cs.AI（2024-11-18）

📊 共 14 篇论文 | 🔗 2 篇有代码

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (10 🔗1) 支柱二：RL算法与架构 (RL & Architecture) (4 🔗1)

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

#题目一句话要点标签🔗⭐
1 Edge-Enhanced Dilated Residual Attention Network for Multimodal Medical Image Fusion 提出边缘增强的空洞残差注意力网络，用于多模态医学图像融合。 multimodal ✅
2 HistoEncoder: a digital pathology foundation model for prostate cancer HistoEncoder：用于前列腺癌数字病理学的预训练基础模型 foundation model
3 Search, Verify and Feedback: Towards Next Generation Post-training Paradigm of Foundation Models via Verifier Engineering 提出验证器工程，面向大模型后训练，通过搜索、验证与反馈提升模型能力。 foundation model
4 Exploring adversarial robustness of JPEG AI: methodology, comparison and new methods 提出评估JPEG AI对抗鲁棒性的新方法，并进行大规模对比实验 large language model
5 Artificial Scientific Discovery 探索人工科学发现：从AlphaGo到ChatGPT，构建自主生成研究的机器。 multimodal
6 AdaptLIL: A Gaze-Adaptive Visualization for Ontology Mapping AdaptLIL：一种基于眼动追踪的本体映射自适应可视化方法 multimodal
7 Generative AI on the Edge: Architecture and Performance Evaluation 在边缘设备上评估生成式AI：探索低成本硬件上的LLM推理性能 large language model
8 Topology-aware Preemptive Scheduling for Co-located LLM Workloads 提出拓扑感知抢占式调度方法，提升LLM混合工作负载资源利用率。 large language model
9 Alien Recombination: Exploring Concept Blends Beyond Human Cognitive Availability in Visual Art 提出Alien Recombination方法，探索AI在视觉艺术中超越人类认知局限的概念融合 large language model
10 PerfCodeGen: Improving Performance of LLM Generated Code with Execution Feedback PerfCodeGen：利用执行反馈提升LLM生成代码的性能 large language model

🔬 支柱二：RL算法与架构 (RL & Architecture) (4 篇)

#题目一句话要点标签🔗⭐
11 PSPO*: An Effective Process-supervised Policy Optimization for Reasoning Alignment 提出PSPO*框架，通过非线性奖励塑造提升LLM推理对齐效果 reward shaping large language model chain-of-thought
12 Syllabus: Portable Curricula for Reinforcement Learning Agents Syllabus：用于强化学习智能体的通用课程学习库 reinforcement learning curriculum learning ✅
13 Regret-Free Reinforcement Learning for LTL Specifications 针对未知动态系统的LTL规范，提出无悔强化学习算法 reinforcement learning
14 Hybrid Data-Driven SSM for Interpretable and Label-Free mmWave Channel Prediction 提出混合数据驱动SSM，用于可解释的无标签毫米波信道预测 SSM

⬅️ 返回 cs.AI 首页 · 🏠 返回主页