6 accepted papers
Time series analysis underpins scientific advances. While specialized models have advanced various time series tasks, scientific domains face unique challenges: limited samples with complex physical dynamics, missing observations, multi-resolution sampling, and requirements for physical consistency.…
Prevalent retrieval-based tool-use pipelines struggle with a dual semantic challenge: their retrievers often employ encoders that fail to capture complex semantics, while the Large Language Model (LLM) itself lacks intrinsic tool knowledge from its natural language pretraining. Generative methods of…
Text-to-image synthesis has made remarkable progress, yet accurately interpreting complex and lengthy prompts remains challenging, often resulting in semantic inconsistencies and missing details. Existing solutions, such as fine-tuning, are model-specific and require training, while prior automatic
Enhancing large language models (LLMs) with external tools has become a promising approach for solving complex tasks. As the number of available tools grows, context-based prompting methods increasingly rely on retrieval mechanisms. A common solution is to represent each tool with a unique token and
Light sensing and communication represent a vital link in the progress of biological evolution, helping organisms to respond to their environment and carry out survival activities. To simulate this process and exploit it in engineering applications, we develop a light-driven micro/nanorobotic system
The past decade has witnessed significant advances in time series modeling with deep learning. While achieving state-of-the-art results, the best-performing architectures vary highly across applications and domains. Meanwhile, for natural language processing, the Generative Pre-trained Transformer (…