28 citations · 81 across the 35 of their papers we have counts for
37 papers
Swarm Telepathy: Prefill-Free KV-Cache Transfer Across Families
Abdulrahman Alabdulkareem, Irene Tenison, Yang Zhang +3
LLM multi-agent systems split work across agents that communicate through text. An agent summarizes its findings, another agent receives the text. This constrains communication to…
VisAudit: Evaluating Multimodal Agents for Visual Diagnosis and Repair
Shicheng Liu, Adam Kahirov, Qi Zhang +5
Multimodal agents are increasingly used for data visualization tasks but remain limited in autonomous review. Unlike humans, they may fail to recognize when a visualization is inco…
SafeDream: Safety World Model for Proactive Early Jailbreak Detection
Bo Yan, Weikai Lin, Yada Zhu +1
Multi-turn jailbreak attacks progressively erode LLM safety alignment across seemingly innocuous conversation turns, achieving success rates exceeding 90% against state-of-the-art…
MC-Search: Evaluating and Enhancing Multimodal Agentic Search with Structured Long Reasoning Chains
Xuying Ning, Dongqi Fu, Tianxin Wei +7
With the increasing demand for step-wise, cross-modal, and knowledge-grounded reasoning, multimodal large language models (MLLMs) are evolving beyond the traditional fixed retrieve…
How Much Reasoning Do Retrieval-Augmented Models Add beyond LLMs? A Benchmarking Framework for Multi-Hop Inference over Hybrid Knowledge
Junhong Lin, Bing Zhang, Song Wang +4
Large language models (LLMs) continue to struggle with knowledge-intensive questions that require up-to-date information and multi-hop reasoning. Augmenting LLMs with hybrid extern…
Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents
Yuanchen Bei, Tianxin Wei, Xuying Ning +7
Long-term memory is a critical capability for multimodal large language model (MLLM) agents, particularly in conversational settings where information accumulates and evolves over…
HeroFilter: Adaptive Spectral Graph Filter for Varying Heterophilic Relations
Shuaicheng Zhang, Haohui Wang, Junhong Lin +5
Graph heterophily, where connected nodes have different labels, has attracted significant interest recently. Most existing works adopt a simplified approach - using low-pass filter…
Temporal Reasoning with Large Language Models Augmented by Evolving Knowledge Graphs
Junhong Lin, Song Wang, Xiaojie Guo +2
Large language models (LLMs) excel at many language understanding tasks but struggle to reason over knowledge that evolves. To address this, recent work has explored augmenting LLM…
Efficient and Transferable Agentic Knowledge Graph RAG via Reinforcement Learning
Junhong Lin, Shicheng Liu, Jinyeop Song +3
Knowledge-graph retrieval-augmented generation (KG-RAG) couples large language models (LLMs) with structured, verifiable knowledge graphs (KGs) to reduce hallucination and provide…
Breaking Silos: Adaptive Model Fusion Unlocks Better Time Series Forecasting
Zhining Liu, Ze Yang, Xiao Lin +6
Time-series forecasting plays a critical role in many real-world applications. Although increasingly powerful models have been developed and achieved superior results on benchmark…
CLIMB: Class-imbalanced Learning Benchmark on Tabular Data
Zhining Liu, Zihao Li, Ze Yang +6
Class-imbalanced learning (CIL) on tabular data is important in many real-world applications where the minority class holds the critical but rare outcomes. In this paper, we presen…
ClimateBench-M: A Multi-Modal Climate Data Benchmark with a Simple Generative Method
Dongqi Fu, Yada Zhu, Zhining Liu +10
Climate science studies the structure and dynamics of Earth's climate system and seeks to understand how climate changes over time, where the data is usually stored in the format o…
RAG over Tables: Hierarchical Memory Index, Multi-Stage Retrieval, and Benchmarking
Jiaru Zou, Dongqi Fu, Sirui Chen +5
Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating them with an external knowledge base to improve the answer relevance and accuracy. In real…
Reasoning of Large Language Models over Knowledge Graphs with Super-Relations
Song Wang, Junhong Lin, Xiaojie Guo +3
While large language models (LLMs) have made significant progress in processing and reasoning over knowledge graphs, current methods suffer from a high non-retrieval rate. This lim…
PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play
Wei Fang, Yang Zhang, Kaizhi Qian +2
Large language models (LLMs) are increasingly integrated with specialized external tools, yet many tasks demand zero-shot tool usage with minimal or noisy documentation. Existing s…
Language in the Flow of Time: Time-Series-Paired Texts Weaved into a Unified Temporal Narrative
Zihao Li, Xiao Lin, Zhining Liu +8
While many advances in time series models focus exclusively on numerical data, research on multimodal time series, particularly those involving contextual textual information, rema…
Enterprise Benchmarks for Large Language Model Evaluation
Bing Zhang, Mikio Takeuchi, Ryo Kawahara +5
The advancement of large language models (LLMs) has led to a greater challenge of having a rigorous and systematic evaluation of complex tasks performed, especially in enterprise a…
When Heterophily Meets Heterogeneity: Challenges and a New Large-Scale Graph Benchmark
Junhong Lin, Xiaojie Guo, Shuaicheng Zhang +2
Graph mining has become crucial in fields such as social science, finance, and cybersecurity. Many large-scale real-world networks exhibit both heterogeneity, where multiple node a…
AIM: Attributing, Interpreting, Mitigating Data Unfairness
Zhining Liu, Ruizhong Qiu, Zhichen Zeng +3
Data collected in the real world often encapsulates historical discrimination against disadvantaged groups and individuals. Existing fair machine learning (FairML) research has pre…
Neural Active Learning Beyond Bandits
Yikun Ban, Ishika Agarwal, Ziwei Wu +4
We study both stream-based and pool-based active learning with neural network approximations. A recent line of works proposed bandit-based approaches that transformed active learni…
Adversarial Attacks on Fairness of Graph Neural Networks
Binchi Zhang, Yushun Dong, Chen Chen +3
Fairness-aware graph neural networks (GNNs) have gained a surge of attention as they can reduce the bias of predictions on any demographic group (e.g., female) in graph-based appli…
Self-Specialization: Uncovering Latent Expertise within Large Language Models
Junmo Kang, Hongyin Luo, Yada Zhu +6
Recent works have demonstrated the effectiveness of self-alignment in which a large language model is aligned to follow general instructions using instructional data generated from…
Class-Imbalanced Graph Learning without Class Rebalancing
Zhining Liu, Ruizhong Qiu, Zhichen Zeng +7
Class imbalance is prevalent in real-world node classification tasks and poses great challenges for graph learning models. Most existing studies are rooted in a class-rebalancing (…
Mastering Long-Tail Complexity on Graphs: Characterization, Learning, and Generalization
Haohui Wang, Baoyu Jing, Kaize Ding +6
In the context of long-tail classification on graphs, the vast majority of existing work primarily revolves around the development of model debiasing strategies, intending to mitig…