KW
Kaiwen Wei
cs.AIcs.CLcs.CVcs.HCcs.LGAffective computingArtificial intelligenceArtificial IntelligenceClinical competenceClinical Competence
On Valency
published · living versionsW_zv9qtvj7·v1 · currentpublished
Structure-Aligned History Learning with Subspace-Structured Semantic IDs for Generative Recommendation
with Kejun He, Jie Zhang, Xiaomian Kang, Yuming Yang +10
1 version
Preprints & journals
18 papers in the corpus · 2023–2026Structure-Aligned History Learning with Subspace-Structured Semantic IDs for Generative Recommendation2610.25093v1 · Kaiwen Wei, Kejun He, Jie Zhang et al.2026 · 0 citationsarXivon Valency
RingMoClaw: An Experience-Inspired Multi-Agent Framework for Self-Evolving Research in Remote Sensing2609.00814v3 · Kaiyue Kang, Qixuan He, Peijin Wang et al.2026 · 0 citationsarXiv
Latent Diffusion With Topology-Preserving Conditioning for Structure-Aware Data Generation.42678870 · Lei, Qin, Chen, Ceran, Zhong, Jiang et al.2026 · 0 citationsIEEE transactions on neural networks and learning systems. 2026;PP
ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding2605.13228v1 · Xiao Liu, Nayu Liu, Junnan Zhu et al.2026 · 0 citationsarXiv
AI-driven multimodal simulation for psychiatric clinical education: conceptual framework and preliminary validation of the cognitive core.42121148 · Li, Xiao, Qiu, Haitang, Li, Xuemei et al.2026 · 0 citationsBMC medical education. 2026;26(1)
Context-Aware Learning and Pattern Decomposition for Temporal Knowledge Graph Reasoning.41289102 · Liao, Longquan, Zheng, Linjiang, Shang, Jiaxing et al.2026 · 2 citationsIEEE transactions on neural networks and learning systems. 2026;37(5):2307-2320
Do Models See in Line with Human Vision? Probing the Correspondence Between LVLM Representations and EEG Signals2603.08303v1 · Xin Xiao, Yang Lei, Haoyang Zeng et al.2026 · 0 citationsarXiv
Do Models Hear Like Us? Probing the Representational Alignment of Audio LLMs and Naturalistic EEG2601.16540v2 · Haoyun Yang, Xin Xiao, Jiang Zhong et al.2026 · 0 citationsarXiv
GeoViS: Geospatially Rewarded Visual Search for Remote Sensing Visual Grounding2512.02715v1 · Peirong Zhang, Yidan Zhang, Luxiao Xu et al.2025 · 0 citationsarXiv
CFVBench: A Comprehensive Video Benchmark for Fine-grained Multimodal Retrieval-Augmented Generation2510.09266v1 · Kaiwen Wei, Xiao Liu, Jie Zhang et al.2025 · 0 citationsarXiv
Exploring Similarity between Neural and LLM Trajectories in Language Processing2509.24307v2 · Xin Xiao, Kaiwen Wei, Jiang Zhong et al.2025 · 0 citationsarXiv
Learning to Shop Like Humans: A Review-driven Retrieval-Augmented Recommendation Framework with LLMs2509.00698v1 · Kaiwen Wei, Jinpeng Gao, Jiang Zhong et al.2025 · 0 citationsarXiv
MIRAGE: Scaling Test-Time Inference with Parallel Graph-Retrieval-Augmented Reasoning Chains2508.18260v2 · Kaiwen Wei, Rui Shan, Dongsheng Zou et al.2025 · 0 citationsarXiv
Benchmarking Multimodal RAG through a Chart-based Document Question-Answering Generation Framework2502.14864v1 · Yuming Yang, Jiang Zhong, Li Jin et al.2025 · 0 citationsarXiv
Latent Distribution Decoupling: A Probabilistic Framework for Uncertainty-Aware Multimodal Emotion Recognition2502.13954v1 · Jingwang Huang, Jiang Zhong, Qin Lei et al.2025 · 0 citationsarXiv
Multimodal Cross-Lingual Summarization for Videos: A Revisit in Knowledge Distillation Induced Triple-Stage Training Method.39172610 · Liu, Nayu, Wei, Kaiwen, Yang, Yong et al.2024 · 8 citationsIEEE transactions on pattern analysis and machine intelligence. 2024;46(12):10697-10714
Chain-of-Specificity: An Iteratively Refining Method for Eliciting Knowledge from Large Language Models2402.15526v1 · Kaiwen Wei, Jingyuan Zhang, Hongzhi Zhang et al.2024 · 0 citationsarXiv
PPN: Parallel Pointer-based Network for Key Information Extraction with Complex Layouts2307.10551v1 · Kaiwen Wei, Jie Yao, Jingyuan Zhang et al.2023 · 1 citationarXiv
Career total: 49 works. 18 are in this corpus.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.