PPaperPicks

Wei Huang

RIKEN Center for Advanced Intelligence Projec, Tokyo, Japan

27 papers at tracked venues · 26 at CORE A* · active 2024–2026

DBLP profile ↗ORCID 0000-0001-5583-1774 ↗Homepage ↗

Venues

NeurIPS ×11ICML ×6ICLR ×4AAAI ×2CVPR ×2AISTATS ×1SIGKDD ×1

Frequent coauthors

Andi Han
DBLP profile ↗ORCID search ↗
×3
Dake Bu
DBLP profile ↗ORCID search ↗
×3
Yilan Chen
DBLP profile ↗ORCID search ↗
×2
Bikang Pan
DBLP profile ↗ORCID search ↗
×2
Chenyu Zheng
DBLP profile ↗ORCID search ↗
×2
Jiarui Jiang
DBLP profile ↗ORCID search ↗
×2
Tongcheng Zhang
DBLP profile ↗ORCID search ↗
×1
Yue Wang
DBLP profile ↗ORCID search ↗
×1
Bingrui Li
DBLP profile ↗ORCID search ↗
×1
Xin Zheng
DBLP profile ↗ORCID search ↗
×1
Hongyi Wang
DBLP profile ↗ORCID search ↗
×1
Hao Wu
DBLP profile ↗ORCID search ↗
×1

Papers

  1. On the Learning Dynamics of Two-layer Linear Networks with Label Noise SGD
    AAAI 2026 ·
    Tongcheng Zhang
    DBLP profile ↗ORCID search ↗
  2. GRU: Mitigating the Trade-off between Unlearning and Retention for LLMs
    ICML 2025 ·
    Yue Wang
    DBLP profile ↗ORCID search ↗
  3. Generalization Bound of Gradient Flow through Training Trajectory and Data-dependent Kernel
    NeurIPS 2025 ·
    Yilan Chen
    DBLP profile ↗ORCID search ↗
  4. How Does Label Noise Gradient Descent Improve Generalization in the Low SNR Regime?
    NeurIPS 2025 · Wei Huang
  5. NLPrompt: Noise-Label Prompt Learning for Vision-Language Models
    CVPR 2025 ·
    Bikang Pan
    DBLP profile ↗ORCID search ↗
  6. On the Feature Learning in Diffusion Models
    ICLR 2025 ·
    Andi Han
    DBLP profile ↗ORCID search ↗
  7. On the Optimization and Generalization of Two-layer Transformers with Sign Gradient Descent
    ICLR 2025 ·
    Bingrui Li
    DBLP profile ↗ORCID search ↗
  8. On the Role of Label Noise in the Feature Learning Process
    ICML 2025 ·
    Andi Han
    DBLP profile ↗ORCID search ↗
  9. Provable In-Context Vector Arithmetic via Retrieving Task Concepts
    ICML 2025 ·
    Dake Bu
    DBLP profile ↗ORCID search ↗
  10. Quantifying the Optimization and Generalization Advantages of Graph Neural Networks Over Multilayer Perceptrons
    AISTATS 2025 · Wei Huang
  11. Scaling Diffusion Transformers Efficiently via μP
    NeurIPS 2025 ·
    Chenyu Zheng
    DBLP profile ↗ORCID search ↗
  12. Test-Time Graph Neural Dataset Search With Generative Projection
    ICML 2025 ·
    Xin Zheng
    DBLP profile ↗ORCID search ↗
  13. Trained Mamba Emulates Online Gradient Descent in In-Context Linear Regression
    NeurIPS 2025 ·
    Jiarui Jiang
    DBLP profile ↗ORCID search ↗
  14. Understanding the Forgetting of (Replay-based) Continual Learning via Feature Learning: Angle Matters
    ICML 2025 ·
    Hongyi Wang
    DBLP profile ↗ORCID search ↗
  15. Earthfarsser: Versatile Spatio-Temporal Dynamical Systems Modeling in One Model
    AAAI 2024 ·
    Hao Wu
    DBLP profile ↗ORCID search ↗
  16. Federated Learning from Vision-Language Foundation Models: Theoretical Analysis and Method
    NeurIPS 2024 ·
    Bikang Pan
    DBLP profile ↗ORCID search ↗
  17. Global and Local Prompts Cooperation via Optimal Transport for Federated Learning
    CVPR 2024 ·
    Hongxia Li
    DBLP profile ↗ORCID search ↗
  18. Graph Lottery Ticket Automated
    ICLR 2024 ·
    Guibin Zhang
    DBLP profile ↗ORCID search ↗
  19. On Mesa-Optimization in Autoregressively Trained Transformers: Emergence and Capability
    NeurIPS 2024 ·
    Chenyu Zheng
    DBLP profile ↗ORCID search ↗
  20. On the Comparison between Multi-modal and Single-modal Contrastive Learning
    NeurIPS 2024 · Wei Huang
  21. Provable and Efficient Dataset Distillation for Kernel Ridge Regression
    NeurIPS 2024 ·
    Yilan Chen
    DBLP profile ↗ORCID search ↗
  22. Provably Neural Active Learning Succeeds via Prioritizing Perplexing Samples
    ICML 2024 ·
    Dake Bu
    DBLP profile ↗ORCID search ↗
  23. Provably Transformers Harness Multi-Concept Word Semantics for Efficient In-Context Learning
    NeurIPS 2024 ·
    Dake Bu
    DBLP profile ↗ORCID search ↗
  24. SLTrain: a sparse plus low rank approach for parameter and memory efficient pretraining
    NeurIPS 2024 ·
    Andi Han
    DBLP profile ↗ORCID search ↗
  25. The Heterophilic Snowflake Hypothesis: Training and Empowering GNNs for Heterophilic Graphs
    SIGKDD 2024 ·
    Kun Wang
    DBLP profile ↗ORCID search ↗
  26. Understanding Convergence and Generalization in Federated Learning through Feature Learning Theory
    ICLR 2024 · Wei Huang
  27. Unveil Benign Overfitting for Transformer in Vision: Training Dynamics, Convergence, and Generalization
    NeurIPS 2024 ·
    Jiarui Jiang
    DBLP profile ↗ORCID search ↗