10 papers
VISPATH: Visual-Intent-Guided Path Reasoning for Multimodal Knowledge Graph Question Answering
Jinke Wu, Zhengpin Li, Mengzhe Jia +2
Knowledge graph question answering (KGQA) enables models to answer natural-language questions through structured graph reasoning and has achieved substantial progress across many b…
ChronoQG: Towards a Temporally Expressive and Hop-Bounded Benchmark for Temporal Knowledge Graph Question Generation
Xuemeng Liu, Zhengpin Li, Wanpeng Tang +2
Knowledge graph question generation (KGQG) aims to generate natural-language questions from structured graph evidence. Existing KGQG benchmarks, however, are mostly built on static…
PECKER: A Precisely Efficient Critical Knowledge Erasure Recipe For Machine Unlearning in Diffusion Models
Zhiyong Ma, Zhitao Deng, Huan Tang +4
Machine unlearning (MU) has become a critical technique for GenAI models' safe and compliant operation. While existing MU methods are effective, most impose prohibitive training ti…
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
DataFlow Team, Bohan Zeng, Daili Hua +39
World models have garnered significant attention as a promising research direction in artificial intelligence, yet a clear and unified definition remains lacking. In this paper, we…
BrowseComp-: A Visual, Vertical, and Verifiable Benchmark for Multimodal Browsing Agents
Huanyao Zhang, Jiepeng Zhou, Bo Li +22
Multimodal large language models (MLLMs), equipped with increasingly advanced planning and tool-use capabilities, are evolving into autonomous agents capable of performing multimod…
Think Bright, Diffuse Nice: Enhancing T2I-ICL via Inductive-Bias Hint Instruction and Query Contrastive Decoding
Zhiyong Ma, Zhenpeng Li, Yuanjie Shi +3
Text-to-Image In-Context Learning (T2I-ICL) enables customized image synthesis via interleaved text-image examples but faces two mutually reinforcing bottlenecks, compliance failur…
Panning for Gold: Expanding Domain-Specific Knowledge Graphs with General Knowledge
Runhao Zhao, Weixin Zeng, Wentao Zhang +4
Domain-specific knowledge graphs (DKGs) are critical yet often suffer from limited coverage compared to General Knowledge Graphs (GKGs). Existing tasks to enrich DKGs rely primaril…
TIP and Polish: Text-Image-Prototype Guided Multi-Modal Generation via Commonality-Discrepancy Modeling and Refinement
Zhiyong Ma, Jiahao Chen, Qingyuan Chuai +1
Multi-modal generation struggles to ensure thematic coherence and style consistency. Semantically, existing methods suffer from cross-modal mismatch and lack explicit modeling of c…
Generating Long-form Story Using Dynamic Hierarchical Outlining with Memory-Enhancement
Qianyue Wang, Jinwu Hu, Zhengping Li +4
Long-form story generation task aims to produce coherent and sufficiently lengthy text, essential for applications such as novel writingand interactive storytelling. However, exist…
Prompt-SAW: Leveraging Relation-Aware Graphs for Textual Prompt Compression
Muhammad Asif Ali, Zhengping Li, Shu Yang +8
Large Language Models (LLMs) have shown exceptional abilities for multiple different natural language processing tasks. While prompting is a crucial tool for LLM inference, we obse…