cs.AI（2026-03-11）

📊 共 13 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) (5) 支柱二：RL算法与架构 (RL & Architecture) (5 🔗1) 支柱三：空间感知与语义 (Perception & Semantics) (2) 支柱八：物理动画 (Physics-based Animation) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (5 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Resource-constrained Amazons chess decision framework integrating large language models and graph attention	提出结合大语言模型和图注意力网络的资源受限Amazons棋决策框架	large language model foundation model
2	A Platform-Agnostic Multimodal Digital Human Modelling Framework: Neurophysiological Sensing in Game-Based Interaction	提出一种平台无关的多模态数字人建模框架，用于游戏交互中的神经生理传感研究。	multimodal
3	Utility Function is All You Need: LLM-based Congestion Control	GenCC：利用LLM自动生成拥塞控制效用函数，显著提升网络性能	large language model chain-of-thought
4	Speaker Verification with Speech-Aware LLMs: Evaluation and Augmentation	提出一种基于语音感知LLM的说话人验证方法，并进行评估和增强。	large language model
5	Conversational AI-Enhanced Exploration System to Query Large-Scale Digitised Collections of Natural History Museums	提出基于对话式AI的探索系统，用于查询大型自然历史博物馆数字化馆藏	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	🔗	⭐
6	Does LLM Alignment Really Need Diversity? An Empirical Study of Adapting RLVR Methods for Moral Reasoning	验证性奖励强化学习可有效迁移至道德推理，无需显式多样性机制	reinforcement learning large language model
7	IH-Challenge: A Training Dataset to Improve Instruction Hierarchy on Frontier LLMs	提出IH-Challenge数据集以提升前沿LLM的指令层次性	reinforcement learning instruction following	✅
8	HEAL: Hindsight Entropy-Assisted Learning for Reasoning Distillation	提出HEAL框架，通过后见之明熵辅助学习提升推理蒸馏效果	distillation
9	Adaptive RAN Slicing Control via Reward-Free Self-Finetuning Agents	提出基于自精调Agent的自适应RAN切片控制方法，无需人工奖励。	reinforcement learning large language model
10	Quantum entanglement provides a competitive advantage in adversarial games	量子纠缠提升对抗博弈强化学习性能：以Pong游戏为例	reinforcement learning representation learning

🔬 支柱三：空间感知与语义 (Perception & Semantics) (2 篇)

#	题目	一句话要点	标签	🔗	⭐
11	EvoSchema: Towards Text-to-SQL Robustness Against Schema Evolution	EvoSchema：针对数据库模式演变的文本到SQL鲁棒性评测基准	semantic mapping semantic map
12	Structured Linked Data as a Memory Layer for Agent-Orchestrated Retrieval	利用结构化链接数据增强Agent编排的检索式生成系统	affordance

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

#	题目	一句话要点	标签	🔗	⭐
13	Human Presence Detection via Wi-Fi Range-Filtered Doppler Spectrum on Commodity Laptops	提出基于Wi-Fi测距滤波多普勒频谱的人体存在检测方案，无需额外硬件。	PULSE

⬅️ 返回 cs.AI 首页 · 🏠 返回主页