cs.LG（2025-01-09）
📊 共 9 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) (4 🔗1)
支柱二：RL算法与架构 (RL & Architecture) (4)
支柱八：物理动画 (Physics-based Animation) (1)
🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | Analyzing Memorization in Large Language Models through the Lens of Model Attribution | 通过模型归因分析大型语言模型中的记忆现象 | large language model | ||
| 2 | Mechanistic understanding and validation of large AI models with SemanticLens | SemanticLens：利用语义空间理解和验证大型AI模型 | foundation model multimodal | ✅ | |
| 3 | Accelerated Diffusion Models via Speculative Sampling | 提出基于推测采样的加速扩散模型方法，显著提升生成速度。 | large language model | ||
| 4 | Deriving Coding-Specific Sub-Models from LLMs using Resource-Efficient Pruning | 提出基于Wanda剪枝的编程语言特定子模型提取方法，降低LLM计算需求。 | 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 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Knowledge Transfer in Model-Based Reinforcement Learning Agents for Efficient Multi-Task Learning | 提出一种基于知识蒸馏的模型强化学习方法，用于高效多任务学习。 | reinforcement learning world model distillation | ||
| 6 | FedSA: A Unified Representation Learning via Semantic Anchors for Prototype-based Federated Learning | FedSA：通过语义锚点统一表征学习，解决原型联邦学习中的异构性问题。 | representation learning contrastive learning | ||
| 7 | Session-Level Dynamic Ad Load Optimization using Offline Robust Reinforcement Learning | 提出基于离线鲁棒强化学习的会话级动态广告加载优化方法 | reinforcement learning | ||
| 8 | Transformer-Squared: Self-adaptive LLMs | Transformer-Squared：通过自适应调整LLM权重矩阵奇异分量，实现高效的任务泛化 | reinforcement learning large language model |
🔬 支柱八：物理动画 (Physics-based Animation) (1 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 9 | A Multi-Layer CNN-GRUSKIP model based on transformer for spatial TEMPORAL traffic flow prediction | 提出基于Transformer的多层CNN-GRUSKIP模型，用于时空交通流量预测。 | spatiotemporal |