cs.AI（2026-07-24）

📊 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) (11 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (4) 支柱六：视频提取与匹配 (Video Extraction) (1)

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

#题目一句话要点标签🔗⭐
1 CausalForge: A Formally Grounded, Self-Improving Agentic Framework for Automated Research in Causal Inference 提出CausalForge框架以解决因果推断研究的自动化问题 large language model ✅
2 TRACE-ROUTER: Task-Consistent and Adaptive Online Routing for Agentic AI 提出TRACE-Router以解决长时序任务的路由问题 large language model
3 HiKV: Hierarchical Importance-Aware KV Cache with Hardware Acceleration for LLM Decoding 提出HiKV以解决长上下文大语言模型解码中的KV缓存瓶颈问题 large language model
4 Unified Static-Dynamic Pruning for Efficient LLM Inference 提出统一静态-动态剪枝以提升LLM推理效率 large language model
5 Opaque Epistemic Mediation: How LLM Deployment Configurations Shape the Validation of Pseudo-Science 探讨LLM配置对伪科学验证的影响 large language model
6 MineValiCoder: Reliable Code Generation with Test Case Quality Mining and Bipartite Graph-Based Mutual Validation 提出MineValiCoder以解决代码生成中的测试用例质量问题 large language model
7 A Self-Calibrating Agentic AI Framework for Autonomous Edge Resource Allocation 提出自校准代理AI框架以解决自主边缘资源分配问题 large language model
8 IDEAgent: Agentic Quality-Diversity Search for Research Idea Generation 提出IDEAgent以解决研究创意生成中的质量与多样性问题 large language model ✅
9 Towards Trustworthy and Cost-Efficient Data Integration: From Naïve RAG to Agentic RAG 提出基于知识的RAG以解决企业数据集成的信任与成本问题 large language model
10 Neptuna: A Comprehensive Machine Learning Framework for Benchmarking Complex Multiphase Flows 提出Neptuna框架以解决复杂多相流的基准测试问题 foundation model ✅
11 Semiotic logical hexagon theory for LLM logical reasoning 提出HexLogicAgent以解决LLM逻辑推理中的语义组织问题 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🔗⭐
12 PRIMS: Physics-guided Representation for Fluid Identification in Multimodal Sensing 提出PRIMS以解决微流体识别中的物理关系问题 representation learning multimodal
13 TRW: TRACE-RealWorld---An Auditable Consistency Contract for World Models as Materialized Views 提出TRACE-RealWorld以解决动态物理世界中的一致性管理问题 world model world models predictive model
14 Deconstructing Off-Policy Ratios: Entropy-Scaled Trust Regions for Asynchronous Reinforcement Learning 提出熵缩放信任区域以解决异步强化学习中的数据不稳定问题 reinforcement learning large language model
15 Learning as Reasoning Unfolds: Progressive Rollout Allocation for Efficient Reinforcement Learning 提出VIGOR以解决GRPO在强化学习中的效率问题 reinforcement learning chain-of-thought

🔬 支柱六：视频提取与匹配 (Video Extraction) (1 篇)

#题目一句话要点标签🔗⭐
16 Zero-Shot Mission-Level Evaluation for Aerial MLLM Agents 提出MissionBench以评估空中多模态大语言模型的任务能力 egocentric embodied AI large language model

⬅️ 返回 cs.AI 首页 · 🏠 返回主页