Lune

学者档案2020-2026

Siliang Tang

Zhejiang University

54论文数
16末位作者
124合作者人数
0一作
0独著

一作与末位作者按论文署名顺序统计,部分顶会采用姓氏字母顺序署名。

近期论文54

  1. WiseEdit: Benchmarking Cognition- and Creativity-Informed Image Editing第 9 位,共 9 位作者CVPR 2026 · 9 次引用
  2. MoA: Heterogeneous Mixture of Adapters for Parameter-Efficient Fine-Tuning of Large Language Models第 9 位,共 10 位作者ACL 2026 · 2 次引用
  3. AHEAD: Attention Head Energy-Aware Dynamics for Hallucination Mitigation in MLLMs第 3 位,共 4 位作者ACL Findings 2026
  4. Benchmarking and Improving Fine-Grained Text-to-Image Alignment via Paired Reinforcement Learning第 11 位,共 11 位作者ICML 2026
  5. CoMoL: Efficient Mixture of LoRA Experts via Dynamic Core Space Merging第 11 位,共 11 位作者ACL Findings 2026
  6. Learning to Adapt: Self-Improving Web Agent via Cognitive-Aware Exploration第 9 位,共 9 位作者CVPR 2026
  7. Towards Meta-Cognitive Knowledge Editing for Multimodal LLMs第 8 位,共 10 位作者WWW 2026
  8. GraphCLIP: Enhancing Transferability in Graph Foundation Models for Text-Attributed Graphs第 8 位,共 8 位作者WWW 2025 · 54 次引用
  9. Janus-Pro-R1: Advancing Collaborative Visual Comprehension and Generation via Reinforcement Learning第 8 位,共 12 位作者NeurIPS 2025 · 11 次引用
  10. TeamLoRA: Boosting Low-Rank Adaptation with Expert Collaboration and Competition第 11 位,共 12 位作者ACL 2025 · 10 次引用
  11. EvolvedGRPO: Unlocking Reasoning in LVLMs via Progressive Instruction Evolution第 6 位,共 7 位作者NeurIPS 2025 · 2 次引用
  12. Meta-Reflection: A Feedback-Free Reflection Learning Framework第 9 位,共 10 位作者ACL 2025 · 2 次引用
  13. ChatMap: Mining Human Thought Processes for Customer Service Chatbots via Multi-Agent Collaboration第 9 位,共 9 位作者ACL Findings 2025 · 1 次引用
  14. Robust Modality-Incomplete Anomaly Detection: A Modality-Instructive Framework with Benchmark第 7 位,共 10 位作者ACM MM 2025 · 1 次引用
  15. Generative Multimodal Pretraining with Discrete Diffusion Timestep Tokens第 8 位,共 9 位作者CVPR 2025
  16. GraphControl: Adding Conditional Control to Universal Graph Pre-trained Models for Graph Domain Transfer Learning第 5 位,共 6 位作者WWW 2024 · 43 次引用
  17. Data Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance第 6 位,共 6 位作者AAAI 2024 · 32 次引用
  18. HalluciDoctor: Mitigating Hallucinatory Toxicity in Visual Instruction Data第 7 位,共 9 位作者CVPR 2024 · 29 次引用
  19. MARIO: Model Agnostic Recipe for Improving OOD Generalization of Graph Contrastive Learning第 4 位,共 4 位作者WWW 2024 · 18 次引用
  20. Revisiting the Domain Shift and Sample Uncertainty in Multi-source Active Domain Transfer第 7 位,共 8 位作者CVPR 2024 · 17 次引用
  21. I3: Intent-Introspective Retrieval Conditioned on Instructions第 10 位,共 10 位作者SIGIR 2024 · 7 次引用
  22. Bridging Local Details and Global Context in Text-Attributed Graphs第 6 位,共 6 位作者EMNLP 2024 · 5 次引用
  23. Fact : Teaching MLLMs with Faithful, Concise and Transferable Rationales第 8 位,共 10 位作者ACM MM 2024 · 2 次引用
  24. De-fine: Decomposing and Refining Visual Programs with Auto-Feedback第 9 位,共 10 位作者ACM MM 2024 · 1 次引用
  25. DIEM: Decomposition-Integration Enhancing Multimodal Insights第 7 位,共 7 位作者CVPR 2024
  26. T2S-GPT: Dynamic Vector Quantization for Autoregressive Sign Language Production from Text第 4 位,共 5 位作者ACL 2024
  27. Visually-Prompted Language Model for Fine-Grained Scene Graph Generation in an Open World第 4 位,共 6 位作者ICCV 2023 · 51 次引用
  28. Continual Vision-Language Representation Learning with Off-Diagonal Information第 3 位,共 5 位作者ICML 2023 · 40 次引用
  29. Gradient-Regulated Meta-Prompt Learning for Generalizable Vision-Language Models第 4 位,共 10 位作者ICCV 2023 · 34 次引用
  30. Learning in Imperfect Environment: Multi-Label Classification with Long-Tailed Distribution and Partial Labels第 5 位,共 6 位作者ICCV 2023 · 28 次引用

展示最近收录的 30 篇论文。

黄昏的海面,两侧是细线勾勒的悬崖