6 papers
Mind Your Margin and Boundary: Are Your Distilled Datasets Truly Robust?
Muquan Li, Yingyi Ma, Yihong Huang +5
Dataset distillation (DD) compresses a large training set into a small synthetic set for efficient training, but most DD methods optimize only clean accuracy and leave robustness u…
Rethinking LLM-Driven Heuristic Design: Generating Efficient and Specialized Solvers via Dynamics-Aware Optimization
Rongzheng Wang, Yihong Huang, Muquan Li +6
Large Language Models (LLMs) have advanced the field of Combinatorial Optimization through automated heuristic generation. Instead of relying on manual design, this LLM-Driven Heur…
KEPo: Knowledge Evolution Poison on Graph-based Retrieval-Augmented Generation
Qizhi Chen, Chao Qi, Yihong Huang +5
Graph-based Retrieval-Augmented Generation (GraphRAG) constructs the Knowledge Graph (KG) from external databases to enhance the timeliness and accuracy of Large Language Model (LL…
Nüwa: Mending the Spatial Integrity Torn by VLM Token Pruning
Yihong Huang, Fei Ma, Yihua Shao +4
Vision token pruning has proven to be an effective acceleration technique for the efficient Vision Language Model (VLM). However, existing pruning methods demonstrate excellent per…
NeuroPath: Neurobiology-Inspired Path Tracking and Reflection for Semantically Coherent Retrieval
Junchen Li, Rongzheng Wang, Yihong Huang +3
Retrieval-augmented generation (RAG) greatly enhances large language models (LLMs) performance in knowledge-intensive tasks. However, naive RAG methods struggle with multi-hop ques…
GraphCogent: Mitigating LLMs' Working Memory Constraints via Multi-Agent Collaboration in Complex Graph Understanding
Rongzheng Wang, Shuang Liang, Qizhi Chen +6
Large language models (LLMs) show promising performance on small-scale graph reasoning tasks but fail when handling real-world graphs with complex queries. This phenomenon arises f…