Wei Hu

Venues

Frequent coauthors

Papers

1. How Do Answer Tokens Read Reasoning Traces? Self-Reading Patterns in Thinking LLMs for Quantitative Reasoning
   ACL 2026 ·

   Haoyang Chen

   DBLP profile ↗ORCID search ↗
2. Skill-Aware Data Selection and Fine-Tuning for Data-Efficient Reasoning Distillation
   ACL 2026 ·

   Lechen Zhang

   DBLP profile ↗ORCID search ↗
3. To Diff or Not to Diff? Structure-Aware and Adaptive Output Formats for Efficient LLM-based Code Editing
   ACL 2026 ·

   Wei Cheng

   DBLP profile ↗ORCID search ↗
4. Benign Overfitting in Single-Head Attention
   NeurIPS 2025 ·

   Roey Magen

   DBLP profile ↗ORCID search ↗
5. ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents
   ACL 2025 ·

   Zhigen Li

   DBLP profile ↗ORCID search ↗
6. HyperGCT: A Dynamic Hyper-GNN-Learned Geometric Constraint for 3D Registration
   ICCV 2025 ·

   Xiyu Zhang

   DBLP profile ↗ORCID search ↗
7. Let Me Grok for You: Accelerating Grokking via Embedding Transfer from a Weaker Model
   ICLR 2025 ·

   Zhiwei Xu

   DBLP profile ↗ORCID search ↗
8. Mixture of LoRA Experts for Continual Information Extraction with LLMs
   EMNLP 2025 ·

   Zitao Wang

   DBLP profile ↗ORCID search ↗
9. Swing-by Dynamics in Concept Learning and Compositional Generalization
   ICLR 2025 ·

   Yongyi Yang

   DBLP profile ↗ORCID search ↗
10. What Happens During the Loss Plateau? Understanding Abrupt Learning in Transformers
    NeurIPS 2025 ·

    Pulkit Gopalani

    DBLP profile ↗ORCID search ↗
11. A Multi-Node Multi-GPU Distributed GNN Training Framework for Large-Scale Online Advertising
    CIKM 2024 ·

    Xuewu Jiao

    DBLP profile ↗ORCID search ↗
12. Abrupt Learning in Transformers: A Case Study on Matrix Completion
    NeurIPS 2024 ·

    Pulkit Gopalani

    DBLP profile ↗ORCID search ↗
13. Benign Overfitting and Grokking in ReLU Networks for XOR Cluster Data
    ICLR 2024 ·

    Zhiwei Xu

    DBLP profile ↗ORCID search ↗
14. DFlow: A Generative Model Combining Denoising AutoEncoder and Normalizing Flow for High Fidelity Waveform Generation
    ICML 2024 ·

    Chenfeng Miao

    DBLP profile ↗ORCID search ↗
15. DHGCN: Dynamic Hop Graph Convolution Network for Self-Supervised Point Cloud Learning
    AAAI 2024 ·

    Jincen Jiang

    DBLP profile ↗ORCID search ↗
16. E-Paraformer: A Faster and Better Parallel Transformer for Non-autoregressive End-to-End Mandarin Speech Recognition
    InterSpeech 2024 ·

    Kun Zou

    DBLP profile ↗ORCID search ↗
17. Geospatial Topological Relation Extraction from Text with Knowledge Augmentation
    SDM 2024 · Wei Hu
18. How Do Transformers Learn In-Context Beyond Simple Functions? A Case Study on Learning with Representations
    ICLR 2024 ·

    Tianyu Guo

    DBLP profile ↗ORCID search ↗
19. Improving Multilingual Text-to-Speech with Mixture-of-Language-Experts and Accent Disentanglement
    InterSpeech 2024 ·

    Jing Wu

    DBLP profile ↗ORCID search ↗
20. Multi-frequency Attention Approach for Enhanced Ultrasound Image Segmentation
    MICCAI 2024 ·

    Zicheng Hu

    DBLP profile ↗ORCID search ↗
21. Near-Interpolators: Rapid Norm Growth and the Trade-Off between Interpolation and Generalization
    AISTATS 2024 ·

    Yutong Wang

    DBLP profile ↗ORCID search ↗
22. Understanding Surprising Generalization Phenomena in Deep Learning
    AAAI 2024 · Wei Hu