Lune

Profiles2020-2026

Juncheng Li

Zhejiang University

41Papers
2Last author
84Unique co-authors
6First author
0Solo

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

Recent papers41

  1. Towards Physically Executable 3D Gaussian for Embodied NavigationAuthor 11 of 11ICLR 2026 · 22 citations
  2. WiseEdit: Benchmarking Cognition- and Creativity-Informed Image EditingAuthor 8 of 9CVPR 2026 · 9 citations
  3. MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language ModelsAuthor 7 of 10ACL 2026 · 2 citations
  4. Evolving Generalist Virtual Agents with Generative and Associative MemoryAuthor 9 of 10AAAI 2026 · 1 citation
  5. DeepAlign: Mitigating Modality Conflict through Modality-Specific AlignmentAuthor 4 of 6CVPR 2026
  6. Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware ExplorationAuthor 8 of 9CVPR 2026
  7. NeurVLA: Unleashing Failure-Handling Capability of Vision-Language-Action Models via Neural-Symbolic ReasoningAuthor 3 of 4ICML 2026
  8. SCOPE: Evolving Symbolic World for Planning in Open-Ended EnvironmentsAuthor 8 of 10ICML 2026
  9. Towards Meta-Cognitive Knowledge Editing for Multimodal LLMsAuthor 5 of 10WWW 2026
  10. Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement LearningAuthor 5 of 12NeurIPS 2025 · 11 citations
  11. TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and CompetitionAuthor 9 of 12ACL 2025 · 10 citations
  12. EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction EvolutionAuthor 3 of 7NeurIPS 2025 · 2 citations
  13. Robust Modality-Incomplete Anomaly Detection: A Modality-Instructive Framework with BenchmarkAuthor 3 of 10ACM MM 2025 · 1 citation
  14. The Best of Both Worlds: Integrating Language Models and Diffusion Models for Video GenerationAuthor 6 of 7ICCV 2025 · 1 citation
  15. Boosting Virtual Agent Learning and Reasoning: A Step-Wise, Multi-Dimensional, and Generalist Reward Model with BenchmarkAuthor 10 of 10ICML 2025
  16. Generative Multimodal Pretraining with Discrete Diffusion Timestep TokensAuthor 7 of 9CVPR 2025
  17. Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual SceneAuthor 5 of 7CVPR 2025
  18. SILMM: Self-Improving Large Multimodal Models for Compositional Text-to-Image GenerationAuthor 5 of 7CVPR 2025
  19. What Limits Virtual Agent Application? OmniBench: A Scalable Multi-Dimensional Benchmark for Essential Virtual Agent CapabilitiesAuthor 11 of 13ICML 2025
  20. Momentor: Advancing Video Large Language Model with Fine-Grained Temporal ReasoningAuthor 2 of 8ICML 2024 · 121 citations
  21. Auto-Encoding Morph-Tokens for Multimodal LLMAuthor 3 of 9ICML 2024 · 36 citations
  22. HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction DataAuthor 2 of 9CVPR 2024 · 29 citations
  23. Unified Generative and Discriminative Training for Multi-modal Large Language ModelsAuthor 2 of 10NeurIPS 2024 · 19 citations
  24. Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain TransferAuthor 5 of 8CVPR 2024 · 17 citations
  25. I3: Intent-Introspective Retrieval Conditioned on InstructionsAuthor 2 of 10SIGIR 2024 · 7 citations
  26. Fact : Teaching MLLMs with Faithful, Concise and Transferable RationalesAuthor 7 of 10ACM MM 2024 · 2 citations
  27. De-fine: Decomposing and Refining Visual Programs with Auto-FeedbackAuthor 2 of 10ACM MM 2024 · 1 citation
  28. DIEM: Decomposition-Integration Enhancing Multimodal InsightsAuthor 4 of 7CVPR 2024
  29. Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open WorldAuthor 2 of 6ICCV 2023 · 51 citations
  30. Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language ModelsAuthor 1 of 10ICCV 2023 · 34 citations

Showing the 30 most recent indexed papers.

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