cs.AI（2026-06-24）

📊 共 18 篇论文 | 🔗 1 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (11 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (5) 支柱四：生成式动作 (Generative Motion) (1) 支柱三：空间感知与语义 (Perception & Semantics) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (11 篇)

#题目一句话要点标签🔗⭐
1 Agentic evolution of physically constrained foundation models 提出一种物理约束下的多智能体发现引擎以解决硬件兼容性问题 generalist agent foundation model chain-of-thought
2 Privacy Vulnerabilities of Attention Layers in Tabular Foundation Models and Protection of High-Risk Queries 提出AMIA以解决表格基础模型的隐私漏洞问题 foundation model
3 BrainAgent: A Large Language Model-Driven Multi-Agent Framework for Autonomous Brain Signal Understanding 提出BrainAgent框架以解决脑信号理解的智能化问题 large language model
4 Supervised Post-training of Speech Foundation Models for Robust Adaptation in Speech Deepfake Detection 提出混帧后训练策略以增强语音深伪检测的鲁棒性 foundation model
5 Stabilizing black-box algorithms through task-oriented randomization 提出任务导向随机化方法以稳定黑箱算法 large language model
6 Helpful or Harmful? Evaluating LLM-Assisted Vulnerability Patching via a Human Study 评估LLM辅助漏洞修复的有效性与风险 large language model
7 Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface 提出可解释控制框架XCF以解决复杂控制系统的透明性问题 large language model
8 An Approach for a Supporting Multi-LLM System for Automated Certification Based on the German IT-Grundschutz 提出多大型语言模型系统以支持德国IT-Grundschutz的自动化认证 large language model
9 Evaluating LLMs on Real-World Software Performance Optimization 提出SWE-Pro基准以解决软件性能优化评估问题 large language model
10 STEB: A Speech-to-Speech Translation Expressiveness Benchmark for Evaluating Beyond Translation Fidelity 提出STEB以解决语音翻译中的表达性评估问题 large language model ✅
11 Long-Term Simulation Exposes Cognitive-Developmental Risks in AI Companions 提出TSJ框架以解决AI伴侣的认知发展风险评估问题 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (5 篇)

#题目一句话要点标签🔗⭐
12 InvestPhilBench: A Multi-Layer Dynamic Benchmark for Evaluating Large Language Model Procedural Reasoning in Expert Investment Philosophy 提出InvestPhilBench以评估大语言模型在投资哲学中的程序推理能力 MAE large language model
13 Omni-Perception Policy Optimization for Multimodal Emotion Reasoning 提出OPPO框架以优化多模态情感推理中的全感知能力 reinforcement learning multimodal
14 WinDOM: Self-Family Distillation for Small-Model GUI Grounding 提出WinDOM以解决小模型GUI定位数据获取与训练结合问题 reinforcement learning distillation
15 The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems 提出不可逃避的安全内核以解决AI系统控制问题 RLHF world model world models
16 Cliff Tokens: Identifying Single-Token Failure Triggers in LLM Mathematical Reasoning 提出悬崖标记以识别LLM数学推理中的单标记失败触发因素 DPO large language model

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
17 Decoupling Reconnaissance and Exploitation: Measuring the Capability Boundaries of LLM-Based Web Penetration Testing 提出两阶段解耦评估框架以提升LLM渗透测试能力 penetration large language model

🔬 支柱三：空间感知与语义 (Perception & Semantics) (1 篇)

#题目一句话要点标签🔗⭐
18 From Sounds to Scenes: A Benchmark for Evaluating Context-Aware Auditory Scene Understanding in Large Audio Language Models 提出CASU基准以解决音频场景理解的复杂性问题 scene understanding

⬅️ 返回 cs.AI 首页 · 🏠 返回主页