毫米波技术赋能人体测量，非接触高精度成像新方案，arXiv最新研究突破。
arXiv:2605.23064v1 Announce Type: cross Abstract: Body shape and circumferences are clinically informative biomarkers for risk stratification, includi…
单GPU实现凸优化方法，高效解决LLM偏好对齐难题，降低RLHF计算成本。
arXiv:2605.23244v1 Announce Type: new Abstract: Fine-tuning large language models (LLMs) to align with human preferences has driven the success of sys…
最新研究系统评估了大模型后训练中的“灾难性遗忘”，为提升模型持续学习能力提供关键方法论。
arXiv:2603.06610v2 Announce Type: replace Abstract: Large language model (LLM) post-training enhances latent skills, unlocks value alignment, improves…
首次探索如何利用基础模型推动因果生成建模，为新范式研究提供理论基石。
arXiv:2605.23861v1 Announce Type: cross Abstract: Causal generative modeling is essential for developing reliable and transparent AI systems capable o…
从稀疏横截面快照中学习个体动态演化的新方法，无需密集时间序列数据即可建模个体行为轨迹
arXiv:2605.23470v1 Announce Type: cross Abstract: Predicting how a dynamical unit evolves over time - how an individual ages, an epidemic spreads, or …
从文化演化理论解释大模型自我训练导致的模型崩溃，提出五个可证伪预测，填补语言学空白。
arXiv:2605.23054v1 Announce Type: cross Abstract: Model collapse, the progressive degradation of LLMs trained on their own outputs, has been character…
利用大模型蕴含的稀疏性先验，为高维数据特征选择提供鲁棒策略，理论贡献显著。
arXiv:2605.23102v1 Announce Type: cross Abstract: Large language models (LLMs) offer a scalable mechanism to elicit domain-informed prior information …
新方法「BarrierSteer」通过学习障碍引导机制提升大模型安全性，理论创新强，但缺乏实验细节。
arXiv:2602.20102v2 Announce Type: replace-cross Abstract: Despite the strong performance of large language models (LLMs) across diverse tasks, their s…
从零基础到AI研究员的8阶段系统学习路线，完整覆盖LLM核心理论与实践前沿。
Article URL: https://github.com/barvhaim/llm-learning-path Comments URL: https://news.ycombinator.com/item?id=48255624 Points: 1 # Comments: 0
用AI实时分析国际象棋走法，帮你理解每一步背后的战术逻辑
Two years ago, I simply could not get LLMs to reason about chess without (both me and the LLM) spiraling into fits. Today, things are different. Comme…
用Claude AI从零搭建全栈轮盘游戏并部署到AWS，边学边做的实战分享，适合想快速上手的开发者。
I wanted to build a roulette website. I also set out to learn. I have worked in IT for some time, started with Windows admin, moved to Linux, and then…
使用子采样NTK特征扩展贝叶斯最后层，提升大规模模型的不确定性量化与可扩展性，ICML 2026最新成果。
arXiv:2602.01279v2 Announce Type: replace Abstract: Bayesian Last Layers (BLLs) provide a convenient and computationally efficient way to estimate unc…
突破传统统一学习率，重尾分布指导LLM逐层自适应学习，大幅提升训练效率与模型性能。
arXiv:2605.22297v1 Announce Type: cross Abstract: Learning rate configuration is a fundamental aspect of modern deep learning. The prevailing practice…
GRPO新变体F-TIS：通过多模型协作提升LLM后训练奖励信号多样性，突破单一策略局限。
arXiv:2605.22537v1 Announce Type: new Abstract: Reinforcement learning methods such as GRPO have seen great popularity in LLM post-training. In GRPO, …
破解多会话强化学习中记忆增强LLM智能体的公平信用分配难题，来自最新学术论文
arXiv:2605.21768v1 Announce Type: new Abstract: Memory-augmented LLM agents enable interactions that extend beyond finite context windows by storing, …
提出自进化元认知策略优化方法，让LLM红队测试更智能高效地发现安全漏洞。
arXiv:2605.10067v3 Announce Type: replace-cross Abstract: Red teaming is critical for uncovering vulnerabilities in Large Language Models (LLMs). Whil…
让保守的LLM在任务对话中主动出击，论文用奖励塑造RL解锁销售场景的前瞻策略。
arXiv:2605.22240v1 Announce Type: new Abstract: Proactive task-oriented dialogue (TOD), such as outbound sales, demands a persuasive agent that active…
亲手搭建AI网站生成器，从零到一的真实经验与教训，开发者必读。
I've been wanting to build something with AI for a while now. Not just a wrapper around ChatGPT, but something that actually feels useful. So I built …
突破异质智能体协同难题，提出HACRL框架，让类型各异的智能体高效协作学习。
arXiv:2603.02604v2 Announce Type: replace Abstract: We introduce Heterogeneous Agent Collaborative Reinforcement Learning (HACRL), a new Reinforcement…
探讨形式定理证明中对称性的选择，为自动推理提供新视角。
arXiv:2605.22257v1 Announce Type: cross Abstract: Formal theorem provers based on large language models (LLMs) are highly sensitive to superficial var…