| 1 |
Learn from Downstream and Be Yourself in Multimodal Large Language Model Fine-Tuning |
提出重要性感知权重分配策略,缓解多模态大语言模型微调中的泛化能力退化问题 |
large language model multimodal |
|
|
| 2 |
Understanding Multimodal LLMs: the Mechanistic Interpretability of Llava in Visual Question Answering |
通过机制可解释性分析,理解LLaVA在视觉问答中的工作原理 |
large language model multimodal |
✅ |
|
| 3 |
Debiasing Watermarks for Large Language Models via Maximal Coupling |
提出基于最大耦合的无偏水印方法,用于大型语言模型,在保证文本质量的同时提高可检测性。 |
large language model |
|
|
| 4 |
Multilingual Large Language Models: A Systematic Survey |
多语言大型语言模型(MLLM)的系统性综述研究 |
large language model |
✅ |
|
| 5 |
Beyond Human-Like Processing: Large Language Models Perform Equivalently on Forward and Backward Scientific Text |
大型语言模型在正向和反向科学文本上表现相当,质疑类人处理假设 |
large language model |
|
|
| 6 |
BianCang: A Traditional Chinese Medicine Large Language Model |
提出BianCang:一个面向中医领域的大语言模型,提升中医诊断和辨证能力 |
large language model |
✅ |
|
| 7 |
AddrLLM: Address Rewriting via Large Language Model on Nationwide Logistics Data |
AddrLLM:基于大规模物流数据的地址重写大语言模型框架 |
large language model |
|
|
| 8 |
SRA-MCTS: Self-driven Reasoning Augmentation with Monte Carlo Tree Search for Code Generation |
提出SRA-MCTS,通过自驱动推理增强和蒙特卡洛树搜索提升代码生成能力 |
large language model chain-of-thought |
✅ |
|
| 9 |
Capturing Sparks of Abstraction for the ARC Challenge |
利用LLM从ARC挑战代码解决方案中提取抽象逻辑,提升问题理解能力 |
large language model |
|
|
| 10 |
SEFD: Semantic-Enhanced Framework for Detecting LLM-Generated Text |
提出SEFD框架,利用语义增强检测LLM生成文本,提升复述场景下的检测精度。 |
large language model |
|
|
| 11 |
FastDraft: How to Train Your Draft |
FastDraft:通过高效预训练和对齐,为大型语言模型快速训练Draft模型。 |
large language model |
|
|
| 12 |
Analyzing Pokémon and Mario Streamers' Twitch Chat with LLM-based User Embeddings |
提出基于LLM用户嵌入的Twitch聊天分析方法,用于理解游戏主播观众类型 |
large language model |
|
|