Research
A paper is listed when one of its authors is affiliated with the lab. Data: OpenAlex.
IF-CRITIC: Towards a Fine-Grained LLM Critic for Instruction-Following EvaluationZhipu AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1CL2GEC: A Multi-Discipline Benchmark for Continual Learning in Chinese Literature Grammatical Error CorrectionZhipu AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Glyph: Scaling Context Windows via Visual-Text CompressionZhipu AI · Annual Meeting of the Association for Computational Linguistics (ACL)Jan 1Towards Transparent and Efficient Anomaly Detection in Industrial Processes through ExIFFIZhipu AI · IEEE Transactions on Industry ApplicationsJan 1Research and Development of a System Adaptation Strategy for the AUTOSAR Crypto StackZhipu AI · SAE technical papers on CD-ROM/SAE technical paper seriesDec 31, 2025Evaluating Hydro-Science and Engineering Knowledge of Large Language ModelsZhipu AI · arXiv (Cornell University)Dec 3, 2025Generalizing Graph Transformers Across Diverse Graphs and Tasks via Pre-TrainingZhipu AI · IEEE Transactions on Knowledge and Data Engineering2 citationsNov 13, 2025Dual Denoising Diffusion Model for Session-based Social RecommendationZhipu AI · ACM International Conference on Information and Knowledge Management (CIKM)2 citationsNov 7, 2025JPS: Jailbreak Multimodal Large Language Models with Collaborative Visual Perturbation and Textual SteeringZhipu AI · ACM International Conference on Multimedia (ACM MM)5 citationsOct 25, 2025LVBench: An Extreme Long Video Understanding BenchmarkZhipu AI · IEEE/CVF International Conference on Computer Vision (ICCV)31 citationsOct 19, 2025OmniCache: A Trajectory-Oriented Global Perspective on Training-Free Cache Reuse for Diffusion Transformer ModelsZhipu AI · IEEE/CVF International Conference on Computer Vision (ICCV)5 citationsOct 19, 2025VPO: Aligning Text-to-Video Generation Models with Prompt OptimizationZhipu AI · IEEE/CVF International Conference on Computer Vision (ICCV)5 citationsOct 19, 2025Concat-ID: Towards Universal Identity-Preserving Video SynthesisZhipu AI · IEEE International Conference on Computer Vision Workshops3 citationsOct 19, 2025DKGFN: Deep Knowledge Graph Fusion Network for RecommendationZhipu AI · Data Intelligence1 citationOct 1, 2025Knowledge Graph-based Recommendation via Generative Denoising and Multi-Level Contrastive LearningZhipu AI · Data IntelligenceOct 1, 2025An efficient two-stage computing method for large-scale research interest miningZhipu AI · Future Generation Computer Systems1 citationSep 6, 2025ComputerRL: Scaling End-to-End Online Reinforcement Learning for Computer Use AgentsZhipu AI · arXiv (Cornell University)Aug 19, 2025AtomR: Atomic Operator-Empowered Large Language Models for Heterogeneous Knowledge ReasoningZhipu AI · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD)2 citationsAug 3, 2025GuidedLatent: Defending VAEs against Membership Inference Attacks via Distribution-Guided PrivacyZhipu AI · International Joint Conference on Neural Networks (IJCNN)1 citationJun 30, 2025ICT: Image-Object Cross-Level Trusted Intervention for Mitigating Object Hallucination in Large Vision-Language ModelsZhipu AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings7 citationsJun 10, 2025MotionBench: Benchmarking and Improving Fine-Grained Video Motion Understanding for Vision Language ModelsZhipu AI · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings19 citationsJun 1, 2025A review on synergizing knowledge graphs and large language modelsZhipu AI · Computing13 citationsJun 1, 2025AGENTIF: Benchmarking Instruction Following of Large Language Models in Agentic ScenariosZhipu AI · arXiv (Cornell University)May 22, 2025Enhancing LLM-Based Agents via Global Planning and Hierarchical ExecutionZhipu AI · arXiv (Cornell University)Apr 23, 2025Ask, Acquire, Understand: A Multimodal Agent-based Framework for Social Abuse Detection in MemesZhipu AI · International World Wide Web Conference (WWW)5 citationsApr 22, 2025