cs.LG（2024-11-25）

📊 共 11 篇论文

🎯 兴趣领域导航

支柱九：具身大模型 (Embodied Foundation Models) (9) 支柱二：RL算法与架构 (RL & Architecture) (1) 支柱七：动作重定向 (Motion Retargeting) (1)

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

#	题目	一句话要点	标签	🔗	⭐
1	Unraveling Arithmetic in Large Language Models: The Role of Algebraic Structures	利用代数结构提升大语言模型算术能力，实现更强的泛化性	large language model chain-of-thought
2	Probing the limitations of multimodal language models for chemistry and materials research	MaCBench：评估多模态语言模型在化学与材料研究中的局限性	multimodal
3	A quantum inspired predictor of Parkinsons disease built on a diverse, multimodal dataset	提出基于多模态数据集和量子启发算法的帕金森病预测模型，提升早期诊断准确性。	multimodal
4	Representation Collapsing Problems in Vector Quantization	研究向量量化中的表征坍塌问题，并提出缓解方案	large language model
5	Fundamental Limits of Prompt Tuning Transformers: Universality, Capacity and Efficiency	探究Prompt Tuning Transformer的根本限制：通用性、容量与效率	foundation model
6	Interpreting Language Reward Models via Contrastive Explanations	提出基于对比解释的语言奖励模型可解释性分析方法	large language model
7	Speculative Decoding with CTC-based Draft Model for LLM Inference Acceleration	提出基于CTC的推测解码方法，提升LLM推理加速时的草稿接受率	large language model
8	MixPE: Quantization and Hardware Co-design for Efficient LLM Inference	MixPE：面向高效LLM推理的量化与硬件协同设计	large language model
9	Adaptive Circuit Behavior and Generalization in Mechanistic Interpretability	研究揭示GPT-2小型模型IOI电路在不同提示下的泛化能力与适应性	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	Video-Text Dataset Construction from Multi-AI Feedback: Promoting Weak-to-Strong Preference Learning for Video Large Language Models	提出MMAIP-V数据集与Iter-W2S-RLAIF框架，提升视频大语言模型在VQA任务中的对齐能力。	preference learning large language model multimodal

🔬 支柱七：动作重定向 (Motion Retargeting) (1 篇)

#	题目	一句话要点	标签	🔗	⭐
11	Graph Adapter of EEG Foundation Models for Parameter Efficient Fine Tuning	提出EEG-GraphAdapter，用于脑电图基础模型的参数高效微调	spatial relationship foundation model

⬅️ 返回 cs.LG 首页 · 🏠 返回主页