PPaperPicks

Kai Wang

National University of Singapore, School of Computing, Singapore

40 papers at tracked venues · 36 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0002-1154-5175 ↗Google Scholar ↗Homepage ↗

Venues

NeurIPS ×13ICLR ×6CVPR ×5ICML ×5AAAI ×3ECCV ×2ACL ×1ACM MM ×1EMNLP ×1ICCV ×1IJCAI ×1SIGKDD ×1

Frequent coauthors

Wangbo Zhao
DBLP profile ↗ORCID search ↗
×3
Ziheng Qin
DBLP profile ↗ORCID search ↗
×3
Pengfei Zhou
DBLP profile ↗ORCID search ↗
×2
Yudong Zhang
DBLP profile ↗ORCID search ↗
×2
Guibin Zhang
DBLP profile ↗ORCID search ↗
×2
Kun Wang
DBLP profile ↗ORCID search ↗
×2
Zhenghao Zhao
DBLP profile ↗ORCID search ↗
×1
Zhiyuan Liang
DBLP profile ↗ORCID search ↗
×1
Chen Zhu
DBLP profile ↗ORCID search ↗
×1
Xu Zhao Pan
DBLP profile ↗ORCID search ↗
×1
Rana Muhammad Shahroz
DBLP profile ↗ORCID search ↗
×1
Jindi Lv
DBLP profile ↗ORCID search ↗
×1

Papers

  1. MDK12-Bench: A Multi-Discipline Benchmark for Evaluating Reasoning in Multimodal Large Language Models
    AAAI 2026 ·
    Pengfei Zhou
    DBLP profile ↗ORCID search ↗
  2. A Closer Look at Time Steps is Worthy of Triple Speed-Up for Diffusion Model Training
    CVPR 2025 · Kai Wang
  3. A Stitch in Time Saves Nine: Small VLM is a Precise Guidance for Accelerating Large VLMs
    CVPR 2025 ·
    Wangbo Zhao
    DBLP profile ↗ORCID search ↗
  4. Distilling Long-tailed Datasets
    CVPR 2025 ·
    Zhenghao Zhao
    DBLP profile ↗ORCID search ↗
  5. Drag-and-Drop LLMs: Zero-Shot Prompt-to-Weights
    NeurIPS 2025 ·
    Zhiyuan Liang
    DBLP profile ↗ORCID search ↗
  6. Drawing Informative Gradients from Sources: A One-stage Transfer Learning Framework for Cross-city Spatiotemporal Forecasting
    AAAI 2025 ·
    Yudong Zhang
    DBLP profile ↗ORCID search ↗
  7. Dynamic Diffusion Transformer
    ICLR 2025 ·
    Wangbo Zhao
    DBLP profile ↗ORCID search ↗
  8. EA-Vit: Efficient Adaptation for Elastic Vision Transformer
    ICCV 2025 ·
    Chen Zhu
    DBLP profile ↗ORCID search ↗
  9. Emphasizing Discriminative Features for Dataset Distillation in Complex Scenarios
    CVPR 2025 · Kai Wang
  10. Info-Coevolution: An Efficient Framework for Data Model Coevolution
    ICML 2025 ·
    Ziheng Qin
    DBLP profile ↗ORCID search ↗
  11. MPBench: A Comprehensive Multimodal Reasoning Benchmark for Process Errors Identification
    ACL 2025 ·
    Xu Zhao Pan
    DBLP profile ↗ORCID search ↗
  12. Neural-Driven Image Editing
    NeurIPS 2025 ·
    Pengfei Zhou
    DBLP profile ↗ORCID search ↗
  13. ORAL: Prompting Your Large-Scale LoRAs via Conditional Recurrent Diffusion
    EMNLP 2025 ·
    Rana Muhammad Shahroz
    DBLP profile ↗ORCID search ↗
  14. Pruning-Robust Mamba with Asymmetric Multi-Scale Scanning Paths
    NeurIPS 2025 ·
    Jindi Lv
    DBLP profile ↗ORCID search ↗
  15. REPA Works Until It Doesn't: Early-Stopped, Holistic Alignment Supercharges Diffusion Training
    NeurIPS 2025 ·
    Ziqiao Wang
    DBLP profile ↗ORCID search ↗
  16. Real-Time Video Generation with Pyramid Attention Broadcast
    ICLR 2025 ·
    Xuanlei Zhao
    DBLP profile ↗ORCID search ↗
  17. Scaling Up Parameter Generation: A Recurrent Diffusion Approach
    NeurIPS 2025 · Kai Wang
  18. StarTrail: Concentric Ring Sequence Parallelism for Efficient Near-Infinite-Context Transformer Model Training
    NeurIPS 2025 ·
    Ziming Liu
    DBLP profile ↗ORCID search ↗
  19. Time-Frequency Disentanglement Boosted Pre-Training: A Universal Spatio-Temporal Modeling Framework
    IJCAI 2025 ·
    Yudong Zhang
    DBLP profile ↗ORCID search ↗
  20. Unsupervised Learning for Class Distribution Mismatch
    ICML 2025 ·
    Pan Du
    DBLP profile ↗ORCID search ↗
  21. X-Field: A Physically Informed Representation for 3D X-ray Reconstruction
    NeurIPS 2025 ·
    Feiran Wang
    DBLP profile ↗ORCID search ↗
  22. ATOM: Attention Mixer for Efficient Dataset Distillation
    CVPR 2024 ·
    Samir Khaki
    DBLP profile ↗ORCID search ↗
  23. Aligning Large Language Models with Representation Editing: A Control Perspective
    NeurIPS 2024 ·
    Lingkai Kong
    DBLP profile ↗ORCID search ↗
  24. Can We Evaluate Domain Adaptation Models Without Target-Domain Labels?
    ICLR 2024 ·
    Jianfei Yang
    DBLP profile ↗ORCID search ↗
  25. Causal Deciphering and Inpainting in Spatio-Temporal Dynamics via Diffusion Model
    NeurIPS 2024 ·
    Yifan Duan
    DBLP profile ↗ORCID search ↗
  26. Dataset Growth
    ECCV 2024 ·
    Ziheng Qin
    DBLP profile ↗ORCID search ↗
  27. DiM: Distilling Dataset into Generative Model
    ECCV 2024 · Kai Wang
  28. DiffAug: Enhance Unsupervised Contrastive Learning with Domain-Knowledge-Free Diffusion-based Data Augmentation
    ICML 2024 ·
    Zelin Zang
    DBLP profile ↗ORCID search ↗
  29. Dynamic Tuning Towards Parameter and Inference Efficiency for ViT Adaptation
    NeurIPS 2024 ·
    Wangbo Zhao
    DBLP profile ↗ORCID search ↗
  30. Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning
    NeurIPS 2024 ·
    Zebang Cheng
    DBLP profile ↗ORCID search ↗
  31. GDeR: Safeguarding Efficiency, Balancing, and Robustness via Prototypical Graph Pruning
    NeurIPS 2024 ·
    Guibin Zhang
    DBLP profile ↗ORCID search ↗
  32. InfoBatch: Lossless Training Speed Up by Unbiased Dynamic Data Pruning
    ICLR 2024 ·
    Ziheng Qin
    DBLP profile ↗ORCID search ↗
  33. MVPbev: Multi-view Perspective Image Generation from BEV with Test-time Controllability and Generalizability
    ACM MM 2024 ·
    Buyu Liu
    DBLP profile ↗ORCID search ↗
  34. Navigating Complexity: Toward Lossless Graph Condensation via Expanding Window Matching
    ICML 2024 ·
    Yuchen Zhang
    DBLP profile ↗ORCID search ↗
  35. NuwaDynamics: Discovering and Updating in Causal Spatio-Temporal Modeling
    ICLR 2024 ·
    Kun Wang
    DBLP profile ↗ORCID search ↗
  36. Rethinking Human Evaluation Protocol for Text-to-Video Models: Enhancing Reliability, Reproducibility, and Practicality
    NeurIPS 2024 ·
    Tianle Zhang
    DBLP profile ↗ORCID search ↗
  37. Summarizing Stream Data for Memory-Constrained Online Continual Learning
    AAAI 2024 ·
    Jianyang Gu
    DBLP profile ↗ORCID search ↗
  38. The Snowflake Hypothesis: Training and Powering GNN with One Node One Receptive Field
    SIGKDD 2024 ·
    Kun Wang
    DBLP profile ↗ORCID search ↗
  39. Towards Lossless Dataset Distillation via Difficulty-Aligned Trajectory Matching
    ICLR 2024 ·
    Ziyao Guo
    DBLP profile ↗ORCID search ↗
  40. Two Heads Are Better Than One: Boosting Graph Sparse Training via Semantic and Topological Awareness
    ICML 2024 ·
    Guibin Zhang
    DBLP profile ↗ORCID search ↗