Profiles2020-2026ORCID 0000-0002-9076-6565
Zhaochun Ren
Leiden University
66Papers
26Last author
125Unique co-authors
2First author
0Solo
First and last author come from byline position, which some venues assign alphabetically.
Recent papers66
- Disentangling Knowledge Representations for Large Language Model EditingAuthor 5 of 7ICLR 2026 · 6 citations
- ZeroGR: A Generalizable and Scalable Framework for Zero-Shot Generative RetrievalAuthor 7 of 8ICLR 2026 · 6 citations
- Reinforced Efficient Reasoning via Semantically Diverse ExplorationAuthor 2 of 12ACL 2026 · 5 citations
- Differentiable Semantic ID for Generative RecommendationAuthor 7 of 7SIGIR 2026
- ReportLogic: Evaluating Logical Quality in Deep Research ReportsAuthor 7 of 7ACL 2026
- Social Welfare Function Leaderboard: On the Emergence of LLM Agents as the Welfare DictatorAuthor 16 of 17ACL Findings 2026
- Tool Learning in the Wild: Empowering Language Models as Automatic Tool AgentsAuthor 9 of 9WWW 2025 · 59 citations
- A Token is Worth over 1, 000 Tokens: Efficient Knowledge Distillation through Low-Rank CloneAuthor 5 of 6NeurIPS 2025 · 17 citations
- Iterative Self-Incentivization Empowers Large Language Models as Agentic SearchersAuthor 6 of 6NeurIPS 2025 · 15 citations
- ExcluIR: Exclusionary Neural Information RetrievalAuthor 5 of 8AAAI 2025 · 10 citations
- Retrieval Models Aren't Tool-Savvy: Benchmarking Tool Retrieval for Large Language ModelsAuthor 7 of 7ACL Findings 2025 · 7 citations
- Enhancing RAG Efficiency with Adaptive Context CompressionAuthor 3 of 3EMNLP Findings 2025 · 5 citations
- Constrained Auto-Regressive Decoding Constrains Generative RetrievalAuthor 2 of 8SIGIR 2025 · 3 citations
- Belief-Calibrated Multi-Agent Consensus Seeking for Complex NLP TasksAuthor 4 of 6NeurIPS 2025 · 2 citations
- UIPE: Enhancing LLM Unlearning by Removing Knowledge Related to Forgetting TargetsAuthor 4 of 6EMNLP Findings 2025 · 1 citation
- Bridging the Capability Gap: Joint Alignment Tuning for Harmonizing LLM-based Multi-Agent SystemsAuthor 7 of 8EMNLP Findings 2025
- Improving Sequential Recommenders through Counterfactual Augmentation of System ExposureAuthor 2 of 10SIGIR 2025
- MACPO: Weak-to-Strong Alignment via Multi-Agent Contrastive Preference OptimizationAuthor 7 of 7ICLR 2025
- Offline Trajectory Optimization for Offline Reinforcement LearningAuthor 2 of 9KDD 2025
- OmniKV: Dynamic Context Selection for Efficient Long-Context LLMsAuthor 7 of 9ICLR 2025
- Task Knowledge Injection via Interpolations and Reinstatement for Large Language Model GeneralizationAuthor 6 of 7ACL Findings 2025
- Confucius: Iterative Tool Learning from Introspection Feedback by Easy-to-Difficult CurriculumAuthor 9 of 9AAAI 2024 · 84 citations
- Disentangling ID and Modality Effects for Session-based RecommendationAuthor 3 of 6SIGIR 2024 · 32 citations
- Generative News RecommendationAuthor 5 of 7WWW 2024 · 24 citations
- Generative Retrieval as Multi-Vector Dense RetrievalAuthor 6 of 8SIGIR 2024 · 14 citations
- Learning to Use Tools via Cooperative and Interactive AgentsAuthor 10 of 10EMNLP Findings 2024 · 14 citations
- MEFT: Memory-Efficient Fine-Tuning through Sparse AdapterAuthor 7 of 7ACL 2024 · 4 citations
- Self-Supervised Position Debiasing for Large Language ModelsAuthor 4 of 6ACL Findings 2024 · 4 citations
- CAUSE: Counterfactual Assessment of User Satisfaction Estimation in Task-Oriented Dialogue SystemsAuthor 2 of 6ACL Findings 2024 · 3 citations
- KnowTuning: Knowledge-aware Fine-tuning for Large Language ModelsAuthor 9 of 9EMNLP 2024 · 3 citations
Showing the 30 most recent indexed papers.
