Caigao Jiang
YOU?
Author Swipe
View article: Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning
Unlocking the Power of Function Vectors for Characterizing and Mitigating Catastrophic Forgetting in Continual Instruction Tuning Open
Catastrophic forgetting (CF) poses a significant challenge in machine learning, where a model forgets previously learned information upon learning new tasks. Despite the advanced capabilities of Large Language Models (LLMs), they continue …
View article: ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planning
ROMAS: A Role-Based Multi-Agent System for Database monitoring and Planning Open
In recent years, Large Language Models (LLMs) have demonstrated remarkable capabilities in data analytics when integrated with Multi-Agent Systems (MAS). However, these systems often struggle with complex tasks that involve diverse functio…
View article: Refine Large Language Model Fine-tuning via Instruction Vector
Refine Large Language Model Fine-tuning via Instruction Vector Open
Fine-tuning large language models (LLMs) can cause them to lose their general capabilities. However, the intrinsic mechanisms behind such forgetting remain unexplored. In this paper, we begin by examining this phenomenon by focusing on kno…
View article: Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models
Demonstration of DB-GPT: Next Generation Data Interaction System Empowered by Large Language Models Open
The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software. The technologies of interacting with data particularly have an important entanglement with LLMs as efficient and intuitive data i…
View article: DB-GPT: Empowering Database Interactions with Private Large Language Models
DB-GPT: Empowering Database Interactions with Private Large Language Models Open
The recent breakthroughs in large language models (LLMs) are positioned to transition many areas of software. Database technologies particularly have an important entanglement with LLMs as efficient and intuitive database interactions are …
View article: Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompt Open
Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when …
View article: Prompt-augmented Temporal Point Process for Streaming Event Sequence
Prompt-augmented Temporal Point Process for Streaming Event Sequence Open
Neural Temporal Point Processes (TPPs) are the prevalent paradigm for modeling continuous-time event sequences, such as user activities on the web and financial transactions. In real-world applications, event data is typically received in …
View article: Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference
Enhancing Asynchronous Time Series Forecasting with Contrastive Relational Inference Open
Asynchronous time series, also known as temporal event sequences, are the basis of many applications throughout different industries. Temporal point processes(TPPs) are the standard method for modeling such data. Existing TPP models have f…
View article: WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine
WeaverBird: Empowering Financial Decision-Making with Large Language Model, Knowledge Base, and Search Engine Open
We present WeaverBird, an intelligent dialogue system designed specifically for the finance domain. Our system harnesses a large language model of GPT architecture that has been tuned using extensive corpora of finance-related text. As a r…
View article: Continual Learning in Predictive Autoscaling
Continual Learning in Predictive Autoscaling Open
Predictive Autoscaling is used to forecast the workloads of servers and prepare the resources in advance to ensure service level objectives (SLOs) in dynamic cloud environments. However, in practice, its prediction task often suffers from …
View article: EasyTPP: Towards Open Benchmarking Temporal Point Processes
EasyTPP: Towards Open Benchmarking Temporal Point Processes Open
Continuous-time event sequences play a vital role in real-world domains such as healthcare, finance, online shopping, social networks, and so on. To model such data, temporal point processes (TPPs) have emerged as the most natural and comp…
View article: Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompts
Towards Anytime Fine-tuning: Continually Pre-trained Language Models with Hypernetwork Prompts Open
Continual pre-training has been urgent for adapting a pre-trained model to a multitude of domains and tasks in the fast-evolving world. In practice, a continually pre-trained model is expected to demonstrate not only greater capacity when …
View article: Learning Large-scale Universal User Representation with Sparse Mixture of Experts
Learning Large-scale Universal User Representation with Sparse Mixture of Experts Open
Learning user sequence behaviour embedding is very sophisticated and challenging due to the complicated feature interactions over time and high dimensions of user features. Recent emerging foundation models, e.g., BERT and its variants, en…
View article: Unit Ball Model for Embedding Hierarchical Structures in the Complex Hyperbolic Space
Unit Ball Model for Embedding Hierarchical Structures in the Complex Hyperbolic Space Open
Learning the representation of data with hierarchical structures in the hyperbolic space attracts increasing attention in recent years. Due to the constant negative curvature, the hyperbolic space resembles tree metrics and captures the tr…