cs.LG（2025-07-22）
📊 共 5 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | CIMR: Contextualized Iterative Multimodal Reasoning for Robust Instruction Following in LVLMs | CIMR：上下文迭代多模态推理，提升LVLM在复杂指令跟随任务中的鲁棒性 | large language model multimodal instruction following | ||
| 2 | SiLQ: Simple Large Language Model Quantization-Aware Training | SiLQ：一种简易的大语言模型量化感知训练方法，显著提升量化模型精度。 | large language model | ||
| 3 | Steering Out-of-Distribution Generalization with Concept Ablation Fine-Tuning | 提出概念消融微调(CAFT)，无需修改训练数据即可引导LLM的分布外泛化。 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (2 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 4 | Scaling Linear Attention with Sparse State Expansion | 提出基于稀疏状态扩展的线性注意力机制，有效处理长上下文建模问题。 | reinforcement learning linear attention | ||
| 5 | Sensor Drift Compensation in Electronic-Nose-Based Gas Recognition Using Knowledge Distillation | 提出基于知识蒸馏的电子鼻传感器漂移补偿方法，显著提升气体识别精度。 | distillation |