Large language model (LLM) based agents have recently attracted much attention from the
research and industry communities. Compared with original LLMs, LLM-based agents are …

Although Large Language Models (LLMs) have demonstrated potential in processing
graphs, they struggle with comprehending graphical structure information through prompts …

We present Timer-XL, a generative Transformer for unified time series forecasting. To
uniformly predict 1D and 2D time series, we generalize next token prediction, predominantly …

Handling long input contexts remains a significant challenge for Large Language Models
(LLMs), particularly in resource-constrained environments such as mobile devices. Our work …

Despite significant advancements in large language models (LLMs), the rapid and frequent
integration of small-scale experiences, such as interactions with surrounding objects …

Prompt compression is an innovative method for efficiently condensing input prompts while
preserving essential information. To facilitate quick-start services, user-friendly interfaces …

Length extrapolation algorithms based on Rotary position embedding (RoPE) have shown
promising results in extending the context length of language models. However …

In retrieval-augmented systems, context ranking techniques are commonly employed to
reorder the retrieved contexts based on their relevance to a user query. A standard …

Building a human-like system that continuously interacts with complex environments--
whether simulated digital worlds or human society--presents several key challenges. Central …

Building effective machine learning (ML) workflows to address complex tasks is a primary
focus of the Automatic ML (AutoML) community and a critical step toward achieving artificial …