cs.AI（2024-12-27）

📊 共 10 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) (9 🔗3) 支柱二：RL算法与架构 (RL & Architecture) (1)

🔬 支柱九：具身大模型 (Embodied Foundation Models) (9 篇)

#	题目	一句话要点	标签	🔗	⭐
1	Hindsight Planner: A Closed-Loop Few-Shot Planner for Embodied Instruction Following	提出Hindsight Planner，解决具身指令跟随任务中少样本规划的鲁棒性问题	large language model instruction following
2	"Did my figure do justice to the answer?" : Towards Multimodal Short Answer Grading with Feedback (MMSAF)	提出MMSAF：一个多模态短答案评分与反馈问题及数据集，用于提升开放式问题自动评分。	large language model multimodal
3	Find the Intention of Instruction: Comprehensive Evaluation of Instruction Understanding for Large Language Models	提出IoInst基准，评估大语言模型在干扰信息下的指令理解能力	large language model instruction following
4	A Survey on Large Language Model Acceleration based on KV Cache Management	综述：基于KV缓存管理的大语言模型加速方法研究	large language model multimodal	✅
5	Toward Adaptive Reasoning in Large Language Models with Thought Rollback	提出Thought Rollback框架，提升大语言模型在复杂推理任务中的自适应性和纠错能力	large language model
6	Position: Theory of Mind Benchmarks are Broken for Large Language Models	揭示大语言模型心智理论评测的局限性，提出功能性心智理论评估方法	large language model
7	An Engorgio Prompt Makes Large Language Model Babble on	提出Engorgio方法，通过构造恶意prompt增加大语言模型推理成本，影响服务可用性。	large language model	✅
8	Boosting Private Domain Understanding of Efficient MLLMs: A Tuning-free, Adaptive, Universal Prompt Optimization Framework	提出IDEAL Prompt框架，无需微调即可提升EMLLM在私有领域的理解能力	large language model multimodal
9	Xmodel-2 Technical Report	Xmodel-2：一个12亿参数的推理专用大语言模型，实现高效训练和卓越性能。	large language model	✅

🔬 支柱二：RL算法与架构 (RL & Architecture) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
10	Adaptive Context-Aware Multi-Path Transmission Control for VR/AR Content: A Deep Reinforcement Learning Approach	提出ACMPTCP，利用深度强化学习优化AR/VR内容的多路径传输控制。	reinforcement learning deep reinforcement learning DRL

⬅️ 返回 cs.AI 首页 · 🏠 返回主页