9 papers
Refine Thought: A Test-Time Inference Method for Embedding Model Reasoning
Guangzhi Wang, Kai Li, Yinghao Jiao +1
We propose RT (Refine Thought), a method that can enhance the semantic reasoning ability of text embedding models. The method obtains the final semantic representation by running m…
TiMem: Temporal-Hierarchical Memory Consolidation for Long-Horizon Conversational Agents
Kai Li, Xuanqing Yu, Ziyi Ni +9
Long-horizon conversational agents have to manage ever-growing interaction histories that quickly exceed the finite context windows of large language models (LLMs). Existing memory…
AudioTrust: Benchmarking the Multifaceted Trustworthiness of Audio Large Language Models
Kai Li, Can Shen, Yile Liu +31
The rapid development and widespread adoption of Audio Large Language Models (ALLMs) demand rigorous evaluation of their trustworthiness. However, existing evaluation frameworks ar…
Breaking Data Efficiency Dilemma: A Federated and Augmented Learning Framework For Alzheimer's Disease Detection via Speech
Xiao Wei, Bin Wen, Yuqin Lin +5
Early diagnosis of Alzheimer's Disease (AD) is crucial for delaying its progression. While AI-based speech detection is non-invasive and cost-effective, it faces a critical data ef…
Enhancing Open-Vocabulary Object Detection through Multi-Level Fine-Grained Visual-Language Alignment
Tianyi Zhang, Antoine Simoulin, Kai Li +5
Traditional object detection systems are typically constrained to predefined categories, limiting their applicability in dynamic environments. In contrast, open-vocabulary object d…
Ostrakon-VL: Towards Domain-Expert MLLM for Food-Service and Retail Stores
Zhiyong Shen, Gongpeng Zhao, Jun Zhou +10
Multimodal Large Language Models (MLLMs) have recently achieved substantial progress in general-purpose perception and reasoning. Nevertheless, their deployment in Food-Service and…