activity
20242026
collaborators

8 papers

cs.CV2026

ReLoop-UME: Recurrent Depth with Learnable Retrieval Registers for Universal Multimodal Embedding

Shijie Wang, Xiangzhao Hao, Yueti Li +3

Universal multimodal embedding (UME) maps heterogeneous multimodal inputs into a shared embedding space. Existing UME models either form embeddings through single forward encoding…

cs.CV2026

TRACE: Task-Adaptive Reasoning and Representation Learning for Universal Multimodal Retrieval

Xiangzhao Hao, Shijie Wang, Tianyu Yang +3

Universal Multimodal Retrieval requires unified embedding models capable of interpreting diverse user intents, ranging from simple keywords to complex compositional instructions. W…

cs.LG2026

R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training

Gengsheng Li, Jinghan He, Shijie Wang +7

Self-play bootstraps LLM reasoning through an iterative Challenger-Solver loop: the Challenger is trained to generate questions that target the Solver's capabilities, and the Solve…

cs.AI2026

JADE: Bridging the Strategic-Operational Gap in Dynamic Agentic RAG

Yiqun Chen, Erhan Zhang, Tianyi Hu +8

The evolution of Retrieval-Augmented Generation (RAG) has shifted from static retrieval pipelines to dynamic, agentic workflows where a central planner orchestrates multi-turn reas…

cs.CL2025

InvestAlign: Overcoming Data Scarcity in Aligning Large Language Models with Investor Decision-Making Processes under Herd Behavior

Huisheng Wang, Zhuoshi Pan, Hangjing Zhang +3

Aligning Large Language Models (LLMs) with investor decision-making processes under herd behavior is a critical challenge in behavioral finance, which grapples with a fundamental l…

cs.AI2025

HAIBU-ReMUD: Reasoning Multimodal Ultrasound Dataset and Model Bridging to General Specific Domains

Shijie Wang, Yilun Zhang, Zeyu Lai +1

Multimodal large language models (MLLMs) have shown great potential in general domains but perform poorly in some specific domains due to a lack of domain-specific data, such as im…