1
Ptolemaic and LLM Architecture Compared (In 3D)
用3D模型直观对比托勒密天文学与LLM架构，创意跨学科视角令人眼前一亮。
Article URL: https://celestial-llm-mirror.vercel.app/ Comments URL: https://news.ycombinator.com/item?id=48915548 Points: 1 # Comments: 0
2
Beyond Na\"ive Prompting: Strategies for Improved Context-aided Forecasting with LLMs
突破简单提示，提出改进上下文辅助预测的新策略，让LLM预测更精准
arXiv:2508.09904v3 Announce Type: replace-cross Abstract: Real-world forecasting requires models to integrate not only historical data but also releva…
3
Agentic Context Learning with Self-Discovered Specification
让AI自动发现任务规范，在上下文中动态学习，实现更强自主推理能力。
arXiv:2607.09794v1 Announce Type: new Abstract: Context learning is an emerging inference-time task where LLMs must learn and apply novel, task-specif…
4
Context Tuning for In-Context Optimization
ICML 2026最新论文，提出上下文调优方法，让大模型在上下文优化中表现更高效。
arXiv:2507.04221v3 Announce Type: replace-cross Abstract: We introduce Context Tuning, a simple and effective method to significantly enhance few-shot…
5
How AI is changing language
《卫报》深度揭秘AI如何重塑语言与文学创作，从ChatGPT到未来小说，探讨技术对人机交互的颠覆性影响。
Article URL: https://www.theguardian.com/books/ng-interactive/2026/jul/04/future-of-fiction-next-great-novel-ai-language-chat-gpt Comments URL: https:…
6
天文学新突破：SMA 首次实现分钟级响应，13 分钟锁定伽马射线暴创毫米波观测纪录
IT之家 7 月 4 日消息，哈佛-史密松天体物理中心（Center for Astrophysics | Harvard & Smithsonian，CfA）6 月 30 日宣布，其位于美国夏威夷莫纳克亚山（Maunakea）的亚毫米波阵列望远镜（Submillimeter Array，S…
7
World Wide Models: Literary Tools for Cultural AI
用文学工具审视文化AI，跨界视角解析大模型与人文传统的对话。
arXiv:2607.02369v1 Announce Type: cross Abstract: LLMs stage a new form of cultural encounter that is massive, automated, and monolingual. Literary di…
8
DetPO: In-Context Learning with Multi-Modal LLMs for Few-Shot Object Detection
DetPO提出结合多模态大模型的上下文学习，为少样本目标检测提供全新解法，已被欧洲会议接收。
arXiv:2603.23455v2 Announce Type: replace Abstract: Multi-Modal LLMs (MLLMs) demonstrate strong visual grounding capabilities on popular object detect…
9
Probing Memorization of Tabular In-Context Learning
新研究揭示表格型上下文学习的记忆机制，为理解大模型基础行为提供新视角
arXiv:2606.31208v1 Announce Type: new Abstract: Large tabular models (LTMs), i.e., tabular foundation models leveraging in-context learning (ICL), ach…
10
Poller: Are LLMs Suitable for Evaluating the Poetry Understanding Task?
研究LLM能否胜任诗歌理解评估任务，首次提出Poller方法探索AI在文学评价中的可行性。
arXiv:2606.30556v1 Announce Type: new Abstract: Traditional automatic evaluation methods have been shown to be unsuitable for modern Chinese poetry be…
11
Estimating Orbital Parameters of Direct Imaging Exoplanet Using Neural Network
利用神经网络精准估算直接成像系外行星轨道参数，开创AI+天文新方法
arXiv:2510.17459v3 Announce Type: replace-cross Abstract: In this work, we propose a flow-matching Markov chain Monte Carlo (FM-MCMC) algorithm for es…
12
AI Fiction in the Wild
探讨AI生成虚构作品在真实世界中的形态与文化影响，一场AI与文学的跨界对话。
arXiv:2606.22748v1 Announce Type: cross Abstract: Some professional authors are beginning to use AI tools to help produce their fiction writing. Are r…
13
晋江文学城回应苹果 iOS 端“充值异常”：目前问题已修复完毕，用户可前往账号余额确认
晋江文学城iOS端充值异常问题已修复，用户可确认余额，官方致歉并公告
IT之家 6 月 20 日消息，今天陆续有苹果 iOS 用户反馈在晋江文学城遇到充值未到账情况，对此“晋江文学城客小服”在微博致歉，发布公告称目前相应问题已修复完毕。 尊敬的 iOS 用户，发生在 2026 年 6 月 20 日 00：00-05：00 期间，通过 iOS 充值渠道充值后未到账的订单…
14
晋江文学城就部分用户充值未到账致歉：已全部处理完毕
6月20日，@晋江文学城客小服 发布公告称，“尊敬的iOS用户，发生在2026年6月20日00：00-05：00期间，通过iOS充值渠道充值后未到账的订单，截止到2026年6月20日10：00技术已全部处理完毕，期间反馈充值未到账的友友，可移步账号余额做下确认，因此给大家带来不好的体验，深表歉意。”…
15
Quantifying Aleatoric Uncertainty of In-Context Learning for Robust Measure of LLM Prediction Confidence
新方法量化LLM在上下文学习中的偶然不确定性，提升预测置信度的鲁棒性，已被ACL 2026接收。
arXiv:2606.19353v1 Announce Type: cross Abstract: In-Context Learning (ICL) allows LLMs to adapt to new tasks from a few demonstrations, but its relia…
16
Categorical Prior Lock-in: Why In-Context Learning Fails for Structured Data
揭秘大模型在结构化数据上的“卡壳”瞬间：类别先验锁定如何让上下文学习失效
arXiv:2606.11961v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used as conditional generators for structured data, re…
17
Harness In-Context Operator Learning with Chain of Operators
大模型上下文学习新范式：CoO（Chain of Operators）让模型像执行程序一样连续调用算子，提升复杂任务推理能力。
arXiv:2606.12318v1 Announce Type: cross Abstract: Neural operators approximate mappings between function spaces, but often generalize poorly to other …
18
Bimanual Robot Manipulation via Multi-Agent In-Context Learning
多智能体上下文学习让双手机器人协作更灵活，看论文如何突破复杂操控难题
arXiv:2604.20348v2 Announce Type: replace-cross Abstract: Language Models (LLMs) have emerged as powerful reasoning engines for embodied control. In p…
19
Emotion Profiling in LLM-Based Literary Translation: Systematic Shifts Across MT and Post-Editing
LLM翻译文学时情感表达如何偏移？系统分析机器翻译与人工编辑中的情感变化。
arXiv:2606.10113v1 Announce Type: cross Abstract: This paper investigates whether LLM translations exhibit identifiable emotional profiles and how pos…
20
An AI Story Just Won the Commonwealth Short Story Prize
AI创作小说首次斩获英联邦文学大奖，文学与算法的碰撞见证技术新高度
Article URL: https://tumbleweedwords.com/ai-literary-prize-flash-fiction.html Comments URL: https://news.ycombinator.com/item?id=48433318 Points: 3 # …