PPaperPicks

Hao Chen

Carnegie Mellon University, PA, USA

23 papers at tracked venues · 20 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Is Your (Reasoning) Multimodal Language Model Vulnerable Toward Distractions?
  2. Reliable Use of Lemmas via Eligibility Reasoning and Section-Aware Reinforcement Learning
  3. Understanding and Mitigating Bias Inheritance in LLM-based Data Augmentation on Downstream Tasks
  4. CAARMA: Class Augmentation with Adversarial Mixup Regularization
  5. From Pretraining to Pathology: How Noise Leads to Catastrophic Inheritance in Medical Models
  6. ImageFolder: Autoregressive Image Generation with Folded Tokens
  7. Masked Autoencoders Are Effective Tokenizers for Diffusion Models
    ICML 2025 · Hao Chen
  8. On Fairness of Unified Multimodal Large Language Model for Image Generation
  9. Rethinking the Bias of Foundation Model under Long-tailed Distribution
  10. SoftVQ-VAE: Efficient 1-Dimensional Continuous Tokenizer
    CVPR 2025 · Hao Chen
  11. Unleashing Hour-Scale Video Training for Long Video-Language Understanding
  12. A General Framework for Learning from Weak Supervision
    ICML 2024 · Hao Chen
  13. AgentReview: Exploring Peer Review Dynamics with LLM Agents
  14. CompeteAI: Understanding the Competition Dynamics of Large Language Model-based Agents
  15. Completing Visual Objects via Bridging Generation and Segmentation
  16. Conv-Adapter: Exploring Parameter Efficient Transfer Learning for ConvNets
    CVPR 2024 · Hao Chen
  17. Imprecise Label Learning: A Unified Framework for Learning with Various Imprecise Label Configurations
    NeurIPS 2024 · Hao Chen
  18. MDGNN: Multi-Relational Dynamic Graph Neural Network for Comprehensive and Dynamic Stock Investment Prediction
  19. Metric from Human: Zero-shot Monocular Metric Depth Estimation via Test-time Adaptation
  20. PandaLM: An Automatic Evaluation Benchmark for LLM Instruction Tuning Optimization
  21. R2-Bench: Benchmarking the Robustness of Referring Perception Models Under Perturbations
  22. Slight Corruption in Pre-training Data Makes Better Diffusion Models
    NeurIPS 2024 · Hao Chen
  23. Understanding and Mitigating the Label Noise in Pre-training on Downstream Tasks
    ICLR 2024 · Hao Chen