| 1 |
TimeBill: Time-Budgeted Inference for Large Language Models |
TimeBill:面向大语言模型的时间预算推理框架,提升任务完成率。 |
large language model |
|
|
| 2 |
Knowledge Reasoning of Large Language Models Integrating Graph-Structured Information for Pest and Disease Control in Tobacco |
提出GraphRAG框架,融合图结构信息增强大型语言模型在烟草病虫害防治中的知识推理能力 |
large language model |
|
|
| 3 |
CricBench: A Multilingual Benchmark for Evaluating LLMs in Cricket Analytics |
CricBench:一个用于评估LLM在板球分析中性能的多语言基准测试 |
large language model |
|
|
| 4 |
Bridging the Copyright Gap: Do Large Vision-Language Models Recognize and Respect Copyrighted Content? |
评估并提升大视觉语言模型对版权内容的识别与尊重能力 |
multimodal |
|
|
| 5 |
Context as a Tool: Context Management for Long-Horizon SWE-Agents |
提出CAT框架,通过可调用工具管理上下文,提升长程软件工程Agent性能。 |
large language model |
|
|
| 6 |
Broken Words, Broken Performance: Effect of Tokenization on Performance of LLMs |
研究表明LLM分词方式影响性能,提出惩罚函数量化分词质量 |
large language model |
|
|
| 7 |
Method Decoration (DeMe): A Framework for LLM-Driven Adaptive Method Generation in Dynamic IoT Environments |
提出DeMe框架,利用LLM驱动的自适应方法生成,解决动态IoT环境中的任务执行问题。 |
large language model |
|
|