1
2000+真实场景搬进仿真！一个导航模型零样本“通吃”四种机器人本体
亮源新创的Physical Al路线清晰了
2
谷歌发布 TimesFM-3，3.3 亿参数即可进行零样本多变量时间序列预测
IT之家 9 月 1 日消息，谷歌今天发布 TimesFM-3 模型，这是该公司时间序列基础模型系列的第三代产品。拥有原生多变量预测、双注意力机制、连续补丁掩码等特性，可进行零样本多变量时间序列预测。 IT之家从谷歌官方了解到， TimesFM-3 拥有 3.3 亿个参数 ，并在包含超 1 万亿个时…
3
When Do LLMs Replace Fine-Tuned NLU? A Decision Framework for Intent Detection in Production Conversational Systems
零样本大模型能否替代精调NLU？这项研究用ATIS和CLINC150实测，给出基于意图空间的决策框架，生产环境选型必看。
arXiv:2608.20371v1 Announce Type: cross Abstract: A common claim is that zero-shot large language models (LLMs) can replace fine-tuned NLU classifiers…
4
HoloAegis: Frozen Representation, Topological Inference: Minimally Parametric Safety Manifolds for Zero-Shot LLM Guardrails
零样本LLM护栏新思路：用冻结表示+拓扑推理构建极简安全流形，参数少还能防越狱。
arXiv:2608.08485v1 Announce Type: new Abstract: Current LLM safety guardrails face a fundamental tension: fine-tuning distorts pre-trained representat…
5
LELA: an LLM-based Entity Linking Approach with Zero-Shot Domain Adaptation
零样本适应新领域，LELA让大模型做实体链接又快又准，学术干货值得一读
arXiv:2601.05192v2 Announce Type: replace Abstract: Entity linking (mapping ambiguous mentions in text to entities in a knowledge base) is a foundatio…
6
Training-Free versus Training-Based Intent Classification in LLMs: Accuracy, Robustness, and Failure Modes
大模型意图分类新研究：对比零样本与微调路线，揭示精度、鲁棒性与失败边界，值得关注。
arXiv:2608.02415v1 Announce Type: new Abstract: Intent classification in Large Language Models (LLMs) involves categorizing user prompts into predefin…
7
Can Zero-Shot LLMs Predict Child Malnutrition? A Fairness and Temporal Robustness Study
大模型零样本预测儿童营养不良？公平性与时间稳健性双维度验证，AI+公共卫生交叉新探索。
arXiv:2607.29082v1 Announce Type: new Abstract: Child malnutrition remains a major public health challenge in low- and middle-income countries, partic…
8
DWT-Fusion: A Signal-Based Framework for Training-Free LLM-Generated Text Detection
无需训练，基于离散小波变换的LLM文本检测新框架，刷新零样本检测效率。
arXiv:2607.22026v1 Announce Type: new Abstract: Detecting LLM-generated text remains challenging under zero-shot and training-free conditions, especia…
9
Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents
零样本评估空中多模态大模型智能体任务能力，无人机AI新突破
arXiv:2607.22014v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) are emerging as core reasoning modules for embodied agents, y…
10
A Graph Neural Network approach to zero-shot Digital Twins
零样本数字孪生新框架，用图神经网络突破传统几何刚性，实时视觉与几何无缝耦合
arXiv:2607.20535v1 Announce Type: cross Abstract: Traditional Predictive Digital Twins often remain geometrically rigid, requiring extensive retrainin…
11
Geometry-Enhanced Portion Estimation for Multimodal LLMs
用几何信息增强多模态大模型的食物份量估算能力，零样本识别大幅提升
arXiv:2607.16514v1 Announce Type: cross Abstract: Image-based dietary assessment promises to replace costly, bias-prone manual recalls, but portion es…
12
CompDiff: Hierarchical Compositional Diffusion for Fair and Zero-Shot Intersectional Medical Image Generation
用分层组合扩散实现医学图像公平生成，零样本捕捉交叉特征，缓解数据偏见。
arXiv:2603.16551v2 Announce Type: replace-cross Abstract: Generative models are increasingly used to augment medical imaging datasets for fairer AI, y…
13
Telescope: Improving Zero Shot Detection of LLM Generated Content By Measuring Token Repetition Probability
零样本检测AI生成文本新思路：通过衡量token重复概率，抓住大模型训练留下的“痕迹”。
arXiv:2607.04061v1 Announce Type: cross Abstract: Distinguishing Large Language Model (LLM) generated text from human writing is a critical and diffic…
14
Quantifying the Affective Gap: A Zero-Shot Evaluation of LLMs on Fine-Grained Emotion Taxonomies
大模型能否读懂细腻情感？零样本测试揭示AI在细粒度情绪识别上的真实边界，情感计算新基准。
arXiv:2607.00968v1 Announce Type: new Abstract: Emotion recognition in natural language is a foundational challenge in affective computing, with criti…
15
From Search to Synthesis: Training LLMs as Zero-Shot Workflow Generators
零样本工作流生成新范式：训练LLM从搜索到合成，无需示例即可自动编排流程
arXiv:2606.30704v1 Announce Type: cross Abstract: Large language models (LLMs) excel across a wide range of tasks, yet their instance-specific solutio…
16
How LLMs See Creativity: Zero-Shot Scoring of Visual Creativity with Interpretable Reasoning
大模型零样本给视觉创意打分，还能解释推理过程，视觉评估新前沿
arXiv:2606.29672v1 Announce Type: new Abstract: Evaluating the originality of visual images poses enduring challenges for creativity assessment. Autom…
17
Can LLMs Reason About Attention? Towards Zero-Shot Analysis of Multimodal Classroom Behavior
大模型能否理解人类注意力？这项研究用零样本方式分析多模态课堂行为，解锁AI教育新视角。
arXiv:2604.03401v4 Announce Type: replace-cross Abstract: Understanding student engagement usually requires time-consuming manual observation or invas…
18
Ground Then Rank: Revisiting Knowledge-Based VQA with Training-Free Entity Identification
免训练实体识别新方法，先定位再排序，显著提升知识型视觉问答表现
arXiv:2606.23881v1 Announce Type: new Abstract: Knowledge-Based Visual Question Answering (KB-VQA) requires grounding visual queries to external knowl…
19
Training-Free Event Detection and Causality Identification
零样本推理搭配LoRA编码器，无需训练即可精准抽取事件与因果链，NLP实践值得一看。
If you want to pull structured event knowledge out of plain text, you usually start with two questions: what happened? and why did it happen? The firs…
20
Sub-Billion, Super-Frontier: Small Language Models Rival Zero-Shot Frontier LLMs on General and Literary Relation Extraction
小模型也能打：十亿参数以下模型在通用与文学关系抽取上追平前沿大模型，零样本表现亮眼，性价比极高。
arXiv:2606.22606v1 Announce Type: cross Abstract: Large language models (LLMs) achieve strong relation extraction (RE), but their computational demand…