PPaperPicks

Xiangyang Ji

69 papers at tracked venues · 55 at CORE A* · active 20242026

Venues

Frequent coauthors

Papers

  1. Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment
  2. Can Prompt Difficulty be Online Predicted for Accelerating RL Finetuning of Reasoning Models?
  3. Score-Based Model for Low-Rank Tensor Recovery
  4. Active Event-based Stereo Vision
  5. Adaptive Neighborhood-Constrained Q Learning for Offline Reinforcement Learning
  6. Almost Optimal Batch-Regret Tradeoff for Batch Linear Contextual Bandits
  7. Are High-Quality AI-Generated Images More Difficult for Models to Detect?
  8. Bridging the Gap Between Ideal and Real-World Evaluation: Benchmarking AI-Generated Image Detection in Challenging Scenarios
  9. Camera-Specific Imaging Simulation for Raw Domain Image Super Resolution
  10. Can We Achieve Efficient Diffusion without Self-Attention? Distilling Self-Attention Into Convolutions
  11. ConformalSAM: Unlocking the Potential of Foundational Segmentation Models in Semi-Supervised Semantic Segmentation with Conformal Prediction
  12. DPFlow: Adaptive Optical Flow Estimation with a Dual-Pyramid Framework
  13. Delving into Cascaded Instability: A Lipschitz Continuity View on Image Restoration and Object Detection Synergy
  14. DyGS-SLAM: Real-Time Accurate Localization and Gaussian Reconstruction for Dynamic Scenes
  15. Enhanced Event-Based Dense Stereo via Cross-Sensor Knowledge Distillation
  16. EventGPT: Event Stream Understanding with Multimodal Large Language Models
  17. Fast and Robust: Task Sampling with Posterior and Diversity Synergies for Adaptive Decision-Makers in Randomized Environments
  18. FlyLoRA: Boosting Task Decoupling and Parameter Efficiency via Implicit Rank-Wise Mixture-of-Experts
  19. GIVEPose: Gradual Intra-class Variation Elimination for RGB-based Category-Level Object Pose Estimation
  20. Joint Asymmetric Loss for Learning with Noisy Labels
  21. Know2Vec: A Black-Box Proxy for Neural Network Retrieval
  22. Latent Reward: LLM-Empowered Credit Assignment in Episodic Reinforcement Learning
  23. Lessons and Winning Solutions in Industrial Object Detection and Pose Estimation from the 2025 Bin-Picking Perception Challenge
  24. Linguistics-aware Masked Image Modeling for Self-supervised Scene Text Recognition
  25. NTIRE 2025 Challenge on Event-Based Image Deblurring: Methods and Results
  26. Open-Vocabulary Functional 3D Scene Graphs for Real-World Indoor Spaces
  27. PatchVSR: Breaking Video Diffusion Resolution Limits with Patch-wise Video Super-Resolution
  28. PlugMark: A Plug-In Zero-Watermarking Framework for Diffusion Models
  29. Real-Time Scene-Adaptive Tone Mapping for High-Dynamic Range Object Detection
  30. Robust Fast Adaptation from Adversarially Explicit Task Distribution Generation
  31. SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models
  32. Street Gaussians Without 3D Object Tracker
  33. Towards Understanding How Knowledge Evolves in Large Vision-Language Models
  34. UNOPose: Unseen Object Pose Estimation with an Unposed RGB-D Reference Image
  35. $\epsilon$-Softmax: Approximating One-Hot Vectors for Mitigating Label Noise
  36. CompetEvo: Towards Morphological Evolution from Competition
  37. D-SCo: Dual-Stream Conditional Diffusion for Monocular Hand-Held Object Reconstruction
  38. Data-free Neural Representation Compression with Riemannian Neural Dynamics
  39. Doubly Mild Generalization for Offline Reinforcement Learning
  40. Event-3DGS: Event-based 3D Reconstruction Using 3D Gaussian Splatting
  41. Expanding Sparse Tuning for Low Memory Usage
  42. FAFA: Frequency-Aware Flow-Aided Self-supervision for Underwater Object Pose Estimation
  43. FaceChain-SuDe: Building Derived Class to Inherit Category Attributes for One-Shot Subject-Driven Generation
  44. KP-RED: Exploiting Semantic Keypoints for Joint 3D Shape Retrieval and Deformation
  45. Kepler codebook
  46. LLM-Empowered State Representation for Reinforcement Learning
  47. LaPose: Laplacian Mixture Shape Modeling for RGB-Based Category-Level Object Pose Estimation
  48. LanPose: Language-Instructed 6D Object Pose Estimation for Robotic Assembly
  49. Learning Pseudo 3D Guidance for View-Consistent Texturing with 2D Diffusion
  50. Learning Scale-Aware Spatio-temporal Implicit Representation for Event-based Motion Deblurring
  51. Local Action-Guided Motion Diffusion Model for Text-to-Motion Generation
  52. MOHO: Learning Single-View Hand-Held Object Reconstruction with Multi-View Occlusion-Aware Supervision
  53. Offline Reinforcement Learning with OOD State Correction and OOD Action Suppression
  54. ParCo: Part-Coordinating Text-to-Motion Synthesis
  55. Parallel Vertex Diffusion for Unified Visual Grounding
  56. Physical-Based Event Camera Simulator
  57. RAPIDFlow: Recurrent Adaptable Pyramids with Iterative Decoding for Efficient Optical Flow Estimation
  58. RaSim: A Range-aware High-fidelity RGB-D Data Simulation Pipeline for Real-world Applications
  59. Recurrent Partial Kernel Network for Efficient Optical Flow Estimation
  60. Rethinking Imbalance in Image Super-Resolution for Efficient Inference
  61. ShapeMatcher: Self-Supervised Joint Shape Canonicalization, Segmentation, Retrieval and Deformation
  62. Stimulate the Potential of Robots via Competition
  63. SynFog: A Photorealistic Synthetic Fog Dataset Based on End-to-End Imaging Simulation for Advancing Real-World Defogging in Autonomous Driving
  64. The Pitfalls and Promise of Conformal Inference Under Adversarial Attacks
  65. Towards Dynamic Message Passing on Graphs
  66. UW-SDF: Exploiting Hybrid Geometric Priors for Neural SDF Reconstruction from Underwater Multi-view Monocular Images
  67. Unleashing the Potential of Large Language Models through Spectral Modulation
  68. Variance-enlarged Poisson Learning for Graph-based Semi-Supervised Learning with Extremely Sparse Labeled Data
  69. Zero-Mean Regularized Spectral Contrastive Learning: Implicitly Mitigating Wrong Connections in Positive-Pair Graphs