Xin Zhang

Supervised Fine-Tuning or Contrastive Learning? Towards Better Multimodal LLM Reranking

Process-Level Trajectory Evaluation for Environment Configuration in Software Engineering Agents

KaLM-Embedding-V2: Superior Training Techniques and Data Inspire A Versatile Embedding Model

Phased Training for LLM-powered Text Retrieval Models Beyond Data Scaling

R$^2$ec: Towards Large Recommender Models with Reasoning