brown et al., 2020)把 GPT-3 推到 175B 参数,真正的发现却是另一个:只靠提示词里放几个例子,模型就能完成没训过的任务——in-context learning 从此改写了 NLP 的工作方式。本文精读这篇论文的机制、数据与遗留争议。
研究前沿 精选 · 原创 · 10-7 阅读 747·访客 744
思维链为什么有效:推理时计算的研究脉络
「让我们一步步思考」为什么能让模型答对更多题?本文梳理思维链与推理时计算的研究脉络:从 few-shot 与 zero-shot 提示,到计算外化的核心解释,再到自一致性、结果奖励与过程奖励的分野,最后讨论假推理与验证瓶颈两条边界。
研究前沿 精选 · 原创 · 10-6 阅读 650·访客 650
ViRDM: Taming Representation Distribution Matching for Few-Step Causal Video Generation
Few-step autoregressive (AR) video diffusion enables low-latency streaming generation, but existing post-training method…
智能体 HuggingFace Daily Papers · 9-24 阅读 83·访客 82
Convergent Emergence of In-Context Learning Across Modalities
Few-shot in-context learning (ICL), the capacity of a model to infer abstract patterns from input-output examples provid…
行业动态 HuggingFace Daily Papers · 9-12 阅读 43·访客 43
Multi-Grid Post-Training for Long-Form Multi-Shot Video Generation
Generating long-form multi-shot videos requires coherent within-shot motion and visually consistent narratives across sh…
行业动态 HuggingFace Daily Papers · 9-6 阅读 28·访客 28
FewStepRL: Fine-tuning Few-step Diffusion Models with Reinforcement Learning
Reinforcement learning (RL) has become a standard post-training method for diffusion models, but most RL objectives roll…
行业动态 HuggingFace Daily Papers · 11-5 阅读 15·访客 15
Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation
Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robo…
智能体 HuggingFace Daily Papers · 10-31 阅读 5·访客 5
Few people pay for AI, but those who do spend big
& Matthias Bastian Oct 10, 2026 Nano Banana Pro prompted by THE DECODER Key Points Nearly half of US consumers use AI, …
大模型 The Decoder · 10-10 阅读 64·访客 64
Few-Step Generation via Data-Space Iteration
Flow matching has emerged as a scalable paradigm for training high-quality generative models, but sampling from the lear…
行业动态 HuggingFace Daily Papers · 10-8 阅读 26·访客 26
A Developer’s Guide to Laya: Zero-Shot Decisions and Calibration
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
开源项目 MarkTechPost · 10-7 阅读 62·访客 62
SentZero: An Enhanced Sentence-Centric Vision-Language Pretraining for Multi-Task Zero-Shot Chest X-Ray Analysis
Vision-language (VL) pretraining using paired chest X-ray (CXR) images and radiology reports has shown strong potential …
行业动态 HuggingFace Daily Papers · 9-28 阅读 30·访客 30
Just Ask Jev: Reinforcement Learning for Calibrated Decisions as a Zero-Shot Detector of AI Alignment Failures
Detectors of alignment failures screen deployed language models and score alignment benchmarks. Most are generative judg…
研究前沿 HuggingFace Daily Papers · 9-24 阅读 52·访客 49
Restoring Diversity in Distilled Image and Video Generators by Probing Activations
Distilling diffusion models into few-step student models substantially reduces sampling latency, but induces severe dive…
行业动态 HuggingFace Daily Papers · 11-13 阅读 8·访客 8
Raising the quality of insights in agentic analytics
Sponsored In partnership withSnowflake In just a few years, generative AI has changed the face of enterprise analytics, …
智能体 MIT Technology Review · 11-3 阅读 27·访客 27
History Forcing: Distilling History-Dependent Continuations for Long-Horizon Video World Models
Few-step autoregressive video diffusion enables efficient generation, yet maintaining consistency over long rollouts rem…
行业动态 HuggingFace Daily Papers · 11-2 阅读 16·访客 16
Democratizing Robot-Use Agents: A Unified Harness with Open Models
Robot-use Agents (RUAs) have shown promising zero-shot manipulation capabilities, but reliance on frontier, proprietary …
智能体 HuggingFace Daily Papers · 11-1 阅读 18·访客 18
The maker of non-text AI model Jev valued at $7.5B just weeks after launch
TypeSafe AI, the developer of Jev, a new type of AI model that gained rapid popularity after launching just a few weeks …
行业动态 TechCrunch · 10-10 阅读 31·访客 31
OpenAI says a misaligned model deliberately destroyed its own environment hoping for a fresh start with better data
Oct 10, 2026 OpenAI has a few new rogue agent stories.** In the first case (October 6), an AI evaluation model couldn't …
智能体 The Decoder · 10-10 阅读 80·访客 80
Reflex: Visually Grounded Reactive Humanoid Control
Humans effortlessly react to the world; they adeptly return a tennis shot, catch a falling cup, step aside from a passin…
行业动态 HuggingFace Daily Papers · 10-8 阅读 27·访客 27
AI/ML is becoming a performance factor in motorsport
There’s been something of a change in the world of motorsport over the past few years. It has to do with where the money…
行业动态 Ars Technica · 10-7 阅读 30·访客 30
华为首款“韬定律逻辑折叠”芯片海思麒麟 9050 Pro 裸片显微照首曝:双裸片垂直堆叠,晶体管密度提升 55% 而面积小于前代
IT之家 10 月 5 日消息,半导体分析机构 Kurnal Insights 于当地时间 9 月 30 日发布了华为麒麟 9050 Pro 芯片的裸片(Die Shot)显微照,首次从物理层面展示了这款芯片的内部结构。 照片显示,麒麟 9…
行业动态 IT之家 · 10-5 阅读 71·访客 71
Distributionally Robust Mixture-of-Experts Training
Mixture-of-Experts (MoE) transformers scale capacity by activating only a few experts per token, but this sparsity creat…
行业动态 HuggingFace Daily Papers · 10-5 阅读 25·访客 25
DMAD: Distribution Matching as Adversarial Distillation for Fast Visual Generation
Distribution Matching Distillation (DMD) trains a few-step student from the difference between separately estimated targ…
行业动态 HuggingFace Daily Papers · 10-1 阅读 29·访客 29
SlimWise: Decoupling Expert Pruning Across Prefill and Decode for Efficient MoE Serving
Mixture-of-experts (MoE) models activate few experts per token, yet batched decoding can access nearly the entire expert…
智能体 HuggingFace Daily Papers · 9-28 阅读 78·访客 77
Two-thirds of IT leaders report AI results, but few would interrupt the CEO's vacation over them
Sep 26, 2026 Midjourney prompted by THE DECODER The AI bubble debate boils down to one question: Is revenue at AI labs g…
行业动态 The Decoder · 9-27 阅读 46·访客 46
In-Flight KV Cache with Clean Anchors for Faster Autoregressive Video Diffusion
Few-step autoregressive video diffusion generates a long video by splitting the video into temporal chunks and generatin…
行业动态 HuggingFace Daily Papers · 9-26 阅读 32·访客 32
Everything new coming to Meta’s AI agent Muse
Meta’s personal AI agent Muse is only a few weeks old, and the social networking giant isn’t wasting any time building o…
智能体 TechCrunch · 9-24 阅读 99·访客 97
Accent Analogy Guidance: More Speaker Similarity at Equal Accent in Cross-Lingual Voice Cloning
In cross-lingual zero-shot text-to-speech, the accent of the reference leaks into the target speech. We propose accent a…
行业动态 HuggingFace Daily Papers · 9-24 阅读 29·访客 29
Don’t be fooled by this summer of AI hype
It’s been a busy few months for AI hype. At the end of April, Anthropic claimed that its model Claude Mythos is better a…
大模型 MIT Technology Review · 9-22 阅读 58·访客 57
Trump rejects AI slowdown calls, launches "AI Force" instead
The president offered few details on what his proposed new AI Force would do.]
行业动态 Ars Technica · 9-21 阅读 34·访客 34
From Pretraining to Proficiency: Real-World Subtask RL for Long-Horizon Manipulation with Minimal Human Intervention
A pretrained robot foundation policy may execute most of a long-horizon task yet repeatedly fail at a few critical subta…
智能体 HuggingFace Daily Papers · 9-18 阅读 93·访客 92
StepAudio 3 Gen Technical Report
We introduce StepAudio 3 Gen, a general-purpose audio generation model that supports zero-shot text-to-speech (TTS), voi…
行业动态 HuggingFace Daily Papers · 9-11 阅读 34·访客 34
SyncWorld: Visual Calibration Enables World Models as Zero-Shot Simulators
World models are increasingly used as policy-in-the-loop imagination environments, where reliable rollouts require fine-…
智能体 HuggingFace Daily Papers · 9-8 阅读 91·访客 89
Measuring the Checker: Mutation Analysis for GPU-Kernel Benchmark Oracles
Benchmarks for LLM-generated GPU kernels decide correctness with a few random inputs and a loose floating-point toleranc…
研究前沿 HuggingFace Daily Papers · 9-2 阅读 39·访客 39
The open-source movement wants Jensen Huang back
This story originally appeared in The Algorithm, our weekly newsletter on AI. To get stories like this in your inbox fir…
开源项目 MIT Technology Review · 5天前 阅读 30·访客 30
LLM 时代的本体构建流水线:专家定义 + AI 建议
本体构建曾是知识工程的奢侈品:专家协作数月才能交付。LLM 把术语生成、关系抽取、分类归纳的自动化率推到新高度,但公理级精确性仍离不开人。本文给出一条「AI 建议 + 专家评审」的流水线,并对照研究划清自动化边界。
研究前沿 精选 · 用户投稿 · 5天前 阅读 61·访客 61
本体对齐与融合:让多源知识说同一种语言
两个部门各建一套「客户」本体,字段同名不同义、实体同人不同名。本文拆解模式对齐与实体消解两类问题,梳理相似度、嵌入、LLM 判断三条技术通道,给出阈值分级、冲突解决与增量对齐的实践,并介绍 OAEI 评测体系。
研究前沿 精选 · 用户投稿 · 5天前 阅读 41·访客 41
从文本到三元组:LLM 知识抽取与图谱灌库工程
TBox 定好了,ABox 还躺在文档里。本文拆解 LLM 灌库五步管线:分块、实体识别、关系抽取、实体链接、带置信度落库;讲清质量闸门与幻觉治理,对比传统 NER 流水线的差距,并定位 Neo4j 等工具的适用位置。
大模型 精选 · 用户投稿 · 5天前 阅读 45·访客 45
本体驱动检索(下):GraphRAG 全局问答实战
「这批文档讲的是什么」是向量检索答不好的全局摘要问题。GraphRAG 用实体抽取、层级社区、预生成摘要加 map-reduce 换来全局视野。本文拆解四步管线、local 与 global 分工、LazyGraphRAG 成本革命。
大模型 精选 · 用户投稿 · 5天前 阅读 47·访客 47
Cmpnd Releases dspy-wsp: Weight-Space Programming Comes to DSPy
!(https://www.gstatic.com/images/branding/googleg/1x/googleg_standard_color_128dp.png)Add as a preferredsource on Google…
行业动态 MarkTechPost · 11-15 阅读 26·访客 26
CANTraj: Recovering Vehicle Trajectories from CAN Signals in Naturalistic Driving
Open driving releases and usage-based insurance programs often claim to prevent privacy breaches by omitting GPS records…
行业动态 HuggingFace Daily Papers · 11-13 阅读 7·访客 7
模型操作系统之争:谁来做模型之上的调度层
大模型之上正在长出一层「模型操作系统」:路由、上下文管理、工具调用与记忆的统一抽象,决定算力效率与应用形态。基础模型厂商向上、云平台向下、中间件创业公司卡位中间,开放与封闭两条路线拉锯,而模型迭代随时重洗牌面。本篇拆解这场调度层的卡位战。
行业动态 精选 · 原创 · 11-10 阅读 48·访客 48
RAG 的冷启动问题:没有历史数据时怎么建好检索系统
冷启动的缺是三种:缺查询、缺标注、缺反馈。本文给出合成 query-chunk 对的质量控制、企业里"前 RAG 时代"查询的挖掘、首日评测集的最小规模与金丝雀查询机制。
后端技术 精选 · 原创 · 11-9 阅读 84·访客 84
RAG 的查询理解:用户意图识别与查询扩展的研究与实践
意图识别不是分类题而是检索策略的选择题。本文梳理 PRF/RM3/HyDE 的扩展脉络、主题漂移的风险、QPP 自适应力度控制,以及查询理解模块的输出契约设计。
后端技术 精选 · 原创 · 11-9 阅读 70·访客 70
Prompt 的科学研究:提示词对模型行为的影响机制
提示词不是玄学而是可测量变量:FormatSpread 的 76 点波动、指令模板不稳定性、贝叶斯机制解释、软提示与自动提示优化、注入攻击与工程规范。
研究前沿 精选 · 原创 · 11-9 阅读 64·访客 64