Lune

Profiles2020-2026ORCID 0000-0001-8472-7992

Xiangnan He

University of Science and Technology of China

87Papers
38Last author
132Unique co-authors
1First author
0Solo

First and last author come from byline position, which some venues assign alphabetically.

Recent papers87

  1. Reinforced Latent Reasoning for LLM-based RecommendationAuthor 6 of 7ICLR 2026 · 67 citations
  2. Think-While-Generating: On-the-Fly Reasoning for Personalized Long-Form GenerationAuthor 6 of 7ICLR 2026 · 35 citations
  3. Quantile Advantage Estimation: Stabilizing RLVR for LLM ReasoningAuthor 6 of 6ICLR 2026 · 11 citations
  4. NExT-Guard: Training-Free Streaming Safeguard without Token-Level LabelsAuthor 7 of 8ICML 2026 · 4 citations
  5. Contrastive Weak-to-Strong GeneralizationAuthor 7 of 8ICML 2026 · 2 citations
  6. DualEdit: Mitigating Safety Fallback in LLM Backdoor Editing via Affirmation-Refusal RegulationAuthor 7 of 8ICLR 2026 · 2 citations
  7. Uncertainty-aware Generative RecommendationAuthor 4 of 4KDD 2026 · 2 citations
  8. Beyond Static Best-of-N: Bayesian List-wise Alignment for LLM-based RecommendationAuthor 5 of 5SIGIR 2026 · 1 citation
  9. AJ-Bench: Benchmarking Agent-as-a-Judge for Environment-Aware EvaluationAuthor 11 of 11ACL Findings 2026
  10. Beyond Magnitude: Leveraging Direction of RLVR Updates for LLM ReasoningAuthor 11 of 13ICLR 2026
  11. Personalized Generation In Large Model Era: A SurveyAuthor 8 of 9ACL 2025 · 45 citations
  12. Agentic Feedback Loop Modeling Improves Recommendation and User SimulationAuthor 7 of 7SIGIR 2025 · 13 citations
  13. Explainable and Efficient Editing for Large Language ModelsAuthor 6 of 6WWW 2025 · 8 citations
  14. Less is More: Improving LLM Alignment via Preference Data SelectionAuthor 6 of 6NeurIPS 2025 · 4 citations
  15. RePO: Understanding Preference Learning Through ReLU-Based OptimizationAuthor 7 of 8NeurIPS 2025 · 4 citations
  16. Multi-Grained Patch Training for Efficient LLM-based RecommendationAuthor 4 of 4SIGIR 2025 · 3 citations
  17. Addressing Missing Data Issue for Diffusion-based RecommendationAuthor 7 of 7SIGIR 2025 · 2 citations
  18. AlphaEdit: Null-Space Constrained Knowledge Editing for Language ModelsAuthor 7 of 8ICLR 2025 · 1 citation
  19. Route Sparse Autoencoder to Interpret Large Language ModelsAuthor 7 of 7EMNLP 2025 · 1 citation
  20. AnyEdit: Edit Any Knowledge Encoded in Language ModelsAuthor 7 of 8ICML 2025
  21. Precise, Fast, and Low-cost Concept Erasure in Value Space: Orthogonal Complement MattersAuthor 7 of 7CVPR 2025
  22. Towards Robust Alignment of Language Models: Distributionally Robustifying Direct Preference OptimizationAuthor 9 of 9ICLR 2025
  23. Unified Parameter-Efficient Unlearning for LLMsAuthor 8 of 8ICLR 2025
  24. LLaRA: Large Language-Recommendation AssistantAuthor 4 of 4SIGIR 2024 · 120 citations
  25. β-DPO: Direct Preference Optimization with Dynamic βAuthor 8 of 8NeurIPS 2024 · 114 citations
  26. Towards 3D Molecule-Text Interpretation in Language ModelsAuthor 5 of 8ICLR 2024 · 87 citations
  27. Customizing Language Models with Instance-wise LoRA for Sequential RecommendationAuthor 7 of 7NeurIPS 2024 · 66 citations
  28. Large Language Models are Learnable Planners for Long-Term RecommendationAuthor 2 of 8SIGIR 2024 · 34 citations
  29. Boosting Few-Shot Learning via Attentive Feature RegularizationAuthor 6 of 6AAAI 2024 · 30 citations
  30. Text-to-Image Generation for Abstract ConceptsAuthor 5 of 8AAAI 2024 · 25 citations

Showing the 30 most recent indexed papers.

Dusk over the sea between two cliffs drawn in fine vertical lines