提出Thinking Seeds方法，利用历史多样性与位置感知强化学习，显著提升LLM推理效率与泛化能力。
arXiv:2601.21476v2 Announce Type: replace Abstract: On-policy reinforcement learning (RL) for language model post-training suffers from a fundamental …
用LLM模拟AI组织中的单极vs多极、隐藏vs可见代理等权衡，一个值得探索的新方向
Currently there doesn't seem to be anyone trying to simulate the tradeoffs between a singleton and a multipolar setup. Or looking at other tradeoffs l…
揭秘AI群体智慧的核心：多样性如何成为提升AI性能的关键力量，来自ICML 2026工作坊的前沿研究。
arXiv:2606.29661v1 Announce Type: new Abstract: Top AI forecasting systems are approaching superforecaster-level accuracy on future world events, but …
濒危物种保护迈入基因组时代，美国启动计划为全部濒危物种测序，助力精准恢复。
Colossal Biosciences will be biobanking tissues from all of them as well.
揭秘LLM生成教育任务的“人工蜂群”效应，新方法提升内容多样性，推动大规模教育内容定制化。
arXiv:2512.23601v2 Announce Type: replace Abstract: Large language models (LLMs) have shown the potential for generating educational content at scale,…
LLM生成故事的角色多样性研究，ACL 2026论文揭示模型角色生成规律。
arXiv:2606.22454v1 Announce Type: cross Abstract: As LLM-generated text is increasingly used, especially in fictional domains, we explore how much LLM…
研究指出大语言模型生成故事的同质化问题，用叙事学框架揭示AI创造力边界
arXiv:2606.17350v1 Announce Type: cross Abstract: Recent advances in large language models (LLMs) have enabled the generation of high-quality prose, y…
探讨生成式AI领域竞争如何影响模型多样性，为AI生态健康发展提供理论视角
arXiv:2412.08610v3 Announce Type: replace-cross Abstract: Recent evidence, both in the lab and in the wild, suggests that the use of generative artifi…
从DSM-5的官方定义出发，重新思考自闭症的本质，挑战传统诊断框架的局限。
When I attend tech conferences, people usually know me — if they do — for my work on Cilium and my labs. That started changing recently. At the last t…
一篇探讨LLM智能体在社会科学分析中如何平衡方法论多样性、经验一致性与解释脆弱性的前沿学术论文
arXiv:2606.11456v1 Announce Type: cross Abstract: The deployment of LLM-based agents in scientific analysis raises opposing concerns: that agents may …
揭露AI生成语言暗中强化标准语言意识形态，关乎语言多样性与公平性
arXiv:2406.08726v3 Announce Type: replace Abstract: Large language models (LLMs) generate text that reinforces standard language ideology: a bias towa…
提出条件Vendi评分，首个能结合提示上下文评估生成模型多样性的方法，精准衡量AI创造力。
arXiv:2411.02817v2 Announce Type: replace-cross Abstract: Generative models guided by text prompts are widely evaluated for fidelity and prompt alignm…
LLM驱动的科学假设搜索新方法，探索多样化发现潜力
arXiv:2606.10587v1 Announce Type: cross Abstract: Large language models (LLMs) are on the rise for accelerating scientific discovery, most recently in…
直指当前LLM集中化弊端，提出模块化参与机制以拥抱人类智能多样性。
arXiv:2606.07812v1 Announce Type: cross Abstract: Humanity is a mosaic of multifaceted talents and needs, and any truly intelligent AI must reflect th…
世界级多模态推理基准WorldBench，以视觉多样性挑战AI大模型综合能力。
arXiv:2606.06538v1 Announce Type: new Abstract: In real-world applications, models are expected to perform reliably across diverse settings. Yet, many…
揭露AI评估中的地理偏见问题，呼吁提升评测多样性，为公平AI提供新视角
arXiv:2606.05187v1 Announce Type: cross Abstract: Among the many challenges hindering the responsible development and deployment of AI, arguably none …
为LLM后训练设计新方法REDIPO，在不损失对齐的前提下恢复输出多样性，解决指令回答单一化问题。
arXiv:2605.30021v2 Announce Type: replace Abstract: Many open-ended instructions have multiple valid answers that users can benefit from seeing, but p…
一种注册绑定的LLM管道，为热带植物、水生动物及异宠的性状提取提供可溯源证据，方法论严谨且跨物种适用。
arXiv:2606.00994v1 Announce Type: new Abstract: We describe a registry-bound large-language-model extraction pipeline producing evidence-grounded stru…
用质量多样性进化算法系统性挖掘LLM安全漏洞，突破传统对抗测试的局限
arXiv:2606.00801v1 Announce Type: cross Abstract: Current approaches to LLM adversarial testing suffer from coverage gaps: manual red-teaming does not…
用基础模型保持多样性，用对齐模型保证质量，BACo方法在推理时融合两者输出，实现高质量与多样性的双赢。
arXiv:2511.05650v2 Announce Type: replace-cross Abstract: Alignment has greatly improved large language models (LLMs)' output quality at the cost of d…