PPaperPicks

Jing Yang

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

Venues

Frequent coauthors

Papers

  1. 3DAlign-DAER: Dynamic Attention Policy and Efficient Retrieval Strategy for Fine-grained 3D-Text Alignment at Scale
  2. Cost-Effective Communication: An Auction-based Method for Language Agent Interaction
  3. DMSD: Dual-Modal Semantic Disentanglement for Compositional Zero-Shot Learning
  4. DomainCQA: Crafting Knowledge-Intensive QA from Domain-Specific Charts
  5. HiVA: Self-organized Hierarchical Variable Agent via Goal-driven Semantic-Topological Evolution
  6. Multi-Metric Preference Alignment for Generative Speech Restoration
  7. Nash-Pruned CredMAS: Dynamic Panel Pruning for VLM-MAS using Nash-based Selection and Doubly-Robust Credits
  8. RACC: Regret-Aware Confidence Calibration for Consistent Masked Discrete Diffusion Decoding
  9. RaCoT: Plug-and-Play Contrastive Example Generation Mechanism for Enhanced LLM Reasoning Reliability
  10. Reinforcement Learning for Diffusion LLMs via Energy-Based Gibbs Alignment
  11. Top-Down Semantic Refinement for Image Captioning
  12. Best Foot Forward: Robust Foot Reconstruction in-the-wild
  13. CCG: Rare-Label Prediction via Neural SEM-Driven Causal Game
  14. DAFMSVC: One-Shot Singing Voice Conversion with Dual Attention Mechanism and Flow Matching
  15. Evaluating Cognitive-Behavioral Fixation via Multimodal User Viewing Patterns on Social Media
  16. Exploiting Temporal State Space Sharing for Video Semantic Segmentation
  17. Fixing the Double Penalty in Data-Driven Weather Forecasting Through a Modified Spherical Harmonic Loss Function
  18. GM-DF: Generalized Multi-Scenario Deepfake Detection
  19. Gaussian Head & Shoulders: High Fidelity Neural Upper Body Avatars with Anchor Gaussian Guided Texture Warping
  20. Localized Gaussian Splatting Editing with Contextual Awareness
  21. MGMapNet: Multi-Granularity Representation Learning for End-to-End Vectorized HD Map Construction
    ICLR 2025 · Jing Yang
  22. Position: The Artificial Intelligence and Machine Learning Community Should Adopt a More Transparent and Regulated Peer Review Process
    ICML 2025 · Jing Yang
  23. Pretrained Reversible Generation as Unsupervised Visual Representation Learning
  24. SYM3D: Canonicalizing Triplanes via Symmetry for Single-View 3D Learning
    ICCV 2025 · Jing Yang
  25. Uncover Treasures in DCT: Advancing JPEG Quality Enhancement by Exploiting Latent Correlations
    ICCV 2025 · Jing Yang
  26. AID-DTI: Accelerating High-Fidelity Diffusion Tensor Imaging with Detail-Preserving Model-Based Deep Learning
  27. DiffPortrait3D: Controllable Diffusion for Zero-Shot Portrait View Synthesis
  28. PMET: Precise Model Editing in a Transformer
  29. RobNODDI: Robust NODDI Parameter Estimation with Adaptive Sampling Under Continuous Representation