Lune

Profiles2020-2026

Jingbo Shang

University of California, San Diego

75Papers
47Last author
105Unique co-authors
1First author
0Solo

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

Recent papers75

  1. AutoCode: LLMs as Problem Setters for Competitive ProgrammingAuthor 21 of 21ICLR 2026 · 12 citations
  2. SceneAlign: Aligning Multimodal Reasoning to Scene Graphs in Complex Visual ScenesAuthor 8 of 8ACL 2026 · 9 citations
  3. Importance Sampling for Multi-Negative Multimodal Direct Preference OptimizationAuthor 7 of 7ICLR 2026 · 5 citations
  4. Deriving Character Logic from Storyline as Codified Decision TreesAuthor 5 of 5ACL 2026 · 3 citations
  5. Codified Finite-state Machines for Role-playingAuthor 4 of 4ICLR 2026 · 1 citation
  6. Toward Multi-Session Personalized Conversation: A Large-Scale Dataset and Hierarchical Tree Framework for Implicit ReasoningAuthor 5 of 5EMNLP 2025 · 12 citations
  7. Training Language Models to Generate Quality Code with Program Analysis FeedbackAuthor 10 of 11NeurIPS 2025 · 11 citations
  8. Codifying Character Logic in Role-PlayingAuthor 2 of 2NeurIPS 2025 · 7 citations
  9. ZeroHAR: Sensor Context Augments Zero-Shot Wearable Action RecognitionAuthor 9 of 12AAAI 2025 · 6 citations
  10. The Price of Format: Diversity Collapse in LLMsAuthor 5 of 5EMNLP Findings 2025 · 5 citations
  11. Direct Prompt Optimization with Continuous RepresentationsAuthor 3 of 3ACL 2025 · 3 citations
  12. Mitigating Visual Knowledge Forgetting in MLLM Instruction-tuning via Modality-decoupled Gradient DescentAuthor 11 of 13EMNLP Findings 2025 · 3 citations
  13. Cuckoo: An IE Free Rider Hatched by Massive Nutrition in LLM's NestAuthor 4 of 4ACL 2025 · 1 citation
  14. Can Language Models Follow Multiple Turns of Entangled Instructions?Author 14 of 15EMNLP Findings 2025
  15. CoMMIT: Coordinated Multimodal Instruction TuningAuthor 9 of 9EMNLP 2025
  16. Correlation and Navigation in the Vocabulary Key Representation Space of Language ModelsAuthor 3 of 3ICLR 2025
  17. Explainable Chain-of-Thought Reasoning: An Empirical Analysis on State-Aware Reasoning DynamicsAuthor 8 of 9EMNLP Findings 2025
  18. OCEAN: Offline Chain-of-thought Evaluation and Alignment in Large Language ModelsAuthor 11 of 13ICLR 2025
  19. ULTRABENCH: Benchmarking LLMs under Extreme Fine-grained Text GenerationAuthor 3 of 3EMNLP Findings 2025
  20. VeriLocc: End-to-End Cross-Architecture Register Allocation via LLMAuthor 4 of 6EMNLP 2025
  21. Debug like a Human: A Large Language Model Debugger via Verifying Runtime Execution Step by StepAuthor 3 of 3ACL Findings 2024 · 69 citations
  22. UniMTS: Unified Pre-training for Motion Time SeriesAuthor 7 of 7NeurIPS 2024 · 49 citations
  23. Controllable Data Augmentation for Few-Shot Text Mining with Chain-of-Thought Attribute ManipulationAuthor 3 of 3ACL Findings 2024 · 11 citations
  24. Toward Student-oriented Teacher Network Training for Knowledge DistillationAuthor 3 of 3ICLR 2024 · 10 citations
  25. TOOLVERIFIER: Generalization to New Tools via Self-VerificationAuthor 6 of 7EMNLP Findings 2024 · 6 citations
  26. Data Contamination Can Cross Language BarriersAuthor 6 of 6EMNLP 2024 · 4 citations
  27. Evaluating the Smooth Control of Attribute Intensity in Text Generation with LLMsAuthor 5 of 5ACL Findings 2024 · 4 citations
  28. Smaller Language Models are capable of selecting Instruction-Tuning Training Data for Larger Language ModelsAuthor 3 of 3ACL Findings 2024 · 4 citations
  29. Open-world Multi-label Text Classification with Extremely Weak SupervisionAuthor 6 of 6EMNLP 2024 · 3 citations
  30. Fast-ELECTRA for Efficient Pre-trainingAuthor 4 of 6ICLR 2024 · 2 citations

Showing the 30 most recent indexed papers.

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