cs.AI（2025-09-21）

📊 共 16 篇论文 | 🔗 3 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗2) 支柱二：RL算法与架构 (RL & Architecture) (3) 支柱三：空间感知与语义 (Perception & Semantics) (1) 支柱四：生成式动作 (Generative Motion) (1 🔗1) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (10 篇)

#题目一句话要点标签🔗⭐
1 A Chain-of-thought Reasoning Breast Ultrasound Dataset Covering All Histopathology Categories 构建BUS-CoT乳腺超声数据集，覆盖所有组织病理学类别，促进AI链式推理研究。 chain-of-thought
2 From Prediction to Understanding: Will AI Foundation Models Transform Brain Science? 探讨AI基础模型在脑科学中的应用：从预测到理解的挑战与机遇 foundation model
3 MoEs Are Stronger than You Think: Hyper-Parallel Inference Scaling with RoE 提出RoE：一种基于专家路由随机性的超并行推理方法，提升MoE模型性能。 large language model chain-of-thought
4 Governing Automated Strategic Intelligence 利用多模态大模型自动化战略情报分析，提升国家战略竞争力 foundation model multimodal
5 seqBench: A Tunable Benchmark to Quantify Sequential Reasoning Limits of LLMs seqBench：可调基准测试，量化LLM的序列推理能力极限 large language model
6 Similarity Field Theory: A Mathematical Framework for Intelligence 提出相似性场论，为理解智能系统提供数学框架。 large language model
7 MCTS-EP: Empowering Embodied Planning with Online Preference Optimization MCTS-EP：结合在线偏好优化的蒙特卡洛树搜索赋能具身智能规划 large language model ✅
8 Prompt-with-Me: in-IDE Structured Prompt Management for LLM-Driven Software Engineering Prompt-with-Me：IDE内结构化提示管理，提升LLM驱动的软件工程效率 large language model
9 AdaptiveGuard: Towards Adaptive Runtime Safety for LLM-Powered Software AdaptiveGuard：面向LLM软件的自适应运行时安全防护 large language model ✅
10 The Principles of Human-like Conscious Machine 提出类人意识机器的充分性判据与设计原则，探索通用人工智能新范式 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)

#题目一句话要点标签🔗⭐
11 Large Language Models as End-to-end Combinatorial Optimization Solvers 提出基于大语言模型的端到端组合优化求解器，无需中间步骤。 reinforcement learning large language model
12 LLMs as Layout Designers: Enhanced Spatial Reasoning for Content-Aware Layout Generation LaySPA：增强空间推理能力，利用LLM进行内容感知布局生成 reinforcement learning spatial relationship large language model
13 R1-Fuzz: Specializing Language Models for Textual Fuzzing via Reinforcement Learning R1-Fuzz：利用强化学习定制语言模型，提升文本模糊测试效率 reinforcement learning

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

#题目一句话要点标签🔗⭐
14 PGSTalker: Real-Time Audio-Driven Talking Head Generation via 3D Gaussian Splatting with Pixel-Aware Density Control PGSTalker：基于3D高斯溅射和像素感知密度控制的实时音频驱动说话头生成 3D gaussian splatting 3DGS gaussian splatting

🔬 支柱四：生成式动作 (Generative Motion) (1 篇)

#题目一句话要点标签🔗⭐
15 MaskVCT: Masked Voice Codec Transformer for Zero-Shot Voice Conversion With Increased Controllability via Multiple Guidances MaskVCT：基于掩码语音编解码Transformer的零样本语音转换，通过多重引导增强可控性 classifier-free guidance ✅

🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)

#题目一句话要点标签🔗⭐
16 Intention-aware Hierarchical Diffusion Model for Long-term Trajectory Anomaly Detection 提出意图感知的分层扩散模型IHiD，用于长期轨迹异常检测。 spatiotemporal

⬅️ 返回 cs.AI 首页 · 🏠 返回主页