Lune

Profiles2020-2026

Jing Li

Harbin Institute of Technology

23Papers
10Last author
20Unique co-authors
1First author
0Solo

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

Recent papers23

  1. Multi-objective Large Language Model Alignment with Hierarchical ExpertsAuthor 11 of 11ICLR 2026 · 17 citations
  2. Knowledge Fusion of Large Language Models via Modular SkillPacksAuthor 12 of 12ICLR 2026 · 9 citations
  3. Backdoors in RLVR: Jailbreak Backdoors in LLMs From Verifiable RewardAuthor 6 of 6ACL 2026 · 4 citations
  4. FP=XINT: Representing Neural Networks via Low-Bit Series Basis FunctionsAuthor 5 of 6AAAI 2026 · 4 citations
  5. Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM ReasoningAuthor 6 of 6ICLR 2026 · 3 citations
  6. Bridging Functional Correctness and Runtime Efficiency Gaps in LLM-Based Code TranslationAuthor 5 of 6ICML 2026 · 1 citation
  7. Vocabulary Hijacking in LVLMs: Unveiling Critical Attention Heads by Excluding Inert Tokens to Mitigate HallucinationAuthor 7 of 7ACL 2026 · 1 citation
  8. Language Bias in LVLMs: From In-Depth Analysis to Simple and Effective MitigationAuthor 2 of 2ICML 2026
  9. Modality-Decoupled Online Recursive EditingAuthor 4 of 4ICML 2026
  10. SuCo: Sufficiency-guided Continuous Adaptive ReasoningAuthor 7 of 8ICML 2026
  11. Team-Based Self-Play With Dual Adaptive Weighting for Fine-Tuning LLMsAuthor 6 of 6ACL 2026
  12. Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model AlignmentAuthor 4 of 4ICML 2026
  13. Knowledge Editing with Dynamic Knowledge Graphs for Multi-Hop Question AnsweringAuthor 3 of 8AAAI 2025 · 19 citations
  14. Safety Alignment via Constrained Knowledge UnlearningAuthor 3 of 10ACL 2025 · 8 citations
  15. Learning to Watermark: A Selective Watermarking Framework for Large Language Models via Multi-Objective OptimizationAuthor 7 of 7NeurIPS 2025 · 1 citation
  16. Function-to-Style Guidance of LLMs for Code TranslationAuthor 9 of 11ICML 2025
  17. MTSA: Multi-turn Safety Alignment for LLMs through Multi-round Red-teamingAuthor 2 of 7ACL 2025
  18. Neural Parameter Search for Slimmer Fine-Tuned Models and Better TransferAuthor 3 of 13ACL 2025
  19. Parameter Competition Balancing for Model MergingAuthor 3 of 11NeurIPS 2024 · 91 citations
  20. Masked Structural Growth for 2x Faster Language Model Pre-trainingAuthor 3 of 4ICLR 2024 · 30 citations
  21. GRLSTM: Trajectory Similarity Computation with Graph-Based Residual LSTMAuthor 2 of 5AAAI 2023 · 48 citations
  22. HME: A Hyperbolic Metric Embedding Approach for Next-POI RecommendationAuthor 5 of 6SIGIR 2020 · 100 citations
  23. MetaNER: Named Entity Recognition with Meta-LearningAuthor 1 of 3WWW 2020 · 56 citations
Dusk over the sea between two cliffs drawn in fine vertical lines