表格数据基础模型如何兼顾公平性？ICML spotlight论文提出全新训练思路，AI公平性研究者必读。
arXiv:2608.14211v1 Announce Type: cross Abstract: Tabular Foundation Models (TFMs) have emerged as leading methods for tabular predictive tasks, lever…
用反事实基准和训练方法破解大模型事实一致性与异质知识推理的排序难题
arXiv:2608.07838v1 Announce Type: new Abstract: Large language models (LLMs) have increasingly supported response generation grounded in user-provided…
多模态大模型如何在推理中平衡效率与效果？这篇ACM MM论文提出无训练注意力引导切换，值得关注。
arXiv:2608.03450v1 Announce Type: cross Abstract: Reasoning in Multimodal Large Language Models (MLLMs) requires both fine-grained visual perception a…
无需训练，LLM直接为度假租赁长尾房源生成推荐候选，破解协同过滤信号稀疏难题。
arXiv:2607.09877v1 Announce Type: new Abstract: Vacation rental marketplaces face a structural imbalance on the supply side: a small fraction of prope…
LLM在医疗推理中常产生幻觉，这篇论文提出FaithMed训练范式，确保模型忠实引用证据，提升可靠性。
arXiv:2607.01440v1 Announce Type: new Abstract: Faithful reasoning is essential in medicine, where clinical decisions require transparent justificatio…
这项研究提出决策感知训练方法，让生成模型直接优化下游决策目标，突破传统仅追求样本分布的局限。
arXiv:2607.01171v1 Announce Type: new Abstract: Sample-based generative models are increasingly used for probabilistic forecasting in high-stakes deci…
无需训练即可生成概念级局部解释，低成本可解释AI新思路，值得关注。
arXiv:2606.29069v1 Announce Type: cross Abstract: Concept-based Explainable AI (C-XAI) seeks human-understandable explanations grounded in semantic co…
Transformer遇上自动化规划，对称性感知训练让AI规划更高效精准。
arXiv:2508.07743v2 Announce Type: replace Abstract: While transformers excel in many settings, their application in the field of automated planning is…
详解大模型强化学习全流程，从MDP构建到探索学习的模块化指南，前沿且系统。
arXiv:2606.21943v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become central to LLM post-training, yet the methods that dominate c…
揭秘无训练AI图像检测器的脆弱性，系统评估分数方向、预处理与压缩的三重影响。
arXiv:2606.20488v1 Announce Type: new Abstract: Training-free detectors of AI-generated images promise generator-agnostic deployment without classifie…
无需训练即可增强计算MRI的对抗鲁棒性，ICML 2026论文提出全新方法。
arXiv:2501.01908v4 Announce Type: replace-cross Abstract: Deep learning (DL) methods have become the state-of-the-art for reconstructing sub-sampled m…
网友质疑Anthropic新模型Claude Fable 5是全新架构还是仅数据优化，引发版本命名逻辑讨论
I am trying to understand why Claude Fable 5 is different, is it a new architecture, or trained from scratch or just a better fine tuning on top of Op…
多智能体LLM训练新范式：引入角色分解与跨智能体学习信号，实现高效协作与分工。
arXiv:2606.10684v1 Announce Type: cross Abstract: Modern language agents which perform multi-step reasoning have shown strong performance in knowledge…
用概率程序生成推理数据，有效提升LLM的归纳推理能力，方法新颖且可复现。
arXiv:2606.09856v1 Announce Type: cross Abstract: Post-training Large Language Models (LLMs) for reasoning typically focuses on deductive tasks such a…
新方法RePo让大模型重新调整上下文位置，提升长文本理解与推理能力。
arXiv:2512.14391v3 Announce Type: replace-cross Abstract: In-context learning is fundamental to modern Large Language Models (LLMs); however, prevaili…
预训练阶段引入强化学习探索，重新审视LLM策略优化方法，带来新训练范式视角。
arXiv:2606.04272v1 Announce Type: new Abstract: The standard LLM training pipeline applies reinforcement learning (RL) only after pre-training and sup…
无需训练，仅通过反转输入文本，就能显著提升解码器LLM的文本嵌入质量。
arXiv:2606.05858v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened new avenues for generating training-free t…
自蒸馏让大模型在难题上学会专家推理，摆脱依赖更强模型或采样正确解的局限
arXiv:2602.02405v2 Announce Type: replace-cross Abstract: Improving the reasoning capabilities of large language models (LLMs) typically relies either…
自监督训练上下文记忆，为长文本理解提供新范式
arXiv:2606.03197v1 Announce Type: new Abstract: Memory is an indispensable capability for long-horizon LLM agents, enabling them to preserve and utili…
新方法InfoMem用答案条件信息增益训练长上下文记忆代理，大幅提升模型知识检索与记忆能力。
arXiv:2606.03329v1 Announce Type: new Abstract: Long-context tasks require LLMs to identify and preserve answer-relevant information from large contex…