Zhicheng Dou

AdAEM: An Adaptively and Automated Extensible Measurement of LLMs' Value Difference

Toward Effective Tool-Integrated Reasoning via Self-Evolved Preference Learning

MR$^2$-Bench: Going Beyond Matching to Reasoning in Multimodal Retrieval

Agentic Reinforced Policy Optimization

CAReDiO: Enhancing Cultural Alignment of LLM via Representativeness and Distinctiveness Guided Data Optimization

VideoExplorer: Boosting Long Video Understanding with Dynamic Temporal Grounding

Prompting to Prompt: Meta-Template Learning for Transferable Prompt Optimization

FINSIGHT: TOWARDS REAL-WORLD FINANCIAL DEEP RESEARCH

Long Context Compression with Activation Beacon

Chain-of-Retrieval Augmented Generation

WebThinker: Empowering Large Reasoning Models with Deep Research Capability

A Non-Contrastive Learning Framework for Sequential Recommendation with Preference-Preserving Profile Generation

UniGist: Towards General and Hardware-aligned Sequence-level Long Context Compression