| 1 |
Multimodal Fusion with Semi-Supervised Learning Minimizes Annotation Quantity for Modeling Videoconference Conversation Experience |
提出半监督多模态融合方法，高效建模视频会议中的负面体验时刻 |
multimodal |
|
|
| 2 |
KG-TRACES: Enhancing Large Language Models with Knowledge Graph-constrained Trajectory Reasoning and Attribution Supervision |
KG-TRACES：通过知识图谱约束的轨迹推理和归因监督增强大型语言模型 |
large language model |
✅ |
|
| 3 |
GuessBench: Sensemaking Multimodal Creativity in the Wild |
提出GuessBench基准，评估VLM在Minecraft游戏中理解人类创造力的能力。 |
multimodal |
|
|
| 4 |
Improving Automatic Evaluation of Large Language Models (LLMs) in Biomedical Relation Extraction via LLMs-as-the-Judge |
提出结构化输出和领域自适应方法，提升LLM作为评判者在生物医学关系抽取中的自动评估性能。 |
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，提升大语言模型在超长文本阅读理解中的性能 |
large language model |
✅ |
|
| 6 |
Fast or Slow? Integrating Fast Intuition and Deliberate Thinking for Enhancing Visual Question Answering |
提出FOCUS，结合快速直觉与审慎思考增强视觉问答能力 |
large language model multimodal |
|
|
| 7 |
One for All: Update Parameterized Knowledge Across Multiple Models |
提出OnceEdit，通过插件式模型实现多模型间知识更新的稳定性和效率。 |
large language model |
|
|
| 8 |
Chandomitra: Towards Generating Structured Sanskrit Poetry from Natural Language Inputs |
Chandomitra：提出一种将英语翻译为梵语诗歌的结构化生成方法，专注于Anushtubh格律。 |
large language model |
|
|
| 9 |
Understanding and Mitigating Cross-lingual Privacy Leakage via Language-specific and Universal Privacy Neurons |
提出语言特定和通用隐私神经元识别方法，缓解跨语言隐私泄露问题 |
large language model |
|
|