1
DeepSeek Harness 崔添翼：产品核心理念是“一切皆插件”，可扩展性是初心
IT之家 10 月 4 日消息，DeepSeek Harness 组成员崔添翼今日回应了“如何看待 DeepSeek Harness 在新版本中加入 Claude Code Mods 兼容？”，他本人是这次 v0.2.1-alpha.1 版本中加入 Claude Code Mods 兼容层的作者。 …
2
Why Enterprise AI Gets Hard After the First Agent
DolphinX 让企业AI从单一代办扩展到多代理协作，解决第一个Agent后的复杂管理难题，支持实时数据与智能编排，是构建可扩展AI应用的利器。
Article URL: https://medium.com/@DolphinDB_Inc/enterprise-ai-needs-more-than-chatbots-meet-dolphinx-6704da50a733 Comments URL: https://news.ycombinato…
3
Titan Transients and LLM Scalability
探索Titan瞬态现象与LLM可扩展性的交叉前沿，揭开大规模系统性能瓶颈的核心见解。
Article URL: https://queue.acm.org/detail.cfm?id=3819082 Comments URL: https://news.ycombinator.com/item?id=49095428 Points: 2 # Comments: 0
4
Scaling Closed-Loop Feature Channel Configuration with LLMs
用LLM自动配置特征通道，实现闭环系统高效扩展，典型大模型系统级应用。
arXiv:2607.20516v1 Announce Type: cross Abstract: Promising initial results in closed-loop large-language-model-based channel-configuration search dem…
5
EvoGuard: An Extensible Agentic RL-based Framework for Practical and Evolving AI-Generated Image Detection
一种基于智能体强化学习的可扩展框架，让AI生成图像检测能随新攻击方式持续进化。
arXiv:2603.17343v2 Announce Type: replace Abstract: The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making A…
6
BoRP: Bootstrapped Regression Probing for Scalable and Human-Aligned LLM Evaluation
用回归探测评估大模型，兼顾规模与人类偏好，为评测提供新思路。
arXiv:2601.18253v2 Announce Type: replace-cross Abstract: Accurate evaluation of user satisfaction is critical for iterative development of conversati…
7
Scaling Up Thermodynamic AI Models
基于伊辛模型的热力学计算设备，为低功耗 AI 推理和边缘计算带来可扩展新路径。
arXiv:2607.00170v1 Announce Type: cross Abstract: Thermodynamic computing devices based on the Ising model show great promise for low-power AI inferen…
8
Synthetic Interaction Data for Scalable Personalization in Large Language Models
用合成交互数据破解LLM个性化扩展难题，数据瓶颈的新解法。
arXiv:2602.12394v2 Announce Type: replace Abstract: Personalized prompting offers large opportunities for deploying large language models (LLMs) to di…
9
PostgreSQL-Compatible Databases for AI at Scale
AI项目选数据库别踩坑：PostgreSQL兼容可能是甜蜜陷阱，看清扩展性与架构债务再决定。
Article URL: https://www.cockroachlabs.com/blog/postgresql-compatible-databases-ai-scale/ Comments URL: https://news.ycombinator.com/item?id=48718811 …
10
DataStates-LLM: Scalable Checkpointing for Transformer Models Using Composable State Providers
万亿参数模型训练中，检查点瓶颈如何破？这项研究提出可组合状态提供者的可扩展方案，直击分布式训练痛点。
arXiv:2601.16956v1 Announce Type: cross Abstract: The rapid growth of Large Transformer-based models, specifically Large Language Models (LLMs), now s…
11
ReproRepo: Scaling Reproducibility Audits with GitHub Repository Issues
用GitHub Issues实现大规模可重复性审计，让科研结果更可信的新框架。
arXiv:2606.18237v1 Announce Type: cross Abstract: Reproducing research results from papers and released code is central to scientific progress. Existi…
12
Do You Really Need a GPU to Guard Your LLM? CPU-Class Classifiers and Multi-Stage Pipelines for Safety Enforcement at Scale
揭示CPU级分类器在多阶段安全管道中高效防护LLM，打破GPU依赖，量产安全新思路。
arXiv:2512.19011v3 Announce Type: replace-cross Abstract: Safety classifiers that screen LLM inputs for jailbreak attempts have become standard deploy…
13
Edu-Theater: A Data-Efficient Agent Framework for Scalable Learner Behavior Simulation through Staging Roll-Call
让AI模拟学习者行为更省数据？这个教育代理框架通过点名机制实现高效仿真，教育科技研究的新利器。
arXiv:2606.15225v1 Announce Type: cross Abstract: Large-scale learner-task interaction data are crucial for intelligent educational systems but are co…
14
MCR-VQGAN: A Scalable and Cost-Effective Tau PET Synthesis Approach for Alzheimer's Disease Imaging
用MCR-VQGAN模型低成本合成Tau PET影像，为阿尔茨海默病诊断提供可扩展的新方案
arXiv:2512.15947v2 Announce Type: replace-cross Abstract: Tau positron emission tomography (PET) is a critical diagnostic modality for Alzheimer's dis…
15
Efficient Scaling of LLM Training with Flexible Context Parallelism
大模型训练新突破：灵活上下文并行策略，高效扩展LLM训练边界
arXiv:2602.21788v2 Announce Type: replace-cross Abstract: Scaling long-context capabilities is crucial for Large Language Models (LLMs). However, real…
16
Defending Against Malicious Finetuning by Scaling Train-time Adversarial Attacks
通过扩大训练时对抗攻击规模，提出防御恶意微调的新范式，为AI模型安全提供可扩展方案。
arXiv:2606.07970v1 Announce Type: new Abstract: Current open-weight large language models (LLMs) are prone to malicious finetuning attacks, which coul…
17
Scalable Joint Resource Allocation for SLO-Constrained LLM Inference in Heterogeneous GPU Clouds
面向异构GPU云的可扩展联合资源分配方案，高效保障LLM推理的SLO约束
arXiv:2604.07472v2 Announce Type: replace Abstract: Serving large language model (LLM) inference in cloud environments requires jointly optimizing mod…
18
SAGE: Scalable AI Governance & Evaluation
一篇关于可扩展AI治理与评估框架的前沿论文，为AI安全监管提供系统化解决方案
arXiv:2602.07840v3 Announce Type: replace-cross Abstract: Evaluating relevance in large-scale search systems is fundamentally constrained by the gover…
19
Beyond Retrieval: Learning Compact User Representations for Scalable LLM Personalization
提出学习紧凑用户表示替代传统检索，实现大规模LLM个性化，效率与效果兼得
arXiv:2606.04547v1 Announce Type: cross Abstract: Personalizing large language models requires adapting model behavior to individual users while prese…
20
Designing a scalable event-sourced analytics platform
事件溯源设计可扩展分析平台，用户行为事件驱动，状态重建与故障恢复一气呵成。
Designing a scalable event-sourced analytics platform Designing a scalable event-sourced analytics platform In modern data systems, you often need to …