PPaperPicks

Fan Yang

31 papers at tracked venues · 24 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Beyond Euclidean Assumptions: Geometry-Aware Adaptive Routing for Remote Sensing Segmentation
  2. Breaking the Stealth-Potency Trade-off in Clean-Image Backdoors with Generative Trigger Optimization
  3. Display Ads Contextual Relevance Modeling with LLM Labels
  4. Explain the Synth: Interpretable Evaluation of LLM Data Synthesis
  5. FilmSceneDesigner: Chaining Set Design for Procedural Film Scene Generation
  6. KnowThyself: An Agentic Assistant for LLM Interpretability
  7. UDCH: Unsupervised Dynamic Weighted Cluster-cooperative Hashing for Cross-modal Retreival
  8. Adaptive Neighbors and Uncertainty Estimation for Source-Free Unsupervised Domain Adaptation with Noisy Labels
  9. Beyond Surface-Level Patterns: An Essence-Driven Defense Framework Against Jailbreak Attacks in LLMs
  10. CLIP-Guided Backdoor Defense through Entropy-Based Poisoned Dataset Separation
  11. Contrasting Adversarial Perturbations: The Space of Harmless Perturbations
  12. EdgeInfinite: A Memory-Efficient Infinite-Context Transformer for Edge Devices
  13. FCD-Net: Frequency and Contrastive Learning-Driven Network for Document Image Shadow Removal
    ICDAR 2025 · Fan Yang
  14. In vivo cell-type and brain region classification via multimodal contrastive learning
  15. NTIRE 2025 Challenge on Day and Night Raindrop Removal for Dual-Focused Images: Methods and Results
  16. Outline and Detail: A Semantic-Driven Framework for Layered 2D Character Generation
  17. Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoning
  18. Reviving DSP for Advanced Theorem Proving in the Era of Reasoning Models
  19. SeedBench: A Multi-task Benchmark for Evaluating Large Language Models in Seed Science
  20. Self-Interpretable Reinforcement Learning via Rule Ensembles
  21. The Source Image Is the Best Attention for Infrared and Visible Image Fusion
  22. VIIS: Visible and Infrared Information Synthesis for Severe Low-Light Image Enhancement
  23. XCalBid: Robust and Efficient Real-Time Bidding Via Exploratory Pre-Training and Calibrated Q-Learning
  24. An Effective Augmented Lagrangian Method for Fine-Grained Multi-View Optimization
  25. Autoformalize Mathematical Statements by Symbolic Equivalence and Semantic Consistency
  26. EMBOSR: Embodied Spatial Reasoning for Enhanced Situated Question Answering in 3D Scenes
  27. EmoEden: Applying Generative Artificial Intelligence to Emotional Learning for Children with High-Function Autism
  28. Empowering and Assessing the Utility of Large Language Models in Crop Science
  29. MobileNetV4: Universal Models for the Mobile Ecosystem
  30. Neuro-Symbolic Data Generation for Math Reasoning
  31. Sparse Bayesian Deep Learning for Cross Domain Medical Image Reconstruction