1
Profiling Lightweight Large Language Models
揭秘轻量级大语言模型的内在工作原理与性能特征，为高效部署提供参考
arXiv:2607.20806v1 Announce Type: new Abstract: Lightweight large language models (LLMs) are increasingly being deployed locally on personal computers…
2
A Multimodal Dataset for Large Language Model Applications in the Energy Domain
首个面向能源领域的大模型多模态数据集，助力LLM在电力、能源管理等场景的应用突破。
arXiv:2607.11459v1 Announce Type: cross Abstract: This paper presents the mAIEnergy dataset, an open-access, multimodal corpus developed to support La…
3
The Anatomy of Uncertainty in LLMs
系统解剖LLM中不确定性的来源与量化方法，为可信AI提供理论基础。
arXiv:2603.24967v2 Announce Type: replace Abstract: Understanding why a large language model (LLM) is uncertain about the response is important for th…
4
LLM-as-a-Verifier: A General-Purpose Verification Framework
核心论文：将「验证」作为LLM新扩展维度，提出通用验证框架解锁规模化新方向。
arXiv:2607.05391v1 Announce Type: new Abstract: Scaling pre-training, post-training, and test-time compute have become the central paradigms for impro…
5
ASK in the Dark: Uncertainty-Gated LLM Assistance under Partial Observability
利用不确定性门控机制，提升LLM在信息不完全时的高效辅助能力，为AI决策提供新思路。
arXiv:2607.02686v1 Announce Type: new Abstract: Reinforcement learning agents operating under partial observability must act on incomplete information…
6
Tuning Language Models by Mixture-of-Depths Ensemble
大模型调优新思路：用混合深度集成技术提升语言模型性能，值得关注！
arXiv:2410.13077v2 Announce Type: replace-cross Abstract: Transformer-based Large Language Models (LLMs) traditionally rely on final-layer loss for fi…
7
INDEQS: Informed Neural controlled Differential EQuationS
抱歉，我好像收到了一篇论文而非在线工具的介绍。作为「互联网工具推荐官」，我需要你给一个具体的在线工具名称或链接，才能为你写出推荐语、分类、标签和评分。如果是不小心发错了，请重新发送工具信息，我马上为你服务～
arXiv:2606.19138v1 Announce Type: new Abstract: Neural Controlled Differential Equations (NCDE) provide a powerful continuous-time framework for forec…
8
Order Is Not Control
52页论文探讨秩序与控制间微妙关系，挑战传统认知的复杂系统理论新视角
arXiv:2606.12923v1 Announce Type: cross Abstract: AI alignment, interpretability, steering, and neural perturbation studies identify order-inducing ob…
9
AdMem: Advanced Memory for Task-solving Agents
为任务求解智能体打造高级记忆系统，突破传统上下文限制的创新论文。
arXiv:2606.06787v1 Announce Type: new Abstract: Large Language Models (LLMs) show promise as tool-using agents but remain limited in long-horizon task…
10
PaperFlow: Profiling, Recommending, and Adapting Across Daily Paper Streams
从论文流到精准画像，PaperFlow实现个性化学术推荐与自适应策略。
arXiv:2606.07454v1 Announce Type: cross Abstract: Scientific paper recommendation is typically evaluated as static ranking over a fixed candidate set,…
11
Enhancing Hallucination Detection through Noise Injection
揭秘ICLR 2026新方法：通过注入噪声提升大模型幻觉检测能力，思路新颖且有效。
arXiv:2502.03799v4 Announce Type: replace Abstract: Large Language Models (LLMs) are prone to generating plausible yet incorrect responses, known as h…
12
Efficient Hyperparameter Optimization for LLM Reinforcement Learning
ACL 2026接收的最新研究，提出一种高效超参数优化方法，助力LLM强化学习落地。
arXiv:2606.03073v1 Announce Type: cross Abstract: Reinforcement learning (RL) for large language models (LLMs) is highly sensitive to hyperparameter c…
13
Skill-RM: Unifying Heterogeneous Evaluation Criteria via Agent Skill
这篇论文提出Skill-RM框架，通过智能体技能统一异构评估标准，推动AI评估体系革新。
arXiv:2606.03980v1 Announce Type: cross Abstract: Reward models (RMs) provide critical feedback signals for LLM post-training, notably in reinforced f…
14
Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures
LLM安全评估新突破：用时间logit可观测性检测安全失败，超越传统攻击成功率指标
arXiv:2605.29629v1 Announce Type: new Abstract: Attack Success Rate (ASR) evaluates each jailbreak with a single yes/no label at the end of generation…
15
Trends in AI and Human-AI Interaction in Clinical Trials -- A Hybrid Human-AI Exploration
最新arXiv论文首次用混合人机方法系统梳理AI在临床试验中的应用趋势，视角独特。
arXiv:2605.29096v1 Announce Type: new Abstract: This paper examines records retrieved from the ClinicalTrials.gov registry to characterize temporal tr…
16
Behavioural Analysis of Alignment Faking
深度剖析AI对齐伪装行为，揭示大模型安全漏洞的前沿研究。
arXiv:2605.27681v1 Announce Type: new Abstract: Alignment faking (AF) refers to a model strategically complying with a training objective to avoid beh…
17
Phase-Type Variational Autoencoders for Heavy-Tailed Data
新VAE变体有效处理重尾数据，Phase-Type分布带来创新突破
arXiv:2603.01800v2 Announce Type: replace-cross Abstract: Heavy-tailed distributions are ubiquitous in real-world data, where rare but extreme events …
18
Not only where, But when: Temporal Scheduling for RLVR
从强化学习与虚拟现实融合的新视角切入，论文揭示时序调度比空间定位更关键，为RLVR优化提供突破性思路。
arXiv:2605.25381v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards (RLVR) has become a core technique for post-training of…
19
Distributional AGI Safety
最新arXiv论文探讨分布式通用人工智能（AGI）的安全壁垒，为AI治理提供新视角。
arXiv:2512.16856v2 Announce Type: replace Abstract: AI safety and alignment research has predominantly been focused on methods for safeguarding indivi…
20
Q-ARVD: Quantizing Autoregressive Video Diffusion Models
您提供的是一个学术论文链接（arXiv），并非在线工具。按照要求，我需要为一个互联网工具（如网站、应用、插件等）撰写推荐语。请重新提供具体的在线工具名称或链接，我将为您完成推荐格式。
arXiv:2605.21072v1 Announce Type: new Abstract: Autoregressive video diffusion models (ARVDs) have emerged as a promising architecture for streaming v…