10 papers
Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution
Pengcheng Huang, Zhenghao Liu, Shixin Ren +5
Edge-cloud collaboration combines the lower inference overhead and greater data locality of edge-side execution with the stronger capabilities of cloud-hosted models. However, as L…
SPARK: Adaptive Parametric Knowledge Participation for Faithful Retrieval-Augmented Generation
Ruochang Li, Pengcheng Huang, Zhenghao Liu +5
Retrieval-augmented generation (RAG) enhances the faithfulness of large language models (LLMs) by incorporating external knowledge into the generation process. However, conflicts b…
MemoryCard: Topic-Aware Multi-Modal Clue Compression for Long-Video Question Answering
Qing Yang, Pengcheng Huang, Xinze Li +6
Long-video question answering remains challenging for Vision-Language Models (VLMs), as answer-relevant evidence is often sparse, transient, and temporally dispersed across lengthy…
Teaching LLMs to Learn Tool Trialing and Execution through Environment Interaction
Xingjie Gao, Pengcheng Huang, Zhenghao Liu +6
Equipping Large Language Models (LLMs) with external tools enables them to solve complex real-world problems. However, the robustness of existing methods remains a critical challen…
Revealing the Attention Floating Mechanism in Masked Diffusion Models
Xin Dai, Pengcheng Huang, Zhenghao Liu +6
Masked diffusion models (MDMs), which leverage bidirectional attention and a denoising process, are narrowing the performance gap with autoregressive models (ARMs). However, their…
Empirical Analysis of Decoding Biases in Masked Diffusion Models
Pengcheng Huang, Tianming Liu, Zhenghao Liu +5
Masked Diffusion Models (MDMs) have recently emerged as a promising non-autoregressive paradigm for sequence generation. However, their performance is highly sensitive to the choic…
Enhancing Knowledge Graph Completion with GNN Distillation and Probabilistic Interaction Modeling
Lingzhi Wang, Pengcheng Huang, Haotian Li +6
Knowledge graphs (KGs) serve as fundamental structures for organizing interconnected data across diverse domains. However, most KGs remain incomplete, limiting their effectiveness…
ClueAnchor: Clue-Anchored Knowledge Reasoning Exploration and Optimization for Retrieval-Augmented Generation
Hao Chen, Yukun Yan, Sen Mei +9
Retrieval-Augmented Generation (RAG) augments Large Language Models (LLMs) with external knowledge to improve factuality. However, existing RAG systems frequently underutilize the…
ExpandR: Teaching Dense Retrievers Beyond Queries with LLM Guidance
Sijia Yao, Pengcheng Huang, Zhenghao Liu +4
Large language models (LLMs) have demonstrated significant potential in enhancing dense retrieval through query augmentation. However, most existing methods treat the LLM and the r…
ParamMute: Suppressing Knowledge-Critical FFNs for Faithful Retrieval-Augmented Generation
Pengcheng Huang, Zhenghao Liu, Yukun Yan +8
Large language models (LLMs) integrated with retrieval-augmented generation (RAG) have improved factuality by grounding outputs in external evidence. However, they remain susceptib…