cs.LG（2024-12-09）
📊 共 7 篇论文
🎯 兴趣领域导航
🔬 支柱九：具身大模型 (Embodied Foundation Models) (4 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 1 | How to Merge Your Multimodal Models Over Time? | 提出TIME框架，解决多模态模型随时间演进的增量式融合问题 | foundation model multimodal | ||
| 2 | Refusal Tokens: A Simple Way to Calibrate Refusals in Large Language Models | 提出Refusal Tokens，通过简单方式校准大语言模型的拒绝行为 | large language model | ||
| 3 | ONEBench to Test Them All: Sample-Level Benchmarking Over Open-Ended Capabilities | 提出ONEBench：一个用于评估基础模型开放式能力的可扩展样本级基准测试框架 | foundation model | ||
| 4 | I Don't Know: Explicit Modeling of Uncertainty with an [IDK] Token | 提出基于[IDK] Token的校准方法，显式建模语言模型的不确定性，抑制幻觉。 | large language model |
🔬 支柱二：RL算法与架构 (RL & Architecture) (3 篇)
| # | 题目 | 一句话要点 | 标签 | 🔗 | ⭐ |
|---|---|---|---|---|---|
| 5 | Bounded Exploration with World Model Uncertainty in Soft Actor-Critic Reinforcement Learning Algorithm | 提出有界探索方法，提升Soft Actor-Critic算法在强化学习中的探索效率与收敛速度 | reinforcement learning deep reinforcement learning DRL | ||
| 6 | PowerMamba: A Deep State Space Model and Comprehensive Benchmark for Time Series Prediction in Electric Power Systems | PowerMamba：电力系统时间序列预测的深度状态空间模型与综合基准 | Mamba state space model | ||
| 7 | Understanding Factual Recall in Transformers via Associative Memories | 通过联想记忆理解Transformer中的事实性知识回忆能力 | linear attention large language model |