9 citations · 9 across the 9 of their papers we have counts for
11 papers
DeferKV: Rethinking Eviction Timing for One-Shot KV Cache Compression
Zhe Wang, Jiakai Li, Yujia Sun +2
Long-context large language models (LLMs) have demonstrated strong capabilities across a wide range of tasks, but the growing KV cache introduces substantial memory and inference o…
Visual Graph Reasoning via Knowledge Compilation
Rongzheng Wang, Zhe Wang, Ke Qin +6
Visual graph reasoning requires answering graph-theoretic questions directly from graph images, where graph topology and state are conveyed visually rather than given in symbolic f…
Fixed Anchors Are Not Enough: Dynamic Retrieval and Persistent Homology for Dataset Distillation
Muquan Li, Hang Gou, Yingyi Ma +3
Decoupled dataset distillation (DD) compresses large corpora into a few synthetic images by matching a frozen teacher's statistics. However, current residual-matching pipelines rel…
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…
Toward Robust GraphRAG: Mitigating Retrieval Drift and Hallucination from Imperfect Knowledge Graphs
Yizhuo Ma, Jinchuan Xu, Tao Wen +6
Graph Retrieval-Augmented Generation (GraphRAG) has become a common approach for multi-hop reasoning by using knowledge graphs (KGs) as structured retrieval indexes. However, most…
When Safety Becomes a Vulnerability: Exploiting LLM Alignment Homogeneity for Transferable Blocking in RAG
Junchen Li, Liang Xu, Qizhi Chen +6
Retrieval-Augmented Generation (RAG) systems are vulnerable to blocking attacks, in which poisoned documents cause large language models (LLMs) to refuse benign queries. Existing a…
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…
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…
DSAS: A Universal Plug-and-Play Framework for Attention Optimization in Multi-Document Question Answering
Jiakai Li, Rongzheng Wang, Yizhuo Ma +3
While large language models (LLMs) show considerable promise across various fields, they have notable limitations in handling multi-document question answering (Multi-doc QA) tasks…
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…
GraphTool-Instruction: Revolutionizing Graph Reasoning in LLMs through Decomposed Subtask Instruction
Rongzheng Wang, Shuang Liang, Qizhi Chen +2
Large language models (LLMs) have been demonstrated to possess the capabilities to understand fundamental graph properties and address various graph reasoning tasks. Existing metho…