Ke Zeng
4 papers · Latest:
Information Retrieval
Purifying Multimodal Retrieval: Fragment-Level Evidence Selection for RAG
FES-RAG purifies multimodal retrieval by selecting specific fragments, not whole documents, improving MLLM generation and reducing noise.
2604.27600
Information RetrievalFactorized Latent Reasoning for LLM-based Recommendation
This paper introduces Factorized Latent Reasoning (FLR), an LLM-based recommendation framework that disentangles user preferences into multiple factors.
2604.26760
Artificial IntelligenceV-tableR1: Process-Supervised Multimodal Table Reasoning with Critic-Guided Policy Optimization
V-tableR1 is a process-supervised RL framework for MLLMs that enables verifiable, multi-step reasoning on tables, outperforming larger models.
2604.20755
Artificial IntelligenceMeituan Merchant Business Diagnosis via Policy-Guided Dual-Process User Simulation
This paper introduces PGHS, a dual-process user simulation framework that combines LLM reasoning and ML fitting to accurately evaluate merchant strategies.
2604.15190
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.