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…
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…
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…
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…
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…
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…
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…
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 …
悬浮三舱设计兼容旗舰硬件，为高端玩家提供极致散热与扩展空间。
IT之家 5 月 31 日消息，几何未来 (Geometric Future) 本周宣布将在 COMPUTEX 2026 台北国际电脑展上带来一系列的 2026~2027 年新品，包括首次公布的 Model 7 与 Model 7 Extreme。 Model 7 (Extreme) 原型产品采用悬…
开源工具包解决AI记忆中树结构数据的图遍历瓶颈，用向量搜索实现高效作用域检索。
Article URL: https://github.com/0xJaksun/lithium-core Comments URL: https://news.ycombinator.com/item?id=48319144 Points: 1 # Comments: 0
实际使用变通方法后才发现，它们无法扩展——这里有关于CLAUDE.md、Obsidian和Markdown经验的真实教训。
Every team using AI coding tools has invented their own version of the same hack. Some put everything in CLAUDE.md and commit it to the repo. Some mai…
LLM生成代码的溯源难题，这一新方案兼顾效率与可扩展性。
arXiv:2605.28510v1 Announce Type: cross Abstract: Large language models (LLMs) for code completion and generation are increasingly used in software de…
探索LLM欺骗探测线性探针的扩展性、鲁棒性与欺骗表示几何特性，为AI安全提供新视角。
arXiv:2605.27958v1 Announce Type: cross Abstract: Linear probes trained on LLM activations are increasingly proposed as deception-detection metrics, y…
通用智能体协作新框架，用可解释动态决策路径破解规模化合作难题
arXiv:2603.00309v2 Announce Type: replace Abstract: The increasingly popular agentic AI paradigm promises to harness the power of multiple, general-pu…
利用图像基础模型实现可扩展的3D人体放置，虚拟场景与AI融合的前沿突破。
arXiv:2604.19673v2 Announce Type: replace Abstract: Training embodied agents to understand 3D scenes as humans do requires large-scale data of people …
自动生成评估准则，为大规模强化学习训练大模型提供可扩展方案。
arXiv:2605.23454v1 Announce Type: new Abstract: Rubric-based rewards offer a promising way to extend reinforcement learning (RL) for large language mo…
提出在不确定性领域内扩展观测感知规划的新方法，为复杂环境决策提供可扩展方案。
arXiv:2605.22364v1 Announce Type: new Abstract: Deciding which sensing capabilities to deploy on an agent in uncertain domains is a fundamental engine…
专为评估训练大模型设计的可扩展可验证规划基准，填补LLM在复杂规划任务中的性能缺口。
arXiv:2605.20873v1 Announce Type: cross Abstract: Planning is a fundamental capability for large language models (LLMs) because such complex tasks req…
打破多模态数据对齐瓶颈，论文提出仅用成对模态训练MLLM，显著提升跨域可扩展性。
arXiv:2605.21059v1 Announce Type: cross Abstract: Despite the impressive results achieved by multimodal large language models (MLLMs), their training …
提出小语言模型Med-V1，零样本实现生物医学证据归因，兼顾规模与可扩展性
arXiv:2603.05308v2 Announce Type: replace Abstract: Assessing whether an article supports an assertion is essential for hallucination detection and cl…