| 1 |
Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience |
提出半监督学习方法以减少视频会议对话体验建模的标注需求 |
multimodal |
|
|
| 2 |
KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision |
提出KG-TRACES以解决大语言模型推理可解释性不足问题 |
large language model |
✅ |
|
| 3 |
GuessBench: Sensemaking Multimodal Creativity in the Wild |
提出GuessBench以评估多模态创意建模能力 |
multimodal |
|
|
| 4 |
Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge |
提出LLMs作为评判者以改善生物医学关系提取的自动评估 |
large language model |
✅ |
|
| 5 |
Dynamic Chunking and Selection for Reading Comprehension of Ultra-Long Context in Large Language Models |
提出动态分块与选择方法以解决超长文本理解问题 |
large language model |
✅ |
|
| 6 |
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering |
提出FOCUS以解决视觉问答中的复杂推理问题 |
large language model multimodal |
|
|
| 7 |
One for All: Update Parameterized Knowledge Across Multiple Models |
提出OnceEdit以解决多模型知识更新问题 |
large language model |
|
|
| 8 |
From Plain Text to Poetic Form: Generating Metrically-Constrained Sanskrit Verses |
提出一种方法以生成符合韵律的梵文诗歌 |
large language model |
|
|
| 9 |
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons |
提出跨语言隐私泄露防护机制以解决LLM隐私风险问题 |
large language model |
|
|